| Presenter | Papers | Paper URL | Our Slides |
|---|---|---|---|
| Robust | Adversarial Attacks on Graph Structured Data | Faizan [PDF + GaoJi Pdf | |
| Robust | KDD’18 Adversarial Attacks on Neural Networks for Graph Data | Faizan PDF + GaoJi Pdf | |
| Robust | Attacking Binarized Neural Networks | Faizan PDF |
Readings ByTag
Besides using high-level categories, we also use the following detailed tags to label each read post we finished. Click on a tag to see relevant list of readings.
adversarial-examples
adversarial-loss
agi
alphago
amortized
analysis
architecture-search
associative
attention
attribution
autoencoder
autoregressive
auxiliary
backprop
beam
bert
bias
bias-variance
binarization
binary
black-box
blocking
brain
casual
certified-defense
chromatin
cnn
composition
compression
concept
crispr
cryptography
curriculum
data-valuation
denoising
dialog
difference-analysis
differentiation
diffusion
dimension-reduction
discrete
distillation
distributed
dna
domain-adaptation
dynamic
efficiency
ehr
em
embedding
encoder-decoder
expressive
few-shot
forcing
forgetting
fuzzing
gan
gcn
gene-network
generalization
generative
genomics
geometric
graph
graph-attention
graphical-model
hash
heterogeneous
hierarchical
high-dimensional
human-alignment
hyperparameter
image-synthesis
imitation-learning
imputation
influence-functions
infomax
informax
interpretable
invariant
knowledge-graph
language-model
language-processing
learn2learn
loss
low-rank
manifold
markov
matching
matching-net
matrix-completion
memorization
memory
meta-learning
metamorphic
metric-learning
mimic
mobile
model-as-sample
model-criticism
molecule
multi-label
multi-task
mutual-information
neural-programming
neuroscience
nlp
noise
nonparametric
normalization
ntm
optimization
parallel
parsimonious
planning
pointer
privacy
program
propagation
protein
pruning
qa
quantization
random
recommendation
regularization
relational
rl
rna
rnn
robustness
safety
sample-selection
sampling
scalable
secure
semi-supervised
seq2seq
set
shapley
sketch
small-data
software-testing
sparsity
structured
stylometric
submodular
subspace
temporal-difference
text
training
transfer
transfer-learning
trees
tutorial
understanding
vae
value-networks
variational
verification
visualizing
white-box
[1]: adversarial-examples
Table of readings
read on: - 06 Mar 2019
read on: - 02 Dec 2018
| Presenter | Papers | Paper URL | Our Slides |
|---|---|---|---|
| Jennifer | Adversarial Attacks Against Medical Deep Learning Systems | ||
| Jennifer | Adversarial-Playground: A Visualization Suite Showing How Adversarial Examples Fool Deep Learning | ||
| Jennifer | Black-box Generation of Adversarial Text Sequences to Evade Deep Learning Classifiers | ||
| Jennifer | CleverHans | ||
| Ji | Ji-f18-New papers about adversarial attack |
read on: - 20 Nov 2018
| Presenter | Papers | Paper URL | Our Slides |
|---|---|---|---|
| Bill | Adversarial Examples that Fool both Computer Vision and Time-Limited Humans | ||
| Bill | Adversarial Attacks Against Medical Deep Learning Systems | ||
| Bill | TensorFuzz: Debugging Neural Networks with Coverage-Guided Fuzzing | ||
| Bill | Distilling the Knowledge in a Neural Network | ||
| Bill | Defensive Distillation is Not Robust to Adversarial Examples | ||
| Bill | Adversarial Logit Pairing , Harini Kannan, Alexey Kurakin, Ian Goodfellow |
read on: - 03 Aug 2018
| Presenter | Papers | Paper URL | Our Slides |
|---|---|---|---|
| GaoJi | Deep Reinforcement Fuzzing, Konstantin Böttinger, Patrice Godefroid, Rishabh Singh | ||
| GaoJi | Reluplex: An Efficient SMT Solver for Verifying Deep Neural Networks, Guy Katz, Clark Barrett, David Dill, Kyle Julian, Mykel Kochenderfer | ||
| GaoJi | DeepTest: Automated Testing of Deep-Neural-Network-driven Autonomous Cars, Yuchi Tian, Kexin Pei, Suman Jana, Baishakhi Ray | ||
| GaoJi | A few Recent (2018) papers on Black-box Adversarial Attacks, like Prior Convictions: Black-Box Adversarial Attacks with Bandits and Priors 1 | ||
| GaoJi | A few Recent papers of Adversarial Attacks on reinforcement learning, like Adversarial Attacks on Neural Network Policies (Sandy Huang, Nicolas Papernot, Ian Goodfellow, Yan Duan, Pieter Abbeel) | ||
| Testing | DeepXplore: Automated Whitebox Testing of Deep Learning Systems |
read on: - 20 May 2018
| Presenter | Papers | Paper URL | Our Slides |
|---|---|---|---|
| Bill | Seq2Sick: Evaluating the Robustness of Sequence-to-Sequence Models with Adversarial Examples | ||
| Bill | Adversarial Examples for Evaluating Reading Comprehension Systems, Robin Jia, Percy Liang | ||
| Bill | Certified Defenses against Adversarial Examples, Aditi Raghunathan, Jacob Steinhardt, Percy Liang | ||
| Bill | Provably Minimally-Distorted Adversarial Examples, Nicholas Carlini, Guy Katz, Clark Barrett, David L. Dill |
read on: - 12 May 2018
| Presenter | Papers | Paper URL | Our Slides |
|---|---|---|---|
| Bill | Intriguing Properties of Adversarial Examples, Ekin D. Cubuk, Barret Zoph, Samuel S. Schoenholz, Quoc V. Le 1 | ||
| Bill | Adversarial Spheres 2 | ||
| Bill | Adversarial Transformation Networks: Learning to Generate Adversarial Examples, Shumeet Baluja, Ian Fischer 3 | ||
| Bill | Thermometer encoding: one hot way to resist adversarial examples 4 | ||
| Adversarial Logit Pairing , Harini Kannan, Alexey Kurakin, Ian Goodfellow 5 |
read on: - 26 Oct 2017
| Presenter | Papers | Paper URL | Our Slides |
|---|---|---|---|
| Tianlu | Robustness of classifiers: from adversarial to random noise, NIPS16 | PDF 1 | |
| Anant | Blind Attacks on Machine Learners, 2 NIPS16 | ||
| Data Noising as Smoothing in Neural Network Language Models (Ng), ICLR17 3 | |||
| The Robustness of Estimator Composition, NIPS16 4 |
read on: - 23 Oct 2017
| Presenter | Papers | Paper URL | Our Slides |
|---|---|---|---|
| GaoJi | Delving into Transferable Adversarial Examples and Black-box Attacks,ICLR17 1 | ||
| Shijia | On Detecting Adversarial Perturbations, ICLR17 2 | ||
| Anant | Parseval Networks: Improving Robustness to Adversarial Examples, ICML17 3 | ||
| Bargav | Being Robust (in High Dimensions) Can Be Practical, ICML17 4 |
read on: - 19 Jan 2017
| Presenter | Papers | Paper URL | Our Slides |
|---|---|---|---|
| AE | Intriguing properties of neural networks / | ||
| AE | Explaining and Harnessing Adversarial Examples | ||
| AE | Towards Deep Learning Models Resistant to Adversarial Attacks | ||
| AE | DeepFool: a simple and accurate method to fool deep neural networks | ||
| AE | Towards Evaluating the Robustness of Neural Networks by Carlini and Wagner | ||
| Data | Basic Survey of ImageNet - LSVRC competition | URL | |
| Understand | Understanding Black-box Predictions via Influence Functions | ||
| Understand | Deep inside convolutional networks: Visualising image classification models and saliency maps | ||
| Understand | BeenKim, Interpretable Machine Learning, ICML17 Tutorial [^1] | ||
| provable | Provable defenses against adversarial examples via the convex outer adversarial polytope, Eric Wong, J. Zico Kolter, | URL |
Table of readings
read on: - 05 Jul 2020
| Index | Papers | Our Slides |
|---|---|---|
| 1 | BIAS ALSO MATTERS: BIAS ATTRIBUTION FOR DEEP NEURAL NETWORK EXPLANATION | Arsh Survey |
| 2 | Data Shapley: Equitable Valuation of Data for Machine Learning | Arsh Survey |
| What is your data worth? Equitable Valuation of Data | Sanchit Survey | |
| 3 | Neural Network Attributions: A Causal Perspective | Zhe Survey |
| 4 | Defending Against Neural Fake News | Eli Survey |
| 5 | Interpretation of Neural Networks is Fragile | Eli Survey |
| Interpretation of Neural Networks is Fragile | Pan Survey | |
| 6 | Parsimonious Black-Box Adversarial Attacks Via Efficient Combinatorial Optimization | Eli Survey |
| 7 | Retrofitting Word Vectors to Semantic Lexicons | Morris Survey |
| 8 | On Evaluation of Adversarial Perturbations for Sequence-to-Sequence Models | Morris Survey |
| 9 | Towards Deep Learning Models Resistant to Adversarial Attacks | Pan Survey |
| 10 | Robust Attribution Regularization | Pan Survey |
| 11 | Sanity Checks for Saliency Maps | Sanchit Survey |
| 12 | Survey of data generation and evaluation in Interpreting DNN pipelines | Sanchit Survey |
| 13 | Think Architecture First: Benchmarking Deep Learning Interpretability in Time Series Predictions | Sanchit Survey |
| 14 | Universal Adversarial Triggers for Attacking and Analyzing NLP | Sanchit Survey |
| 15 | Apricot: Submodular selection for data summarization in Python | Arsh Survey |
read on: - 10 Dec 2019
| Team INDEX | Title & Link | Tags | Our Slide |
|---|---|---|---|
| T3 | Deletion-Robust Submodular Maximization: Data Summarization with Privacy and Fairness Constraints | submodular, coreset, safety | OurSlide |
| T6 | Decision Boundary Analysis of Adversarial Examples | adversarial-examples | OurSlide |
| T8 | Robustness may be at odds with accuracy | robustness | OurSlide |
| T18 | Towards Reverse-Engineering Black-Box Neural Networks | meta, model-as-sample, safety, privacy | OurSlide |
| T23 | The Odds are Odd: A Statistical Test for Detecting Adversarial Examples | adversarial-examples | OurSlide |
| T25 | Learning how to explain neural networks: PatternNet and PatternAttribution | Attribution, Interpretable | OurSlide |
| T31 | Detecting Statistical Interactions from Neural Network Weights | Interpretable, Relational | OurSlide |
[2]: adversarial-loss
Table of readings
read on: - 11 May 2018
| Presenter | Papers | Paper URL | Our Slides |
|---|---|---|---|
| Chao | Maximizing Subset Accuracy with Recurrent Neural Networks in Multi-label Classification | ||
| Jack | FastXML: A Fast, Accurate and Stable Tree-classifier for eXtreme Multi-label Learning | ||
| BasicMLC | Multi-Label Classification: An Overview | ||
| SPEN | Structured Prediction Energy Networks | ||
| InfNet | Learning Approximate Inference Networks for Structured Prediction | ||
| SPENMLC | Deep Value Networks | ||
| Adversarial | Semantic Segmentation using Adversarial Networks | ||
| EmbedMLC | StarSpace: Embed All The Things! | ||
| deepMLC | CNN-RNN: A Unified Framework for Multi-label Image Classification/ CVPR 2016 | ||
| deepMLC | Order-Free RNN with Visual Attention for Multi-Label Classification / AAAI 2018 |
[3]: agi
Table of readings
read on: - 03 Dec 2022
| Papers | Paper URL | Abstract |
|---|---|---|
| Training language models to follow instructions with human feedback | URL | “further fine-tune this supervised model using reinforcement learning from human feedback. We call the resulting models InstructGPT.” |
| Deep reinforcement learning from human preferences | URL | “explore goals defined in terms of (non-expert) human preferences between pairs of trajectory segments. We show that this approach can effectively solve complex RL tasks without access to the reward function” |
read on: - 03 Jun 2022
Decision Transformer: Reinforcement Learning via Sequence Modeling
- Lili Chen, Kevin Lu, Aravind Rajeswaran, Kimin Lee, Aditya Grover, Michael Laskin, Pieter Abbeel, Aravind Srinivas, Igor Mordatch
- https://arxiv.org/abs/2106.01345
- We introduce a framework that abstracts Reinforcement Learning (RL) as a sequence modeling problem. This allows us to draw upon the simplicity and scalability of the Transformer architecture, and associated advances in language modeling such as GPT-x and BERT. In particular, we present Decision Transformer, an architecture that casts the problem of RL as conditional sequence modeling. Unlike prior approaches to RL that fit value functions or compute policy gradients, Decision Transformer simply outputs the optimal actions by leveraging a causally masked Transformer. By conditioning an autoregressive model on the desired return (reward), past states, and actions, our Decision Transformer model can generate future actions that achieve the desired return. Despite its simplicity, Decision Transformer matches or exceeds the performance of state-of-the-art model-free offline RL baselines on Atari, OpenAI Gym, and Key-to-Door tasks.
Prompting Decision Transformer for Few-Shot Policy Generalization
- Mengdi Xu, Yikang Shen, Shun Zhang, Yuchen Lu, Ding Zhao, Joshua B. Tenenbaum, Chuang Gan
- https://arxiv.org/abs/2206.13499
- Humans can leverage prior experience and learn novel tasks from a handful of demonstrations. In contrast to offline meta-reinforcement learning, which aims to achieve quick adaptation through better algorithm design, we investigate the effect of architecture inductive bias on the few-shot learning capability. We propose a Prompt-based Decision Transformer (Prompt-DT), which leverages the sequential modeling ability of the Transformer architecture and the prompt framework to achieve few-shot adaptation in offline RL. We design the trajectory prompt, which contains segments of the few-shot demonstrations, and encodes task-specific information to guide policy generation. Our experiments in five MuJoCo control benchmarks show that Prompt-DT is a strong few-shot learner without any extra finetuning on unseen target tasks. Prompt-DT outperforms its variants and strong meta offline RL baselines by a large margin with a trajectory prompt containing only a few timesteps. Prompt-DT is also robust to prompt length changes and can generalize to out-of-distribution (OOD) environments.
read on: - 03 May 2022
| Papers | Paper URL | Abstract |
| A Generalist Agent | URL | Gato, works as a multi-modal, multi-task, multi-embodiment generalist policy. The same network with the same weights can play Atari, caption images, chat, stack blocks with a real robot arm and much more, deciding based on its context whether to output text, joint torques, button presses, or other tokens. |
| Why should we prefer offline reinforcement learning over behavioral cloning? ICLR 2022 | URL | natural to ask: when can an offline RL method outperform BC with an equal amount of expert data, even when BC is a natural choice? |
| Uni[MASK]: Unified Inference in Sequential Decision Problems | URL | show how sequential decision making tasks can be thought of in terms of corresponding input maskings, enabling the training of a single model to perform all tasks at once. applies naturally to sequential decision making, where many well-studied tasks like behavior cloning, offline RL, inverse dynamics, and waypoint conditioning correspond to different sequence maskings over a sequence of states, actions, and returns. |
[4]: alphago
Table of readings
read on: - 28 Nov 2017
| Presenter | Papers | Paper URL | Our Slides |
|---|---|---|---|
| Anant | The Predictron: End-to-End Learning and Planning, ICLR17 1 | ||
| ChaoJiang | Szepesvari - Theory of RL 2 | RLSS.pdf + Video | |
| GaoJi | Mastering the game of Go without human knowledge / Nature 2017 3 | ||
| Thomas - Safe Reinforcement Learning | RLSS17.pdf + video | ||
| Sutton - Temporal-Difference Learning | RLSS17.pdf + Video |
[5]: amortized
Table of readings
read on: - 23 Aug 2018
| Presenter | Papers | Paper URL | Our Slides |
|---|---|---|---|
| Arshdeep | The Concrete Distribution: A Continuous Relaxation of Discrete Random Variables, Chris J. Maddison, Andriy Mnih, Yee Whye Teh 1 | ||
| GaoJi | Summary Of Several Autoencoder models | ||
| GaoJi | Latent Constraints: Learning to Generate Conditionally from Unconditional Generative Models, Jesse Engel, Matthew Hoffman, Adam Roberts 2 | ||
| GaoJi | Summary of A Few Recent Papers about Discrete Generative models, SeqGAN, MaskGAN, BEGAN, BoundaryGAN | ||
| Arshdeep | Semi-Amortized Variational Autoencoders, Yoon Kim, Sam Wiseman, Andrew C. Miller, David Sontag, Alexander M. Rush 3 | ||
| Arshdeep | Synthesizing Programs for Images using Reinforced Adversarial Learning, Yaroslav Ganin, Tejas Kulkarni, Igor Babuschkin, S.M. Ali Eslami, Oriol Vinyals 4 |
[6]: analysis
Table of readings
read on: - 12 Dec 2019
| Team INDEX | Title & Link | Tags | Our Slide |
|---|---|---|---|
| T2 | Empirical Study of Example Forgetting During Deep Neural Network Learning | Sample Selection, forgetting | OurSlide |
| T29 | Select Via Proxy: Efficient Data Selection For Training Deep Networks | Sample Selection | OurSlide |
| T9 | How SGD Selects the Global Minima in over-parameterized Learning | optimization | OurSlide |
| T10 | Escaping Saddles with Stochastic Gradients | optimization | OurSlide |
| T13 | To What Extent Do Different Neural Networks Learn the Same Representation | subspace | OurSlide |
| T19 | On the Information Bottleneck Theory of Deep Learning | informax | OurSlide |
| T20 | Visualizing the Loss Landscape of Neural Nets | normalization | OurSlide |
| T21 | Using Pre-Training Can Improve Model Robustness and Uncertainty | training, analysis | OurSlide |
| T24 | Norm matters: efficient and accurate normalization schemes in deep networks | normalization | OurSlide |
[7]: architecture-search
Table of readings
read on: - 02 Nov 2017
| Presenter | Papers | Paper URL | Our Slides |
|---|---|---|---|
| GaoJi | Neural Architecture Search with Reinforcement Learning, ICLR17 1 | ||
| Ceyer | Learning to learn 2 | DLSS17video | |
| Beilun | Optimization as a Model for Few-Shot Learning, ICLR17 3 | PDF + More | |
| Anant | Neural Optimizer Search with Reinforcement Learning, ICML17 4 |
read on: - 05 Oct 2017
| Presenter | Papers | Paper URL | Our Slides |
|---|---|---|---|
| Anant | AdaNet: Adaptive Structural Learning of Artificial Neural Networks, ICML17 1 | ||
| Shijia | SplitNet: Learning to Semantically Split Deep Networks for Parameter Reduction and Model Parallelization, ICML17 2 | ||
| Jack | Proximal Deep Structured Models, NIPS16 3 | ||
| Optimal Architectures in a Solvable Model of Deep Networks, NIPS16 4 | |||
| Tianlu | Large-Scale Evolution of Image Classifiers, ICML17 5 |
Table of readings
read on: - 25 Oct 2018
| Presenter | Papers | Paper URL | Our Slides |
|---|---|---|---|
| Arshdeep | Learning Transferable Architectures for Scalable Image Recognition | ||
| Arshdeep | FractalNet: Ultra-Deep Neural Networks without Residuals |
read on: - 07 Nov 2017
| Presenter | Papers | Paper URL | Our Slides |
|---|---|---|---|
| GaoJi | Forward and Reverse Gradient-Based Hyperparameter Optimization, ICML17 1 | ||
| Chaojiang | Adaptive Neural Networks for Efficient Inference, ICML17 2 | ||
| Bargav | Practical Gauss-Newton Optimisation for Deep Learning, ICML17 3 | ||
| Rita | How to Escape Saddle Points Efficiently, ICML17 4 | ||
| Batched High-dimensional Bayesian Optimization via Structural Kernel Learning |
[8]: associative
Table of readings
[9]: attention
Table of readings
read on: - 05 Aug 2020
| Index | Papers | Our Slides |
|---|---|---|
| 0 | A survey on Interpreting Deep Learning Models | Eli Survey |
| Interpretable Machine Learning: Definitions,Methods, Applications | Arsh Survey | |
| 1 | Explaining Explanations: Axiomatic Feature Interactions for Deep Networks | Arsh Survey |
| 2 | Shapley Value review | Arsh Survey |
| L-Shapley and C-Shapley: Efficient Model Interpretation for Structured Data | Bill Survey | |
| Consistent Individualized Feature Attribution for Tree Ensembles | bill Survey | |
| Summary for A value for n-person games | Pan Survey | |
| L-Shapley and C-Shapley: Efficient Model Interpretation for Structured Data | Rishab Survey | |
| 3 | Hierarchical Interpretations of Neural Network Predictions | Arsh Survey |
| Hierarchical Interpretations of Neural Network Predictions | Rishab Survey | |
| 4 | Beyond Word Importance: Contextual Decomposition to Extract Interactions from LSTMs | Arsh Survey |
| Beyond Word Importance: Contextual Decomposition to Extract Interactions from LSTMs | Rishab Survey | |
| 5 | Towards Hierarchical Importance Attribution: Explaining Compositional Semantics for Neural Sequence Models | Rishab Survey |
| Sanchit Survey | ||
| Generating Hierarchical Explanations on Text Classification via Feature Interaction Detection | Sanchit Survey | |
| 6 | This Looks Like That: Deep Learning for Interpretable Image Recognition | Pan Survey |
| 7 | AllenNLP Interpret | Rishab Survey |
| 8 | DISCOVERY OF NATURAL LANGUAGE CONCEPTS IN INDIVIDUAL UNITS OF CNNs | Rishab Survey |
| 9 | How Does BERT Answer Questions? A Layer-Wise Analysis of Transformer Representations | Rishab Survey |
| 10 | Attention is not Explanation | Sanchit Survey |
| Pan Survey | ||
| 11 | Axiomatic Attribution for Deep Networks | Sanchit Survey |
| 12 | Grad-CAM: Visual Explanations from Deep Networks via Gradient-based Localization | Sanchit Survey |
| 13 | Learning Variational Word Masks to Improve the Interpretability of Neural Text Classifier | Sanchit Survey |
| 14 | “Why Should I Trust You?”Explaining the Predictions of Any Classifier | Yu Survey |
| 15 | INTERPRETATIONS ARE USEFUL: PENALIZING EXPLANATIONS TO ALIGN NEURAL NETWORKS WITH PRIOR KNOWLEDGE | Pan Survey |
read on: - 05 Apr 2019
| Presenter | Papers | Paper URL | Our Slides |
|---|---|---|---|
| Understand | Faithful and Customizable Explanations of Black Box Models | Derrick PDF | |
| Understand | A causal framework for explaining the predictions of black-box sequence-to-sequence models, EMNLP17 | GaoJi PDF + Bill Pdf | |
| Understand | How Powerful are Graph Neural Networks? / Deeper Insights into Graph Convolutional Networks for Semi-Supervised Learning | Pdf + Pdf | GaoJi PDF |
| Understand | Interpretable Graph Convolutional Neural Networks for Inference on Noisy Knowledge Graphs + GNN Explainer: A Tool for Post-hoc Explanation of Graph Neural Networks | Pdf + PDF | GaoJi PDF |
| Understand | Attention is not Explanation, 2019 | ||
| Understand | Understanding attention in graph neural networks, 2019 |
read on: - 15 Feb 2019
| Presenter | Papers | Paper URL | Our Slides |
|---|---|---|---|
| Bio | KDEEP: Protein–Ligand Absolute Binding Affinity Prediction via 3D-Convolutional Neural Networks, 2018 1 | Eli Pdf | |
| Bio | Molecular geometry prediction using a deep generative graph neural network | Eli Pdf | |
| Bio | Visualizing convolutional neural network protein-ligand scoring | PDF() | Eli PDF |
| Bio | Deep generative models of genetic variation capture mutation effects | PDF() | Eli PDF |
| Bio | Attentive cross-modal paratope prediction | Eli PDF |
read on: - 11 May 2018
| Presenter | Papers | Paper URL | Our Slides |
|---|---|---|---|
| Chao | Maximizing Subset Accuracy with Recurrent Neural Networks in Multi-label Classification | ||
| Jack | FastXML: A Fast, Accurate and Stable Tree-classifier for eXtreme Multi-label Learning | ||
| BasicMLC | Multi-Label Classification: An Overview | ||
| SPEN | Structured Prediction Energy Networks | ||
| InfNet | Learning Approximate Inference Networks for Structured Prediction | ||
| SPENMLC | Deep Value Networks | ||
| Adversarial | Semantic Segmentation using Adversarial Networks | ||
| EmbedMLC | StarSpace: Embed All The Things! | ||
| deepMLC | CNN-RNN: A Unified Framework for Multi-label Image Classification/ CVPR 2016 | ||
| deepMLC | Order-Free RNN with Visual Attention for Multi-Label Classification / AAAI 2018 |
read on: - 03 May 2018
| Presenter | Papers | Paper URL | Our Slides |
|---|---|---|---|
| Arshdeep | Show, Attend and Tell: Neural Image Caption Generation with Visual Attention 1 | ||
| Arshdeep | Latent Alignment and Variational Attention 2 | ||
| Arshdeep | Modularity Matters: Learning Invariant Relational Reasoning Tasks, Jason Jo, Vikas Verma, Yoshua Bengio 3 |
read on: - 14 Nov 2017
| Presenter | Papers | Paper URL | Our Slides |
|---|---|---|---|
| ChaoJiang | Courville - Generative Models II | DLSS17Slide + video | |
| GaoJi | Attend, Infer, Repeat: Fast Scene Understanding with Generative Models, NIPS16 1 | PDF + talk | |
| Arshdeep | Composing graphical models with neural networks for structured representations and fast inference, NIPS16 2 | ||
| Johnson - Graphical Models and Deep Learning | DLSSSlide + video | ||
| Parallel Multiscale Autoregressive Density Estimation, ICML17 3 | |||
| Beilun | Conditional Image Generation with Pixel CNN Decoders, NIPS16 4 | ||
| Shijia | Marrying Graphical Models & Deep Learning | DLSS17 + Video |
read on: - 28 Sep 2017
| Presenter | Papers | Paper URL | Our Slides |
|---|---|---|---|
| Jack | Attend, Adapt and Transfer: Attentive Deep Architecture for Adaptive Transfer from multiple sources in the same domain, ICLR17 1 | ||
| Arshdeep | Bidirectional Attention Flow for Machine Comprehension, ICLR17 2 | PDF + code | |
| Ceyer | Image-to-Markup Generation with Coarse-to-Fine Attention, ICML17 | PDF + code | |
| ChaoJiang | Can Active Memory Replace Attention? ; Samy Bengio, NIPS16 3 | ||
| An Information-Theoretic Framework for Fast and Robust Unsupervised Learning via Neural Population Infomax, ICLR17 |
read on: - 26 Sep 2017
| Presenter | Papers | Paper URL | Our Slides |
|---|---|---|---|
| Rita | Paying More Attention to Attention: Improving the Performance of Convolutional Neural Networks via Attention Transfer, ICLR17 1 | ||
| Tianlu | Dynamic Coattention Networks For Question Answering, ICLR17 2 | PDF + code | |
| ChaoJiang | Structured Attention Networks, ICLR17 3 | PDF + code |
read on: - 18 Jan 2017
| Presenter | Papers | Paper URL | Our Slides |
|---|---|---|---|
| seq2seq | Sequence to Sequence Learning with Neural Networks | ||
| Set | Pointer Networks | ||
| Set | Order Matters: Sequence to Sequence for Sets | ||
| Point Attention | Multiple Object Recognition with Visual Attention | ||
| Memory | End-To-End Memory Networks | Jack Survey | |
| Memory | Neural Turing Machines | ||
| Memory | Hybrid computing using a neural network with dynamic external memory | ||
| Muthu | Matching Networks for One Shot Learning (NIPS16) 1 | ||
| Jack | Meta-Learning with Memory-Augmented Neural Networks (ICML16) 2 | ||
| Metric | ICML07 Best Paper - Information-Theoretic Metric Learning |
read on: - 12 Jan 2017
| Presenter | Papers | Paper URL | Our Slides |
|---|---|---|---|
| NLP | A Neural Probabilistic Language Model | ||
| Text | Bag of Tricks for Efficient Text Classification | ||
| Text | Character-level Convolutional Networks for Text Classification | ||
| NLP | BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding | ||
| seq2seq | Neural Machine Translation by Jointly Learning to Align and Translate | ||
| NLP | Natural Language Processing (almost) from Scratch | ||
| Train | Curriculum learning | ||
| Muthu | NeuroIPS Embedding Papers survey 2012 to 2015 | NIPS | |
| Basics | Efficient BackProp |
[10]: attribution
Table of readings
read on: - 10 Dec 2019
| Team INDEX | Title & Link | Tags | Our Slide |
|---|---|---|---|
| T3 | Deletion-Robust Submodular Maximization: Data Summarization with Privacy and Fairness Constraints | submodular, coreset, safety | OurSlide |
| T6 | Decision Boundary Analysis of Adversarial Examples | adversarial-examples | OurSlide |
| T8 | Robustness may be at odds with accuracy | robustness | OurSlide |
| T18 | Towards Reverse-Engineering Black-Box Neural Networks | meta, model-as-sample, safety, privacy | OurSlide |
| T23 | The Odds are Odd: A Statistical Test for Detecting Adversarial Examples | adversarial-examples | OurSlide |
| T25 | Learning how to explain neural networks: PatternNet and PatternAttribution | Attribution, Interpretable | OurSlide |
| T31 | Detecting Statistical Interactions from Neural Network Weights | Interpretable, Relational | OurSlide |
read on: - 12 Oct 2018
| Presenter | Papers | Paper URL | Our Slides |
|---|---|---|---|
| Jack | A Unified Approach to Interpreting Model Predictions | ||
| Jack | “Why Should I Trust You?”: Explaining the Predictions of Any Classifier | ||
| Jack | Visual Feature Attribution using Wasserstein GANs | ||
| Jack | GAN Dissection: Visualizing and Understanding Generative Adversarial Networks | ||
| GaoJi | Recent Interpretable machine learning papers | ||
| Jennifer | The Building Blocks of Interpretability |
read on: - 11 Oct 2017
| Presenter | Papers | Paper URL | Our Slides |
|---|---|---|---|
| Rita | Visualizing Deep Neural Network Decisions: Prediction Difference Analysis, ICLR17 1 | ||
| Arshdeep | Axiomatic Attribution for Deep Networks, ICML17 2 | ||
| The Robustness of Estimator Composition, NIPS16 |
read on: - 10 Oct 2017
| Presenter | Papers | Paper URL | Our Slides |
|---|---|---|---|
| Rita | Learning Important Features Through Propagating Activation Differences, ICML17 1 | ||
| GaoJi | Examples are not Enough, Learn to Criticize! Model Criticism for Interpretable Machine Learning, NIPS16 2 | ||
| Rita | Learning Kernels with Random Features, Aman Sinha*; John Duchi, 3 |
[11]: autoencoder
Table of readings
read on: - 15 Mar 2019
| Presenter | Papers | Paper URL | Our Slides |
|---|---|---|---|
| Generate | Maximum-Likelihood Augmented Discrete Generative Adversarial Networks | Tkach PDF + GaoJi Pdf | |
| Generate | Graphical Generative Adversarial Networks | Arshdeep PDF | |
| Generate | GraphRNN: Generating Realistic Graphs with Deep Auto-regressive Models, ICML2018 | Arshdeep PDF | |
| Generate | Inference in probabilistic graphical models by Graph Neural Networks | Arshdeep PDF | |
| Generate | Encoding robust representation for graph generation | Arshdeep PDF | |
| Generate | Junction Tree Variational Autoencoder for Molecular Graph Generation | Tkach PDF + Arshdeep Pdf | |
| Generate | Graph Convolutional Policy Network for Goal-Directed Molecular Graph Generation NeurIPS18 | Tkach PDF | |
| Generate | Towards Variational Generation of Small Graphs | Tkach PDF + Arshdeep Pdf | |
| Generate | Convolutional Imputation of Matrix Networks | Tkach PDF | |
| Generate | Graph Convolutional Matrix Completion | Tkach PDF | |
| Generate | NetGAN: Generating Graphs via Random Walks ICML18 | [ULR] | Tkach PDF |
| Beam | Stochastic Beams and Where to Find Them: The Gumbel-Top-k Trick for Sampling Sequences Without Replacement | URL | Tkach PDF |
read on: - 29 Dec 2018
| Presenter | Papers | Paper URL | Our Slides |
|---|---|---|---|
| Tkach | Boundary-Seeking Generative Adversarial Networks | ||
| Tkach | Maximum-Likelihood Augmented Discrete Generative Adversarial Networks | ||
| Tkach | Generating Sentences from a Continuous Space |
read on: - 21 Dec 2018
| Presenter | Papers | Paper URL | Our Slides |
|---|---|---|---|
| Arshdeep | Constrained Graph Variational Autoencoders for Molecule Design | ||
| Arshdeep | Learning Deep Generative Models of Graphs | ||
| Arshdeep | Graph Convolutional Policy Network for Goal-Directed Molecular Graph Generation | ||
| Jack | Generating and designing DNA with deep generative models |
read on: - 23 Aug 2018
| Presenter | Papers | Paper URL | Our Slides |
|---|---|---|---|
| Arshdeep | The Concrete Distribution: A Continuous Relaxation of Discrete Random Variables, Chris J. Maddison, Andriy Mnih, Yee Whye Teh 1 | ||
| GaoJi | Summary Of Several Autoencoder models | ||
| GaoJi | Latent Constraints: Learning to Generate Conditionally from Unconditional Generative Models, Jesse Engel, Matthew Hoffman, Adam Roberts 2 | ||
| GaoJi | Summary of A Few Recent Papers about Discrete Generative models, SeqGAN, MaskGAN, BEGAN, BoundaryGAN | ||
| Arshdeep | Semi-Amortized Variational Autoencoders, Yoon Kim, Sam Wiseman, Andrew C. Miller, David Sontag, Alexander M. Rush 3 | ||
| Arshdeep | Synthesizing Programs for Images using Reinforced Adversarial Learning, Yaroslav Ganin, Tejas Kulkarni, Igor Babuschkin, S.M. Ali Eslami, Oriol Vinyals 4 |
[12]: autoregressive
Table of readings
read on: - 14 Nov 2017
| Presenter | Papers | Paper URL | Our Slides |
|---|---|---|---|
| ChaoJiang | Courville - Generative Models II | DLSS17Slide + video | |
| GaoJi | Attend, Infer, Repeat: Fast Scene Understanding with Generative Models, NIPS16 1 | PDF + talk | |
| Arshdeep | Composing graphical models with neural networks for structured representations and fast inference, NIPS16 2 | ||
| Johnson - Graphical Models and Deep Learning | DLSSSlide + video | ||
| Parallel Multiscale Autoregressive Density Estimation, ICML17 3 | |||
| Beilun | Conditional Image Generation with Pixel CNN Decoders, NIPS16 4 | ||
| Shijia | Marrying Graphical Models & Deep Learning | DLSS17 + Video |
[13]: auxiliary
Table of readings
read on: - 30 Nov 2017
| Presenter | Papers | Paper URL | Our Slides |
|---|---|---|---|
| Ceyer | Reinforcement Learning with Unsupervised Auxiliary Tasks, ICLR17 1 | ||
| Beilun | Why is Posterior Sampling Better than Optimism for Reinforcement Learning? Ian Osband, Benjamin Van Roy 2 | ||
| Ji | Deeply AggreVaTeD: Differentiable Imitation Learning for Sequential Prediction, ICML17 3 | ||
| Xueying | End-to-End Differentiable Adversarial Imitation Learning, ICML17 4 | ||
| Deep Value Networks Learn to Evaluate and Iteratively Refine Structured Outputs, ICML17 | |||
| FeUdal Networks for Hierarchical Reinforcement Learning, ICML17 5 |
[14]: backprop
Table of readings
read on: - 12 Jan 2017
| Presenter | Papers | Paper URL | Our Slides |
|---|---|---|---|
| NLP | A Neural Probabilistic Language Model | ||
| Text | Bag of Tricks for Efficient Text Classification | ||
| Text | Character-level Convolutional Networks for Text Classification | ||
| NLP | BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding | ||
| seq2seq | Neural Machine Translation by Jointly Learning to Align and Translate | ||
| NLP | Natural Language Processing (almost) from Scratch | ||
| Train | Curriculum learning | ||
| Muthu | NeuroIPS Embedding Papers survey 2012 to 2015 | NIPS | |
| Basics | Efficient BackProp |
[15]: beam
Table of readings
read on: - 15 Mar 2019
| Presenter | Papers | Paper URL | Our Slides |
|---|---|---|---|
| Generate | Maximum-Likelihood Augmented Discrete Generative Adversarial Networks | Tkach PDF + GaoJi Pdf | |
| Generate | Graphical Generative Adversarial Networks | Arshdeep PDF | |
| Generate | GraphRNN: Generating Realistic Graphs with Deep Auto-regressive Models, ICML2018 | Arshdeep PDF | |
| Generate | Inference in probabilistic graphical models by Graph Neural Networks | Arshdeep PDF | |
| Generate | Encoding robust representation for graph generation | Arshdeep PDF | |
| Generate | Junction Tree Variational Autoencoder for Molecular Graph Generation | Tkach PDF + Arshdeep Pdf | |
| Generate | Graph Convolutional Policy Network for Goal-Directed Molecular Graph Generation NeurIPS18 | Tkach PDF | |
| Generate | Towards Variational Generation of Small Graphs | Tkach PDF + Arshdeep Pdf | |
| Generate | Convolutional Imputation of Matrix Networks | Tkach PDF | |
| Generate | Graph Convolutional Matrix Completion | Tkach PDF | |
| Generate | NetGAN: Generating Graphs via Random Walks ICML18 | [ULR] | Tkach PDF |
| Beam | Stochastic Beams and Where to Find Them: The Gumbel-Top-k Trick for Sampling Sequences Without Replacement | URL | Tkach PDF |
[16]: bert
Table of readings
read on: - 07 Dec 2019
| Team INDEX | Title & Link | Tags | Our Slide |
|---|---|---|---|
| T11 | Parameter-Efficient Transfer Learning for NLP | meta, BERT, text, Transfer | OurSlide |
| T22 | Deep Asymmetric Multi-task Feature Learning | meta, regularization, Multi-task | OurSlide |
read on: - 12 Jan 2017
| Presenter | Papers | Paper URL | Our Slides |
|---|---|---|---|
| NLP | A Neural Probabilistic Language Model | ||
| Text | Bag of Tricks for Efficient Text Classification | ||
| Text | Character-level Convolutional Networks for Text Classification | ||
| NLP | BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding | ||
| seq2seq | Neural Machine Translation by Jointly Learning to Align and Translate | ||
| NLP | Natural Language Processing (almost) from Scratch | ||
| Train | Curriculum learning | ||
| Muthu | NeuroIPS Embedding Papers survey 2012 to 2015 | NIPS | |
| Basics | Efficient BackProp |
[17]: bias
Table of readings
read on: - 05 Jul 2020
| Index | Papers | Our Slides |
|---|---|---|
| 1 | BIAS ALSO MATTERS: BIAS ATTRIBUTION FOR DEEP NEURAL NETWORK EXPLANATION | Arsh Survey |
| 2 | Data Shapley: Equitable Valuation of Data for Machine Learning | Arsh Survey |
| What is your data worth? Equitable Valuation of Data | Sanchit Survey | |
| 3 | Neural Network Attributions: A Causal Perspective | Zhe Survey |
| 4 | Defending Against Neural Fake News | Eli Survey |
| 5 | Interpretation of Neural Networks is Fragile | Eli Survey |
| Interpretation of Neural Networks is Fragile | Pan Survey | |
| 6 | Parsimonious Black-Box Adversarial Attacks Via Efficient Combinatorial Optimization | Eli Survey |
| 7 | Retrofitting Word Vectors to Semantic Lexicons | Morris Survey |
| 8 | On Evaluation of Adversarial Perturbations for Sequence-to-Sequence Models | Morris Survey |
| 9 | Towards Deep Learning Models Resistant to Adversarial Attacks | Pan Survey |
| 10 | Robust Attribution Regularization | Pan Survey |
| 11 | Sanity Checks for Saliency Maps | Sanchit Survey |
| 12 | Survey of data generation and evaluation in Interpreting DNN pipelines | Sanchit Survey |
| 13 | Think Architecture First: Benchmarking Deep Learning Interpretability in Time Series Predictions | Sanchit Survey |
| 14 | Universal Adversarial Triggers for Attacking and Analyzing NLP | Sanchit Survey |
| 15 | Apricot: Submodular selection for data summarization in Python | Arsh Survey |
[18]: bias-variance
Table of readings
[19]: binarization
Table of readings
read on: - 06 Dec 2019
| Team INDEX | Title & Link | Tags | Our Slide |
|---|---|---|---|
| T33 | The High-Dimensional Geometry of Binary Neural Networks | Quantization, binarization, scalable | OurSlide |
| T34 | Modern Neural Networks Generalize on Small Data Sets | small-data, analysis, ensemble | OurSlide |
| T4 | Cognitive Scheduler for Heterogeneous High Performance Computing System | system-application | OurSlide |
[20]: binary
Table of readings
read on: - 25 Mar 2019
| Presenter | Papers | Paper URL | Our Slides |
|---|---|---|---|
| Edge | MobileNets: Efficient Convolutional Neural Networks for Mobile Vision Applications | ||
| Edge | XNOR-Net: ImageNet Classification Using Binary Convolutional Neural Networks | URL | Ryan PDF |
| Edge | DeepX: A Software Accelerator for Low-Power Deep Learning Inference on Mobile Devices | Eamon PDF | |
| Edge | Loss-aware Binarization of Deep Networks, ICLR17 | Ryan PDF | |
| Edge | Espresso: Efficient Forward Propagation for Binary Deep Neural Networks | Eamon PDF | |
| Dynamic | Drop an Octave: Reducing Spatial Redundancy in Convolutional Neural Networks with Octave Convolution | Weilin PDF | |
| Dynamic | Dynamic Scheduling For Dynamic Control Flow in Deep Learning Systems | ||
| Dynamic | Cavs: An Efficient Runtime System for Dynamic Neural Networks |
read on: - 06 Mar 2019
| Presenter | Papers | Paper URL | Our Slides |
|---|---|---|---|
| Robust | Adversarial Attacks on Graph Structured Data | Faizan [PDF + GaoJi Pdf | |
| Robust | KDD’18 Adversarial Attacks on Neural Networks for Graph Data | Faizan PDF + GaoJi Pdf | |
| Robust | Attacking Binarized Neural Networks | Faizan PDF |
read on: - 22 Jun 2017
| Presenter | Papers | Paper URL | Our Slides |
|---|---|---|---|
| Arshdeep | Image Question Answering using Convolutional Neural Network with Dynamic Parameter Prediction 1 | ||
| Arshdeep | Decoupled Neural Interfaces Using Synthetic Gradients 2 | ||
| Arshdeep | Diet Networks: Thin Parameters for Fat Genomics 3 | ||
| Arshdeep | Metric Learning with Adaptive Density Discrimination 4 |
read on: - 02 Jun 2017
| Presenter | Papers | Paper URL | Our Slides |
|---|---|---|---|
| Arshdeep | HyperNetworks, David Ha, Andrew Dai, Quoc V. Le ICLR 2017 1 | ||
| Arshdeep | Learning feed-forward one-shot learners 2 | ||
| Arshdeep | Learning to Learn by gradient descent by gradient descent 3 | ||
| Arshdeep | Dynamic Filter Networks 4 https://arxiv.org/abs/1605.09673 |
read on: - 21 Jan 2017
| Presenter | Papers | Paper URL | Our Slides |
|---|---|---|---|
| DeepBind | Predicting the sequence specificities of DNA- and RNA-binding proteins by deep learning | ||
| DeepSEA | Deep learning sequence-based ab initio prediction of variant effects on expression and disease risk | ||
| DeepSEA | Deep Supervised and Convolutional Generative Stochastic Network for Protein Secondary Structure Prediction, ICML 2014 | ||
| BioBasics | A method for integrating and ranking the evidence for biochemical pathways by mining reactions from text, Bioinformatics13 | ||
| BioBasics | Efficient counting of k-mers in DNA sequences using a Bloom filter. Melsted P, Pritchard JK. BMC Bioinformatics. 2011 | ||
| BioBasics | Fast String Kernels using Inexact Matching for Protein Sequence, JMLR 2004 | ||
| BioBasics | NIPS09: Locality-Sensitive Binary Codes from Shift-Invariant Kernels | ||
| MedSignal | Segmenting Time Series: A Survey and Novel Approach, |
read on: - 20 Jan 2017
| Presenter | Papers | Paper URL | Our Slides |
|---|---|---|---|
| scalable | Sanjiv Kumar (Columbia EECS 6898), Lecture: Introduction to large-scale machine learning 2010 [^1] | ||
| data scalable | Alex Smola - Berkeley SML: Scalable Machine Learning: Syllabus 2012 [^2] | PDF 2014 + PDF | |
| Binary | Binarized Neural Networks: Training Deep Neural Networks with Weights and Activations Constrained to +1 or -1 | ||
| Model | Binary embeddings with structured hashed projections 1 | ||
| Model | Deep Compression: Compressing Deep Neural Networks (ICLR 2016) 2 |
[21]: black-box
Table of readings
read on: - 05 Aug 2020
| Index | Papers | Our Slides |
|---|---|---|
| 0 | A survey on Interpreting Deep Learning Models | Eli Survey |
| Interpretable Machine Learning: Definitions,Methods, Applications | Arsh Survey | |
| 1 | Explaining Explanations: Axiomatic Feature Interactions for Deep Networks | Arsh Survey |
| 2 | Shapley Value review | Arsh Survey |
| L-Shapley and C-Shapley: Efficient Model Interpretation for Structured Data | Bill Survey | |
| Consistent Individualized Feature Attribution for Tree Ensembles | bill Survey | |
| Summary for A value for n-person games | Pan Survey | |
| L-Shapley and C-Shapley: Efficient Model Interpretation for Structured Data | Rishab Survey | |
| 3 | Hierarchical Interpretations of Neural Network Predictions | Arsh Survey |
| Hierarchical Interpretations of Neural Network Predictions | Rishab Survey | |
| 4 | Beyond Word Importance: Contextual Decomposition to Extract Interactions from LSTMs | Arsh Survey |
| Beyond Word Importance: Contextual Decomposition to Extract Interactions from LSTMs | Rishab Survey | |
| 5 | Towards Hierarchical Importance Attribution: Explaining Compositional Semantics for Neural Sequence Models | Rishab Survey |
| Sanchit Survey | ||
| Generating Hierarchical Explanations on Text Classification via Feature Interaction Detection | Sanchit Survey | |
| 6 | This Looks Like That: Deep Learning for Interpretable Image Recognition | Pan Survey |
| 7 | AllenNLP Interpret | Rishab Survey |
| 8 | DISCOVERY OF NATURAL LANGUAGE CONCEPTS IN INDIVIDUAL UNITS OF CNNs | Rishab Survey |
| 9 | How Does BERT Answer Questions? A Layer-Wise Analysis of Transformer Representations | Rishab Survey |
| 10 | Attention is not Explanation | Sanchit Survey |
| Pan Survey | ||
| 11 | Axiomatic Attribution for Deep Networks | Sanchit Survey |
| 12 | Grad-CAM: Visual Explanations from Deep Networks via Gradient-based Localization | Sanchit Survey |
| 13 | Learning Variational Word Masks to Improve the Interpretability of Neural Text Classifier | Sanchit Survey |
| 14 | “Why Should I Trust You?”Explaining the Predictions of Any Classifier | Yu Survey |
| 15 | INTERPRETATIONS ARE USEFUL: PENALIZING EXPLANATIONS TO ALIGN NEURAL NETWORKS WITH PRIOR KNOWLEDGE | Pan Survey |
read on: - 05 Apr 2019
| Presenter | Papers | Paper URL | Our Slides |
|---|---|---|---|
| Understand | Faithful and Customizable Explanations of Black Box Models | Derrick PDF | |
| Understand | A causal framework for explaining the predictions of black-box sequence-to-sequence models, EMNLP17 | GaoJi PDF + Bill Pdf | |
| Understand | How Powerful are Graph Neural Networks? / Deeper Insights into Graph Convolutional Networks for Semi-Supervised Learning | Pdf + Pdf | GaoJi PDF |
| Understand | Interpretable Graph Convolutional Neural Networks for Inference on Noisy Knowledge Graphs + GNN Explainer: A Tool for Post-hoc Explanation of Graph Neural Networks | Pdf + PDF | GaoJi PDF |
| Understand | Attention is not Explanation, 2019 | ||
| Understand | Understanding attention in graph neural networks, 2019 |
read on: - 03 Aug 2018
| Presenter | Papers | Paper URL | Our Slides |
|---|---|---|---|
| GaoJi | Deep Reinforcement Fuzzing, Konstantin Böttinger, Patrice Godefroid, Rishabh Singh | ||
| GaoJi | Reluplex: An Efficient SMT Solver for Verifying Deep Neural Networks, Guy Katz, Clark Barrett, David Dill, Kyle Julian, Mykel Kochenderfer | ||
| GaoJi | DeepTest: Automated Testing of Deep-Neural-Network-driven Autonomous Cars, Yuchi Tian, Kexin Pei, Suman Jana, Baishakhi Ray | ||
| GaoJi | A few Recent (2018) papers on Black-box Adversarial Attacks, like Prior Convictions: Black-Box Adversarial Attacks with Bandits and Priors 1 | ||
| GaoJi | A few Recent papers of Adversarial Attacks on reinforcement learning, like Adversarial Attacks on Neural Network Policies (Sandy Huang, Nicolas Papernot, Ian Goodfellow, Yan Duan, Pieter Abbeel) | ||
| Testing | DeepXplore: Automated Whitebox Testing of Deep Learning Systems |
read on: - 14 Sep 2017
| Presenter | Papers | Paper URL | Our Slides |
|---|---|---|---|
| SE | Equivariance Through Parameter-Sharing, ICML17 1 | ||
| SE | Why Deep Neural Networks for Function Approximation?, ICLR17 2 | ||
| SE | Geometry of Neural Network Loss Surfaces via Random Matrix Theory, 3ICML17 | ||
| Sharp Minima Can Generalize For Deep Nets, ICML17 4 |
read on: - 12 Sep 2017
| Presenter | Papers | Paper URL | Our Slides |
|---|---|---|---|
| Ceyer | A Closer Look at Memorization in Deep Networks, ICML17 1 | ||
| On the Expressive Efficiency of Overlapping Architectures of Deep Learning 2 | DLSSpdf + video | ||
| Mutual Information | Opening the Black Box of Deep Neural Networks via Information 3 | URL + video | |
| ChaoJiang | Toward Deeper Understanding of Neural Networks: The Power of Initialization and a Dual View on Expressivity, NIPS16 |
read on: - 07 Sep 2017
| Presenter | Papers | Paper URL | Our Slides |
|---|---|---|---|
| Beilun | Learning Deep Parsimonious Representations, NIPS16 1 | ||
| Jack | Dense Associative Memory for Pattern Recognition, NIPS16 2 | PDF + video |
read on: - 05 Sep 2017
| Presenter | Papers | Paper URL | Our Slides |
|---|---|---|---|
| Rita | On the Expressive Power of Deep Neural Networks 1 | ||
| Arshdeep | Understanding deep learning requires rethinking generalization, ICLR17 2 | ||
| Tianlu | On Large-Batch Training for Deep Learning: Generalization Gap and Sharp Minima, ICLR17 3 |
read on: - 22 Jul 2017
| Presenter | Papers | Paper URL | Our Slides |
|---|---|---|---|
| GaoJi | A few useful things to know about machine learning | ||
| GaoJi | A few papers related to testing learning, e.g., Understanding Black-box Predictions via Influence Functions | ||
| GaoJi | Automated White-box Testing of Deep Learning Systems 1 | ||
| GaoJi | Testing and Validating Machine Learning Classifiers by Metamorphic Testing 2 | ||
| GaoJi | Software testing: a research travelogue (2000–2014) |
[22]: blocking
Table of readings
read on: - 21 Sep 2017
| Presenter | Papers | Paper URL | Our Slides |
|---|---|---|---|
| Shijia | Outrageously Large Neural Networks: The Sparsely-Gated Mixture-of-Experts Layer, (Dean), ICLR17 1 | ||
| Ceyer | Sequence Modeling via Segmentations, ICML17 2 | ||
| Arshdeep | Input Switched Affine Networks: An RNN Architecture Designed for Interpretability, ICML17 3 |
[23]: brain
Table of readings
read on: - 13 Oct 2018
| Presenter | Papers | Paper URL | Our Slides |
|---|---|---|---|
| Arshdeep | deepCRISPR: optimized CRISPR guide RNA design by deep learning , Genome Biology 2018 | ||
| Arshdeep | The CRISPR tool kit for genome editing and beyond, Mazhar Adli | ||
| Eric | Intro of Genetic Engineering | ||
| Eric | Prediction of off-target activities for the end-to-end design of CRISPR guide RNAs | ||
| Brandon | Generative Modeling for Protein Structure | URL |
read on: - 13 Aug 2018
| Presenter | Papers | Paper URL | Our Slides |
|---|---|---|---|
| Arshdeep | DeepLesion: automated mining of large-scale lesion annotations and universal lesion detection with deep learning. | ||
| Arshdeep | Solving the RNA design problem with reinforcement learning, PLOSCB 1 | ||
| Arshdeep | Deep learning sequence-based ab initio prediction of variant effects on expression and disease risk 2 | ||
| Arshdeep | Towards Gene Expression Convolutions using Gene Interaction Graphs, Francis Dutil, Joseph Paul Cohen, Martin Weiss, Georgy Derevyanko, Yoshua Bengio 3 | ||
| Brandon | Kipoi: Accelerating the Community Exchange and Reuse of Predictive Models for Genomics | ||
| Arshdeep | Feedback GAN (FBGAN) for DNA: a Novel Feedback-Loop Architecture for Optimizing Protein Functions 2 |
[24]: casual
Table of readings
read on: - 05 Jan 2020
| Index | Papers | Our Slides |
|---|---|---|
| 1 | A Flexible Generative Framework for Graph-based Semi-supervised Learning | Arsh Survey |
| 2 | Learning Discrete Structures for Graph Neural Networks | Arsh Survey |
| 4 | Graph Markov Neural Nets | Arsh Survey |
| Graph Markov Neural Networks | Jack Survey | |
| 5 | GLoMo: Unsupervisedly Learned Relational Graphs as Transferable Representations | Arsh Survey |
| 6 | Subgraph Neural Networks | Arsh Survey |
| 7 | Pointer Graph Networks | Arsh Survey |
| 8 | Modeling Relational Data with Graph Convolutional Networks | Arsh Survey |
| 9 | Graph Learning | Zhe Survey |
| 8 | Neural Relational Inference | Zhe Survey |
Table of readings
read on: - 05 Aug 2020
| Index | Papers | Our Slides |
|---|---|---|
| 0 | A survey on Interpreting Deep Learning Models | Eli Survey |
| Interpretable Machine Learning: Definitions,Methods, Applications | Arsh Survey | |
| 1 | Explaining Explanations: Axiomatic Feature Interactions for Deep Networks | Arsh Survey |
| 2 | Shapley Value review | Arsh Survey |
| L-Shapley and C-Shapley: Efficient Model Interpretation for Structured Data | Bill Survey | |
| Consistent Individualized Feature Attribution for Tree Ensembles | bill Survey | |
| Summary for A value for n-person games | Pan Survey | |
| L-Shapley and C-Shapley: Efficient Model Interpretation for Structured Data | Rishab Survey | |
| 3 | Hierarchical Interpretations of Neural Network Predictions | Arsh Survey |
| Hierarchical Interpretations of Neural Network Predictions | Rishab Survey | |
| 4 | Beyond Word Importance: Contextual Decomposition to Extract Interactions from LSTMs | Arsh Survey |
| Beyond Word Importance: Contextual Decomposition to Extract Interactions from LSTMs | Rishab Survey | |
| 5 | Towards Hierarchical Importance Attribution: Explaining Compositional Semantics for Neural Sequence Models | Rishab Survey |
| Sanchit Survey | ||
| Generating Hierarchical Explanations on Text Classification via Feature Interaction Detection | Sanchit Survey | |
| 6 | This Looks Like That: Deep Learning for Interpretable Image Recognition | Pan Survey |
| 7 | AllenNLP Interpret | Rishab Survey |
| 8 | DISCOVERY OF NATURAL LANGUAGE CONCEPTS IN INDIVIDUAL UNITS OF CNNs | Rishab Survey |
| 9 | How Does BERT Answer Questions? A Layer-Wise Analysis of Transformer Representations | Rishab Survey |
| 10 | Attention is not Explanation | Sanchit Survey |
| Pan Survey | ||
| 11 | Axiomatic Attribution for Deep Networks | Sanchit Survey |
| 12 | Grad-CAM: Visual Explanations from Deep Networks via Gradient-based Localization | Sanchit Survey |
| 13 | Learning Variational Word Masks to Improve the Interpretability of Neural Text Classifier | Sanchit Survey |
| 14 | “Why Should I Trust You?”Explaining the Predictions of Any Classifier | Yu Survey |
| 15 | INTERPRETATIONS ARE USEFUL: PENALIZING EXPLANATIONS TO ALIGN NEURAL NETWORKS WITH PRIOR KNOWLEDGE | Pan Survey |
read on: - 05 Apr 2019
| Presenter | Papers | Paper URL | Our Slides |
|---|---|---|---|
| Understand | Faithful and Customizable Explanations of Black Box Models | Derrick PDF | |
| Understand | A causal framework for explaining the predictions of black-box sequence-to-sequence models, EMNLP17 | GaoJi PDF + Bill Pdf | |
| Understand | How Powerful are Graph Neural Networks? / Deeper Insights into Graph Convolutional Networks for Semi-Supervised Learning | Pdf + Pdf | GaoJi PDF |
| Understand | Interpretable Graph Convolutional Neural Networks for Inference on Noisy Knowledge Graphs + GNN Explainer: A Tool for Post-hoc Explanation of Graph Neural Networks | Pdf + PDF | GaoJi PDF |
| Understand | Attention is not Explanation, 2019 | ||
| Understand | Understanding attention in graph neural networks, 2019 |
[25]: certified-defense
Table of readings
read on: - 20 May 2018
| Presenter | Papers | Paper URL | Our Slides |
|---|---|---|---|
| Bill | Seq2Sick: Evaluating the Robustness of Sequence-to-Sequence Models with Adversarial Examples | ||
| Bill | Adversarial Examples for Evaluating Reading Comprehension Systems, Robin Jia, Percy Liang | ||
| Bill | Certified Defenses against Adversarial Examples, Aditi Raghunathan, Jacob Steinhardt, Percy Liang | ||
| Bill | Provably Minimally-Distorted Adversarial Examples, Nicholas Carlini, Guy Katz, Clark Barrett, David L. Dill |
read on: - 19 Jan 2017
| Presenter | Papers | Paper URL | Our Slides |
|---|---|---|---|
| AE | Intriguing properties of neural networks / | ||
| AE | Explaining and Harnessing Adversarial Examples | ||
| AE | Towards Deep Learning Models Resistant to Adversarial Attacks | ||
| AE | DeepFool: a simple and accurate method to fool deep neural networks | ||
| AE | Towards Evaluating the Robustness of Neural Networks by Carlini and Wagner | ||
| Data | Basic Survey of ImageNet - LSVRC competition | URL | |
| Understand | Understanding Black-box Predictions via Influence Functions | ||
| Understand | Deep inside convolutional networks: Visualising image classification models and saliency maps | ||
| Understand | BeenKim, Interpretable Machine Learning, ICML17 Tutorial [^1] | ||
| provable | Provable defenses against adversarial examples via the convex outer adversarial polytope, Eric Wong, J. Zico Kolter, | URL |
[26]: chromatin
Table of readings
read on: - 05 Jun 2020
| Index | Papers | Our Slides |
|---|---|---|
| 1 | Protein 3D Structure Computed from Evolutionary Sequence Variation | Arsh Survey |
| 3 | Regulatory network inference on developmental and evolutionary lineages | Arsh Survey |
| 4 | Deep learning in ultrasound image analysis | Zhe Survey |
| 5 | Predicting the sequence specificities of DNA- and RNA-binding proteins by deep learning (DeepBind) | Jack Survey |
| 6 | Canonical and single-cell Hi-C reveal distinct chromatin interaction sub-networks of mammalian transcription factors | Jack Survey |
| 7 | BindSpace decodes transcription factor binding signals by large-scale sequence embedding | Jack Survey |
| 8 | FastXML: A Fast, Accurate and Stable Tree-classifier for eXtreme Multi-label Learning | Jack Survey |
| 9 | Query-Reduction Networks for Question Answering | Bill Survey |
[27]: cnn
Table of readings
read on: - 11 Dec 2019
| Team INDEX | Title & Link | Tags | Our Slide | |
|---|---|---|---|---|
| T5 | Deep Structured Prediction with Nonlinear Output Transformations | structured | OurSlide | |
| T12 | Large Margin Deep Networks for Classification | OurSlide | large-margin | |
| T15 | Wide Activation for Efficient and Accurate Image Super-Resolution | CNN | OurSlide | |
| T17 | Ordered Neurons: Integrating Tree Structures into Recurrent Neural Networks | RNN | OurSlide | |
| T28 | Processing of missing data by neural networks | imputation | OurSlide | |
| T27 | Implicit Acceleration by Overparameterization | analysis | OurSlide |
[28]: composition
Table of readings
read on: - 14 Nov 2017
| Presenter | Papers | Paper URL | Our Slides |
|---|---|---|---|
| ChaoJiang | Courville - Generative Models II | DLSS17Slide + video | |
| GaoJi | Attend, Infer, Repeat: Fast Scene Understanding with Generative Models, NIPS16 1 | PDF + talk | |
| Arshdeep | Composing graphical models with neural networks for structured representations and fast inference, NIPS16 2 | ||
| Johnson - Graphical Models and Deep Learning | DLSSSlide + video | ||
| Parallel Multiscale Autoregressive Density Estimation, ICML17 3 | |||
| Beilun | Conditional Image Generation with Pixel CNN Decoders, NIPS16 4 | ||
| Shijia | Marrying Graphical Models & Deep Learning | DLSS17 + Video |
read on: - 26 Oct 2017
| Presenter | Papers | Paper URL | Our Slides |
|---|---|---|---|
| Tianlu | Robustness of classifiers: from adversarial to random noise, NIPS16 | PDF 1 | |
| Anant | Blind Attacks on Machine Learners, 2 NIPS16 | ||
| Data Noising as Smoothing in Neural Network Language Models (Ng), ICLR17 3 | |||
| The Robustness of Estimator Composition, NIPS16 4 |
[29]: compression
Table of readings
read on: - 20 Jan 2017
| Presenter | Papers | Paper URL | Our Slides |
|---|---|---|---|
| scalable | Sanjiv Kumar (Columbia EECS 6898), Lecture: Introduction to large-scale machine learning 2010 [^1] | ||
| data scalable | Alex Smola - Berkeley SML: Scalable Machine Learning: Syllabus 2012 [^2] | PDF 2014 + PDF | |
| Binary | Binarized Neural Networks: Training Deep Neural Networks with Weights and Activations Constrained to +1 or -1 | ||
| Model | Binary embeddings with structured hashed projections 1 | ||
| Model | Deep Compression: Compressing Deep Neural Networks (ICLR 2016) 2 |
[30]: concept
Table of readings
read on: - 05 Aug 2020
| Index | Papers | Our Slides |
|---|---|---|
| 0 | A survey on Interpreting Deep Learning Models | Eli Survey |
| Interpretable Machine Learning: Definitions,Methods, Applications | Arsh Survey | |
| 1 | Explaining Explanations: Axiomatic Feature Interactions for Deep Networks | Arsh Survey |
| 2 | Shapley Value review | Arsh Survey |
| L-Shapley and C-Shapley: Efficient Model Interpretation for Structured Data | Bill Survey | |
| Consistent Individualized Feature Attribution for Tree Ensembles | bill Survey | |
| Summary for A value for n-person games | Pan Survey | |
| L-Shapley and C-Shapley: Efficient Model Interpretation for Structured Data | Rishab Survey | |
| 3 | Hierarchical Interpretations of Neural Network Predictions | Arsh Survey |
| Hierarchical Interpretations of Neural Network Predictions | Rishab Survey | |
| 4 | Beyond Word Importance: Contextual Decomposition to Extract Interactions from LSTMs | Arsh Survey |
| Beyond Word Importance: Contextual Decomposition to Extract Interactions from LSTMs | Rishab Survey | |
| 5 | Towards Hierarchical Importance Attribution: Explaining Compositional Semantics for Neural Sequence Models | Rishab Survey |
| Sanchit Survey | ||
| Generating Hierarchical Explanations on Text Classification via Feature Interaction Detection | Sanchit Survey | |
| 6 | This Looks Like That: Deep Learning for Interpretable Image Recognition | Pan Survey |
| 7 | AllenNLP Interpret | Rishab Survey |
| 8 | DISCOVERY OF NATURAL LANGUAGE CONCEPTS IN INDIVIDUAL UNITS OF CNNs | Rishab Survey |
| 9 | How Does BERT Answer Questions? A Layer-Wise Analysis of Transformer Representations | Rishab Survey |
| 10 | Attention is not Explanation | Sanchit Survey |
| Pan Survey | ||
| 11 | Axiomatic Attribution for Deep Networks | Sanchit Survey |
| 12 | Grad-CAM: Visual Explanations from Deep Networks via Gradient-based Localization | Sanchit Survey |
| 13 | Learning Variational Word Masks to Improve the Interpretability of Neural Text Classifier | Sanchit Survey |
| 14 | “Why Should I Trust You?”Explaining the Predictions of Any Classifier | Yu Survey |
| 15 | INTERPRETATIONS ARE USEFUL: PENALIZING EXPLANATIONS TO ALIGN NEURAL NETWORKS WITH PRIOR KNOWLEDGE | Pan Survey |
[31]: crispr
Table of readings
read on: - 13 Oct 2018
| Presenter | Papers | Paper URL | Our Slides |
|---|---|---|---|
| Arshdeep | deepCRISPR: optimized CRISPR guide RNA design by deep learning , Genome Biology 2018 | ||
| Arshdeep | The CRISPR tool kit for genome editing and beyond, Mazhar Adli | ||
| Eric | Intro of Genetic Engineering | ||
| Eric | Prediction of off-target activities for the end-to-end design of CRISPR guide RNAs | ||
| Brandon | Generative Modeling for Protein Structure | URL |
[32]: cryptography
Table of readings
read on: - 22 Feb 2017
| Presenter | Papers | Paper URL | Our Slides |
|---|---|---|---|
| Tobin | Summary of A few Papers on: Machine Learning and Cryptography, (e.g., learning to Protect Communications with Adversarial Neural Cryptography) 1 | ||
| Tobin | Privacy Aware Learning (NIPS12) 2 | ||
| Tobin | Can Machine Learning be Secure?(2006) |
[33]: curriculum
Table of readings
read on: - 31 Oct 2017
| Presenter | Papers | Paper URL | Our Slides |
|---|---|---|---|
| Ceyer | An overview of gradient optimization algorithms, 1 | ||
| Shijia | Osborne - Probabilistic numerics for deep learning 2 | DLSS 2017 + Video | PDF / PDF2 |
| Jack | Automated Curriculum Learning for Neural Networks, ICML17 3 | ||
| DLSS17 | Johnson - Automatic Differentiation 4 | slide + video |
Table of readings
read on: - 12 Jan 2017
| Presenter | Papers | Paper URL | Our Slides |
|---|---|---|---|
| NLP | A Neural Probabilistic Language Model | ||
| Text | Bag of Tricks for Efficient Text Classification | ||
| Text | Character-level Convolutional Networks for Text Classification | ||
| NLP | BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding | ||
| seq2seq | Neural Machine Translation by Jointly Learning to Align and Translate | ||
| NLP | Natural Language Processing (almost) from Scratch | ||
| Train | Curriculum learning | ||
| Muthu | NeuroIPS Embedding Papers survey 2012 to 2015 | NIPS | |
| Basics | Efficient BackProp |
[34]: data-valuation
Table of readings
read on: - 05 Jul 2020
| Index | Papers | Our Slides |
|---|---|---|
| 1 | BIAS ALSO MATTERS: BIAS ATTRIBUTION FOR DEEP NEURAL NETWORK EXPLANATION | Arsh Survey |
| 2 | Data Shapley: Equitable Valuation of Data for Machine Learning | Arsh Survey |
| What is your data worth? Equitable Valuation of Data | Sanchit Survey | |
| 3 | Neural Network Attributions: A Causal Perspective | Zhe Survey |
| 4 | Defending Against Neural Fake News | Eli Survey |
| 5 | Interpretation of Neural Networks is Fragile | Eli Survey |
| Interpretation of Neural Networks is Fragile | Pan Survey | |
| 6 | Parsimonious Black-Box Adversarial Attacks Via Efficient Combinatorial Optimization | Eli Survey |
| 7 | Retrofitting Word Vectors to Semantic Lexicons | Morris Survey |
| 8 | On Evaluation of Adversarial Perturbations for Sequence-to-Sequence Models | Morris Survey |
| 9 | Towards Deep Learning Models Resistant to Adversarial Attacks | Pan Survey |
| 10 | Robust Attribution Regularization | Pan Survey |
| 11 | Sanity Checks for Saliency Maps | Sanchit Survey |
| 12 | Survey of data generation and evaluation in Interpreting DNN pipelines | Sanchit Survey |
| 13 | Think Architecture First: Benchmarking Deep Learning Interpretability in Time Series Predictions | Sanchit Survey |
| 14 | Universal Adversarial Triggers for Attacking and Analyzing NLP | Sanchit Survey |
| 15 | Apricot: Submodular selection for data summarization in Python | Arsh Survey |
[35]: denoising
Table of readings
read on: - 16 Nov 2017
| Presenter | Papers | Paper URL | Our Slides |
|---|---|---|---|
| Arshdeep | Generalization and Equilibrium in Generative Adversarial Nets (ICML17) 1 | PDF + video | |
| Arshdeep | Mode Regularized Generative Adversarial Networks (ICLR17) 2 | ||
| Bargav | Improving Generative Adversarial Networks with Denoising Feature Matching, ICLR17 3 | ||
| Anant | Generative Models and Model Criticism via Optimized Maximum Mean Discrepancy, ICLR17 4 | PDF + code |
[36]: dialog
Table of readings
read on: - 19 Sep 2017
| Presenter | Papers | Paper URL | Our Slides |
|---|---|---|---|
| Jack | Learning End-to-End Goal-Oriented Dialog, ICLR17 1 | ||
| Bargav | Nonparametric Neural Networks, ICLR17 2 | ||
| Bargav | Learning Structured Sparsity in Deep Neural Networks, NIPS16 3 | ||
| Arshdeep | Learning the Number of Neurons in Deep Networks, NIPS16 4 |
[37]: difference-analysis
Table of readings
read on: - 11 Oct 2017
| Presenter | Papers | Paper URL | Our Slides |
|---|---|---|---|
| Rita | Visualizing Deep Neural Network Decisions: Prediction Difference Analysis, ICLR17 1 | ||
| Arshdeep | Axiomatic Attribution for Deep Networks, ICML17 2 | ||
| The Robustness of Estimator Composition, NIPS16 |
read on: - 10 Oct 2017
| Presenter | Papers | Paper URL | Our Slides |
|---|---|---|---|
| Rita | Learning Important Features Through Propagating Activation Differences, ICML17 1 | ||
| GaoJi | Examples are not Enough, Learn to Criticize! Model Criticism for Interpretable Machine Learning, NIPS16 2 | ||
| Rita | Learning Kernels with Random Features, Aman Sinha*; John Duchi, 3 |
[38]: differentiation
Table of readings
read on: - 31 Oct 2017
| Presenter | Papers | Paper URL | Our Slides |
|---|---|---|---|
| Ceyer | An overview of gradient optimization algorithms, 1 | ||
| Shijia | Osborne - Probabilistic numerics for deep learning 2 | DLSS 2017 + Video | PDF / PDF2 |
| Jack | Automated Curriculum Learning for Neural Networks, ICML17 3 | ||
| DLSS17 | Johnson - Automatic Differentiation 4 | slide + video |
[39]: diffusion
Table of readings
read on: - 01 Dec 2022
Stable diffusion
- URL
- “High-Resolution Image Synthesis with Latent Diffusion Models”
DreamBooth: Fine Tuning Text-to-Image Diffusion Models for Subject-Driven Generation
- URL
- “personalization” of text-to-image diffusion models. Given as input just a few images of a subject, we fine-tune a pretrained text-to-image model such that it learns to bind a unique identifier with that specific subject. .”
LoRA: Low-Rank Adaptation of Large Language Models
- URL
-
“propose Low-Rank Adaptation, or LoRA, which freezes the pre-trained model weights and injects trainable rank decomposition matrices into each layer of the Transformer architecture, greatly reducing the number of trainable parameters for downstream tasks. Compared to GPT-3 175B fine-tuned with Adam, LoRA can reduce the number of trainable parameters by 10,000 times and the GPU memory requirement by 3 times.”
An Image is Worth One Word: Personalizing Text-to-Image Generation using Textual Inversion
- https://arxiv.org/abs/2208.01618
- Rinon Gal, Yuval Alaluf, Yuval Atzmon, Or Patashnik, Amit H. Bermano, Gal Chechik, Daniel Cohen-Or
- Text-to-image models offer unprecedented freedom to guide creation through natural language. Yet, it is unclear how such freedom can be exercised to generate images of specific unique concepts, modify their appearance, or compose them in new roles and novel scenes. In other words, we ask: how can we use language-guided models to turn our cat into a painting, or imagine a new product based on our favorite toy? Here we present a simple approach that allows such creative freedom. Using only 3-5 images of a user-provided concept, like an object or a style, we learn to represent it through new “words” in the embedding space of a frozen text-to-image model. These “words” can be composed into natural language sentences, guiding personalized creation in an intuitive way. Notably, we find evidence that a single word embedding is sufficient for capturing unique and varied concepts. We compare our approach to a wide range of baselines, and demonstrate that it can more faithfully portray the concepts across a range of applications and tasks.
[40]: dimension-reduction
Table of readings
read on: - 20 Jan 2017
| Presenter | Papers | Paper URL | Our Slides |
|---|---|---|---|
| scalable | Sanjiv Kumar (Columbia EECS 6898), Lecture: Introduction to large-scale machine learning 2010 [^1] | ||
| data scalable | Alex Smola - Berkeley SML: Scalable Machine Learning: Syllabus 2012 [^2] | PDF 2014 + PDF | |
| Binary | Binarized Neural Networks: Training Deep Neural Networks with Weights and Activations Constrained to +1 or -1 | ||
| Model | Binary embeddings with structured hashed projections 1 | ||
| Model | Deep Compression: Compressing Deep Neural Networks (ICLR 2016) 2 |
[41]: discrete
Table of readings
read on: - 22 Mar 2019
| Presenter | Papers | Paper URL | Our Slides |
|---|---|---|---|
| Scalable | FastGCN: Fast Learning with Graph Convolutional Networks via Importance Sampling | Ryan PDF + Arshdeep Pdf | |
| Scalable | MILE: A Multi-Level Framework for Scalable Graph Embedding | Ryan PDF | |
| Scalable | LanczosNet: Multi-Scale Deep Graph Convolutional Networks | Ryan PDF | |
| Scalable | Demystifying Parallel and Distributed Deep Learning: An In-Depth Concurrency Analysis | Derrick PDF | |
| Scalable | Towards Federated learning at Scale: System Design | URL | Derrick PDF |
| Scalable | DNN Dataflow Choice Is Overrated | Derrick PDF | |
| Scalable | Towards Efficient Large-Scale Graph Neural Network Computing | Derrick PDF | |
| Scalable | PyTorch Geometric | URL | |
| Scalable | PyTorch BigGraph | URL | |
| Scalable | Simplifying Graph Convolutional Networks | ||
| Scalable | Cluster-GCN: An Efficient Algorithm for Training Deep and Large Graph Convolutional Networks |
read on: - 15 Mar 2019
| Presenter | Papers | Paper URL | Our Slides |
|---|---|---|---|
| Generate | Maximum-Likelihood Augmented Discrete Generative Adversarial Networks | Tkach PDF + GaoJi Pdf | |
| Generate | Graphical Generative Adversarial Networks | Arshdeep PDF | |
| Generate | GraphRNN: Generating Realistic Graphs with Deep Auto-regressive Models, ICML2018 | Arshdeep PDF | |
| Generate | Inference in probabilistic graphical models by Graph Neural Networks | Arshdeep PDF | |
| Generate | Encoding robust representation for graph generation | Arshdeep PDF | |
| Generate | Junction Tree Variational Autoencoder for Molecular Graph Generation | Tkach PDF + Arshdeep Pdf | |
| Generate | Graph Convolutional Policy Network for Goal-Directed Molecular Graph Generation NeurIPS18 | Tkach PDF | |
| Generate | Towards Variational Generation of Small Graphs | Tkach PDF + Arshdeep Pdf | |
| Generate | Convolutional Imputation of Matrix Networks | Tkach PDF | |
| Generate | Graph Convolutional Matrix Completion | Tkach PDF | |
| Generate | NetGAN: Generating Graphs via Random Walks ICML18 | [ULR] | Tkach PDF |
| Beam | Stochastic Beams and Where to Find Them: The Gumbel-Top-k Trick for Sampling Sequences Without Replacement | URL | Tkach PDF |
read on: - 29 Dec 2018
| Presenter | Papers | Paper URL | Our Slides |
|---|---|---|---|
| Tkach | Boundary-Seeking Generative Adversarial Networks | ||
| Tkach | Maximum-Likelihood Augmented Discrete Generative Adversarial Networks | ||
| Tkach | Generating Sentences from a Continuous Space |
read on: - 21 Dec 2018
| Presenter | Papers | Paper URL | Our Slides |
|---|---|---|---|
| Arshdeep | Constrained Graph Variational Autoencoders for Molecule Design | ||
| Arshdeep | Learning Deep Generative Models of Graphs | ||
| Arshdeep | Graph Convolutional Policy Network for Goal-Directed Molecular Graph Generation | ||
| Jack | Generating and designing DNA with deep generative models |
read on: - 23 Aug 2018
| Presenter | Papers | Paper URL | Our Slides |
|---|---|---|---|
| Arshdeep | The Concrete Distribution: A Continuous Relaxation of Discrete Random Variables, Chris J. Maddison, Andriy Mnih, Yee Whye Teh 1 | ||
| GaoJi | Summary Of Several Autoencoder models | ||
| GaoJi | Latent Constraints: Learning to Generate Conditionally from Unconditional Generative Models, Jesse Engel, Matthew Hoffman, Adam Roberts 2 | ||
| GaoJi | Summary of A Few Recent Papers about Discrete Generative models, SeqGAN, MaskGAN, BEGAN, BoundaryGAN | ||
| Arshdeep | Semi-Amortized Variational Autoencoders, Yoon Kim, Sam Wiseman, Andrew C. Miller, David Sontag, Alexander M. Rush 3 | ||
| Arshdeep | Synthesizing Programs for Images using Reinforced Adversarial Learning, Yaroslav Ganin, Tejas Kulkarni, Igor Babuschkin, S.M. Ali Eslami, Oriol Vinyals 4 |
[42]: distillation
Table of readings
read on: - 20 Nov 2018
| Presenter | Papers | Paper URL | Our Slides |
|---|---|---|---|
| Bill | Adversarial Examples that Fool both Computer Vision and Time-Limited Humans | ||
| Bill | Adversarial Attacks Against Medical Deep Learning Systems | ||
| Bill | TensorFuzz: Debugging Neural Networks with Coverage-Guided Fuzzing | ||
| Bill | Distilling the Knowledge in a Neural Network | ||
| Bill | Defensive Distillation is Not Robust to Adversarial Examples | ||
| Bill | Adversarial Logit Pairing , Harini Kannan, Alexey Kurakin, Ian Goodfellow |
[43]: distributed
Table of readings
read on: - 22 Mar 2019
| Presenter | Papers | Paper URL | Our Slides |
|---|---|---|---|
| Scalable | FastGCN: Fast Learning with Graph Convolutional Networks via Importance Sampling | Ryan PDF + Arshdeep Pdf | |
| Scalable | MILE: A Multi-Level Framework for Scalable Graph Embedding | Ryan PDF | |
| Scalable | LanczosNet: Multi-Scale Deep Graph Convolutional Networks | Ryan PDF | |
| Scalable | Demystifying Parallel and Distributed Deep Learning: An In-Depth Concurrency Analysis | Derrick PDF | |
| Scalable | Towards Federated learning at Scale: System Design | URL | Derrick PDF |
| Scalable | DNN Dataflow Choice Is Overrated | Derrick PDF | |
| Scalable | Towards Efficient Large-Scale Graph Neural Network Computing | Derrick PDF | |
| Scalable | PyTorch Geometric | URL | |
| Scalable | PyTorch BigGraph | URL | |
| Scalable | Simplifying Graph Convolutional Networks | ||
| Scalable | Cluster-GCN: An Efficient Algorithm for Training Deep and Large Graph Convolutional Networks |
Table of readings
read on: - 20 Jan 2017
| Presenter | Papers | Paper URL | Our Slides |
|---|---|---|---|
| scalable | Sanjiv Kumar (Columbia EECS 6898), Lecture: Introduction to large-scale machine learning 2010 [^1] | ||
| data scalable | Alex Smola - Berkeley SML: Scalable Machine Learning: Syllabus 2012 [^2] | PDF 2014 + PDF | |
| Binary | Binarized Neural Networks: Training Deep Neural Networks with Weights and Activations Constrained to +1 or -1 | ||
| Model | Binary embeddings with structured hashed projections 1 | ||
| Model | Deep Compression: Compressing Deep Neural Networks (ICLR 2016) 2 |
[44]: dna
Table of readings
read on: - 15 Feb 2019
| Presenter | Papers | Paper URL | Our Slides |
|---|---|---|---|
| Bio | KDEEP: Protein–Ligand Absolute Binding Affinity Prediction via 3D-Convolutional Neural Networks, 2018 1 | Eli Pdf | |
| Bio | Molecular geometry prediction using a deep generative graph neural network | Eli Pdf | |
| Bio | Visualizing convolutional neural network protein-ligand scoring | PDF() | Eli PDF |
| Bio | Deep generative models of genetic variation capture mutation effects | PDF() | Eli PDF |
| Bio | Attentive cross-modal paratope prediction | Eli PDF |
read on: - 21 Dec 2018
| Presenter | Papers | Paper URL | Our Slides |
|---|---|---|---|
| Arshdeep | Constrained Graph Variational Autoencoders for Molecule Design | ||
| Arshdeep | Learning Deep Generative Models of Graphs | ||
| Arshdeep | Graph Convolutional Policy Network for Goal-Directed Molecular Graph Generation | ||
| Jack | Generating and designing DNA with deep generative models |
read on: - 13 Oct 2018
| Presenter | Papers | Paper URL | Our Slides |
|---|---|---|---|
| Arshdeep | deepCRISPR: optimized CRISPR guide RNA design by deep learning , Genome Biology 2018 | ||
| Arshdeep | The CRISPR tool kit for genome editing and beyond, Mazhar Adli | ||
| Eric | Intro of Genetic Engineering | ||
| Eric | Prediction of off-target activities for the end-to-end design of CRISPR guide RNAs | ||
| Brandon | Generative Modeling for Protein Structure | URL |
read on: - 13 Aug 2018
| Presenter | Papers | Paper URL | Our Slides |
|---|---|---|---|
| Arshdeep | DeepLesion: automated mining of large-scale lesion annotations and universal lesion detection with deep learning. | ||
| Arshdeep | Solving the RNA design problem with reinforcement learning, PLOSCB 1 | ||
| Arshdeep | Deep learning sequence-based ab initio prediction of variant effects on expression and disease risk 2 | ||
| Arshdeep | Towards Gene Expression Convolutions using Gene Interaction Graphs, Francis Dutil, Joseph Paul Cohen, Martin Weiss, Georgy Derevyanko, Yoshua Bengio 3 | ||
| Brandon | Kipoi: Accelerating the Community Exchange and Reuse of Predictive Models for Genomics | ||
| Arshdeep | Feedback GAN (FBGAN) for DNA: a Novel Feedback-Loop Architecture for Optimizing Protein Functions 2 |
read on: - 20 Apr 2018
| Presenter | Papers | Paper URL | Our Slides |
|---|---|---|---|
| BrandonLiu | Summary of Recent Generative Adversarial Networks (Classified) | ||
| Jack | Generating and designing DNA with deep generative models, Nathan Killoran, Leo J. Lee, Andrew Delong, David Duvenaud, Brendan J. Frey | ||
| GaoJi | More about basics of GAN | ||
| McGan: Mean and Covariance Feature Matching GAN, PMLR 70:2527-2535 | |||
| Wasserstein GAN, ICML17 | |||
| Geometrical Insights for Implicit Generative Modeling, L Bottou, M Arjovsky, D Lopez-Paz, M Oquab |
read on: - 21 Jan 2017
| Presenter | Papers | Paper URL | Our Slides |
|---|---|---|---|
| DeepBind | Predicting the sequence specificities of DNA- and RNA-binding proteins by deep learning | ||
| DeepSEA | Deep learning sequence-based ab initio prediction of variant effects on expression and disease risk | ||
| DeepSEA | Deep Supervised and Convolutional Generative Stochastic Network for Protein Secondary Structure Prediction, ICML 2014 | ||
| BioBasics | A method for integrating and ranking the evidence for biochemical pathways by mining reactions from text, Bioinformatics13 | ||
| BioBasics | Efficient counting of k-mers in DNA sequences using a Bloom filter. Melsted P, Pritchard JK. BMC Bioinformatics. 2011 | ||
| BioBasics | Fast String Kernels using Inexact Matching for Protein Sequence, JMLR 2004 | ||
| BioBasics | NIPS09: Locality-Sensitive Binary Codes from Shift-Invariant Kernels | ||
| MedSignal | Segmenting Time Series: A Survey and Novel Approach, |
[45]: domain-adaptation
Table of readings
read on: - 12 Oct 2017
| Presenter | Papers | Paper URL | Our Slides |
|---|---|---|---|
| Xueying | Semi-supervised Knowledge Transfer for Deep Learning from Private Training Data, ICLR17 1 | ||
| Bargav | Deep Learning with Differential Privacy, CCS16 2 | PDF + video | |
| Bargav | Privacy-Preserving Deep Learning, CCS15 3 | ||
| Xueying | Domain Separation Networks, NIPS16 4 |
[46]: dynamic
Table of readings
read on: - 25 Mar 2019
| Presenter | Papers | Paper URL | Our Slides |
|---|---|---|---|
| Edge | MobileNets: Efficient Convolutional Neural Networks for Mobile Vision Applications | ||
| Edge | XNOR-Net: ImageNet Classification Using Binary Convolutional Neural Networks | URL | Ryan PDF |
| Edge | DeepX: A Software Accelerator for Low-Power Deep Learning Inference on Mobile Devices | Eamon PDF | |
| Edge | Loss-aware Binarization of Deep Networks, ICLR17 | Ryan PDF | |
| Edge | Espresso: Efficient Forward Propagation for Binary Deep Neural Networks | Eamon PDF | |
| Dynamic | Drop an Octave: Reducing Spatial Redundancy in Convolutional Neural Networks with Octave Convolution | Weilin PDF | |
| Dynamic | Dynamic Scheduling For Dynamic Control Flow in Deep Learning Systems | ||
| Dynamic | Cavs: An Efficient Runtime System for Dynamic Neural Networks |
read on: - 22 Mar 2019
| Presenter | Papers | Paper URL | Our Slides |
|---|---|---|---|
| Scalable | FastGCN: Fast Learning with Graph Convolutional Networks via Importance Sampling | Ryan PDF + Arshdeep Pdf | |
| Scalable | MILE: A Multi-Level Framework for Scalable Graph Embedding | Ryan PDF | |
| Scalable | LanczosNet: Multi-Scale Deep Graph Convolutional Networks | Ryan PDF | |
| Scalable | Demystifying Parallel and Distributed Deep Learning: An In-Depth Concurrency Analysis | Derrick PDF | |
| Scalable | Towards Federated learning at Scale: System Design | URL | Derrick PDF |
| Scalable | DNN Dataflow Choice Is Overrated | Derrick PDF | |
| Scalable | Towards Efficient Large-Scale Graph Neural Network Computing | Derrick PDF | |
| Scalable | PyTorch Geometric | URL | |
| Scalable | PyTorch BigGraph | URL | |
| Scalable | Simplifying Graph Convolutional Networks | ||
| Scalable | Cluster-GCN: An Efficient Algorithm for Training Deep and Large Graph Convolutional Networks |
read on: - 22 Feb 2019
| Presenter | Papers | Paper URL | Our Slides |
|---|---|---|---|
| spherical | Spherical CNNs | Fuwen PDF + Arshdeep Pdf | |
| dynamic | Dynamic graph cnn for learning on point clouds, 2018 | Fuwen PDF | |
| basics | Geometric Deep Learning (simple introduction video) | URL | |
| matching | All Graphs Lead to Rome: Learning Geometric and Cycle-Consistent Representations with Graph Convolutional Networks | Fuwen PDF | |
| completion | Geometric matrix completion with recurrent multi-graph neural networks | Fuwen PDF | |
| Tutorial | Geometric Deep Learning on Graphs and Manifolds | URL | Arsh PDF |
| matching | Similarity Learning with Higher-Order Proximity for Brain Network Analysis | Arsh PDF | |
| pairwise | Pixel to Graph with Associative Embedding | Fuwen PDF | |
| 3D | 3D steerable cnns: Learning rotationally equivariant features in volumetric data | URL | Fuwen PDF |
read on: - 25 Oct 2018
| Presenter | Papers | Paper URL | Our Slides |
|---|---|---|---|
| Arshdeep | Learning Transferable Architectures for Scalable Image Recognition | ||
| Arshdeep | FractalNet: Ultra-Deep Neural Networks without Residuals |
read on: - 07 Nov 2017
| Presenter | Papers | Paper URL | Our Slides |
|---|---|---|---|
| GaoJi | Forward and Reverse Gradient-Based Hyperparameter Optimization, ICML17 1 | ||
| Chaojiang | Adaptive Neural Networks for Efficient Inference, ICML17 2 | ||
| Bargav | Practical Gauss-Newton Optimisation for Deep Learning, ICML17 3 | ||
| Rita | How to Escape Saddle Points Efficiently, ICML17 4 | ||
| Batched High-dimensional Bayesian Optimization via Structural Kernel Learning |
read on: - 05 Oct 2017
| Presenter | Papers | Paper URL | Our Slides |
|---|---|---|---|
| Anant | AdaNet: Adaptive Structural Learning of Artificial Neural Networks, ICML17 1 | ||
| Shijia | SplitNet: Learning to Semantically Split Deep Networks for Parameter Reduction and Model Parallelization, ICML17 2 | ||
| Jack | Proximal Deep Structured Models, NIPS16 3 | ||
| Optimal Architectures in a Solvable Model of Deep Networks, NIPS16 4 | |||
| Tianlu | Large-Scale Evolution of Image Classifiers, ICML17 5 |
read on: - 03 Oct 2017
| Presenter | Papers | Paper URL | Our Slides |
|---|---|---|---|
| Tianlu | Ask Me Anything: Dynamic Memory Networks for Natural Language Processing, ICML17 1 | PDF + code | |
| Jack | Reasoning with Memory Augmented Neural Networks for Language Comprehension, ICLR17 2 | ||
| Xueying | State-Frequency Memory Recurrent Neural Networks, ICML17 3 |
read on: - 26 Sep 2017
| Presenter | Papers | Paper URL | Our Slides |
|---|---|---|---|
| Rita | Paying More Attention to Attention: Improving the Performance of Convolutional Neural Networks via Attention Transfer, ICLR17 1 | ||
| Tianlu | Dynamic Coattention Networks For Question Answering, ICLR17 2 | PDF + code | |
| ChaoJiang | Structured Attention Networks, ICLR17 3 | PDF + code |
read on: - 22 Jun 2017
| Presenter | Papers | Paper URL | Our Slides |
|---|---|---|---|
| Arshdeep | Image Question Answering using Convolutional Neural Network with Dynamic Parameter Prediction 1 | ||
| Arshdeep | Decoupled Neural Interfaces Using Synthetic Gradients 2 | ||
| Arshdeep | Diet Networks: Thin Parameters for Fat Genomics 3 | ||
| Arshdeep | Metric Learning with Adaptive Density Discrimination 4 |
read on: - 02 Jun 2017
| Presenter | Papers | Paper URL | Our Slides |
|---|---|---|---|
| Arshdeep | HyperNetworks, David Ha, Andrew Dai, Quoc V. Le ICLR 2017 1 | ||
| Arshdeep | Learning feed-forward one-shot learners 2 | ||
| Arshdeep | Learning to Learn by gradient descent by gradient descent 3 | ||
| Arshdeep | Dynamic Filter Networks 4 https://arxiv.org/abs/1605.09673 |
[47]: efficiency
Table of readings
read on: - 01 Dec 2022
Stable diffusion
- URL
- “High-Resolution Image Synthesis with Latent Diffusion Models”
DreamBooth: Fine Tuning Text-to-Image Diffusion Models for Subject-Driven Generation
- URL
- “personalization” of text-to-image diffusion models. Given as input just a few images of a subject, we fine-tune a pretrained text-to-image model such that it learns to bind a unique identifier with that specific subject. .”
LoRA: Low-Rank Adaptation of Large Language Models
- URL
-
“propose Low-Rank Adaptation, or LoRA, which freezes the pre-trained model weights and injects trainable rank decomposition matrices into each layer of the Transformer architecture, greatly reducing the number of trainable parameters for downstream tasks. Compared to GPT-3 175B fine-tuned with Adam, LoRA can reduce the number of trainable parameters by 10,000 times and the GPU memory requirement by 3 times.”
An Image is Worth One Word: Personalizing Text-to-Image Generation using Textual Inversion
- https://arxiv.org/abs/2208.01618
- Rinon Gal, Yuval Alaluf, Yuval Atzmon, Or Patashnik, Amit H. Bermano, Gal Chechik, Daniel Cohen-Or
- Text-to-image models offer unprecedented freedom to guide creation through natural language. Yet, it is unclear how such freedom can be exercised to generate images of specific unique concepts, modify their appearance, or compose them in new roles and novel scenes. In other words, we ask: how can we use language-guided models to turn our cat into a painting, or imagine a new product based on our favorite toy? Here we present a simple approach that allows such creative freedom. Using only 3-5 images of a user-provided concept, like an object or a style, we learn to represent it through new “words” in the embedding space of a frozen text-to-image model. These “words” can be composed into natural language sentences, guiding personalized creation in an intuitive way. Notably, we find evidence that a single word embedding is sufficient for capturing unique and varied concepts. We compare our approach to a wide range of baselines, and demonstrate that it can more faithfully portray the concepts across a range of applications and tasks.
[48]: ehr
Table of readings
read on: - 20 Dec 2018
| Presenter | Papers | Paper URL | Our Slides |
|---|---|---|---|
| Bill | Seq2SQL: Generating Structured Queries from Natural Language using Reinforcement Learning | ||
| Chao | Deep EHR: A Survey of Recent Advances in Deep Learning Techniques for Electronic Health Record (EHR) Analysis (I) | ||
| Chao | Deep EHR: A Survey of Recent Advances in Deep Learning Techniques for Electronic Health Record (EHR) Analysis (II) | ||
| Derrick | Deep EHR: A Survey of Recent Advances in Deep Learning Techniques for Electronic Health Record (EHR) Analysis (III) | ||
| Chao | Reading Wikipedia to Answer Open-Domain Questions | ||
| Jennifer | Open Domain Question Answering Using Early Fusion of Knowledge Bases and Text |
read on: - 02 Dec 2018
| Presenter | Papers | Paper URL | Our Slides |
|---|---|---|---|
| Jennifer | Adversarial Attacks Against Medical Deep Learning Systems | ||
| Jennifer | Adversarial-Playground: A Visualization Suite Showing How Adversarial Examples Fool Deep Learning | ||
| Jennifer | Black-box Generation of Adversarial Text Sequences to Evade Deep Learning Classifiers | ||
| Jennifer | CleverHans | ||
| Ji | Ji-f18-New papers about adversarial attack |
[49]: em
Table of readings
read on: - 22 Apr 2017
| Presenter | Papers | Paper URL | Our Slides |
|---|---|---|---|
| Muthu | Optimization Methods for Large-Scale Machine Learning, Léon Bottou, Frank E. Curtis, Jorge Nocedal 1 | ||
| Muthu | Fast Training of Recurrent Networks Based on EM Algorithm (1998) 2 | ||
| Muthu | FitNets: Hints for Thin Deep Nets, ICLR15 3 | ||
| Muthu | Two NIPS 2015 Deep Learning Optimization Papers | ||
| Muthu | Difference Target Propagation (2015) 4 |
[50]: embedding
Table of readings
read on: - 22 Mar 2019
| Presenter | Papers | Paper URL | Our Slides |
|---|---|---|---|
| Scalable | FastGCN: Fast Learning with Graph Convolutional Networks via Importance Sampling | Ryan PDF + Arshdeep Pdf | |
| Scalable | MILE: A Multi-Level Framework for Scalable Graph Embedding | Ryan PDF | |
| Scalable | LanczosNet: Multi-Scale Deep Graph Convolutional Networks | Ryan PDF | |
| Scalable | Demystifying Parallel and Distributed Deep Learning: An In-Depth Concurrency Analysis | Derrick PDF | |
| Scalable | Towards Federated learning at Scale: System Design | URL | Derrick PDF |
| Scalable | DNN Dataflow Choice Is Overrated | Derrick PDF | |
| Scalable | Towards Efficient Large-Scale Graph Neural Network Computing | Derrick PDF | |
| Scalable | PyTorch Geometric | URL | |
| Scalable | PyTorch BigGraph | URL | |
| Scalable | Simplifying Graph Convolutional Networks | ||
| Scalable | Cluster-GCN: An Efficient Algorithm for Training Deep and Large Graph Convolutional Networks |
read on: - 17 Feb 2019
| Presenter | Papers | Paper URL | Our Slides |
|---|---|---|---|
| Program | Neural network-based graph embedding for cross-platform binary code similarity detection | Pdf + Pdf | Faizan PDF + GaoJi Pdf |
| Program | Deep Program Reidentification: A Graph Neural Network Solution | Weilin PDF | |
| Program | Heterogeneous Graph Neural Networks for Malicious Account Detection | Weilin Pdf | |
| Program | Learning to represent programs with graphs | Pdf 1 |
read on: - 25 Jan 2019
| Presenter | Papers | Paper URL | Our Notes |
|---|---|---|---|
| Basics | GraphSAGE: Large-scale Graph Representation Learning by Jure Leskovec Stanford University | URL + PDF | |
| Basics | Convolutional Neural Networks on Graphs with Fast Localized Spectral Filtering by Xavier Bresson | URL + PDF | Ryan Pdf |
| Basics | Gated Graph Sequence Neural Networks by Microsoft Research | URL + PDF | Faizan Pdf |
| Basics | DeepWalk - Turning Graphs into Features via Network Embeddings | URL + PDF | |
| Basics | Spectral Networks and Locally Connected Networks on Graphs 1 | GaoJi slides + Bill Pdf | |
| Basics | A Comprehensive Survey on Graph Neural Networks/ Graph Neural Networks: A Review of Methods and Applications | Jack Pdf | |
| GCN | Semi-Supervised Classification with Graph Convolutional Networks | Jack Pdf |
read on: - 27 Aug 2018
| Presenter | Papers | Paper URL | Our Slides |
|---|---|---|---|
| Derrick | GloVe: Global Vectors for Word Representation | ||
| Derrick | PARL.AI: A unified platform for sharing, training and evaluating dialog models across many tasks. | URL | |
| Derrick | scalable nearest neighbor algorithms for high dimensional data (PAMI14) 1 | ||
| Derrick | StarSpace: Embed All The Things! | ||
| Derrick | Weaver: Deep Co-Encoding of Questions and Documents for Machine Reading, Martin Raison, Pierre-Emmanuel Mazaré, Rajarshi Das, Antoine Bordes |
read on: - 10 Jan 2018
| Presenter | Papers | Paper URL | Our Slides |
|---|---|---|---|
| Bill | Google’s Neural Machine Translation System: Bridging the Gap between Human and Machine Translation 1 | ||
| Bill | Measuring the tendency of CNNs to Learn Surface Statistical Regularities Jason Jo, Yoshua Bengio | ||
| Bill | Generating Sentences by Editing Prototypes, Kelvin Guu, Tatsunori B. Hashimoto, Yonatan Oren, Percy Liang 2 | ||
| Bill | On the importance of single directions for generalization, Ari S. Morcos, David G.T. Barrett, Neil C. Rabinowitz, Matthew Botvinick |
read on: - 12 Jan 2017
| Presenter | Papers | Paper URL | Our Slides |
|---|---|---|---|
| QA | Learning to rank with (a lot of) word features | ||
| Relation | A semantic matching energy function for learning with multi-relational data | ||
| Relation | Translating embeddings for modeling multi-relational data | ||
| QA | Reading wikipedia to answer open-domain questions | ||
| QA | Question answering with subgraph embeddings |
read on: - 12 Jan 2017
| Presenter | Papers | Paper URL | Our Slides |
|---|---|---|---|
| NLP | A Neural Probabilistic Language Model | ||
| Text | Bag of Tricks for Efficient Text Classification | ||
| Text | Character-level Convolutional Networks for Text Classification | ||
| NLP | BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding | ||
| seq2seq | Neural Machine Translation by Jointly Learning to Align and Translate | ||
| NLP | Natural Language Processing (almost) from Scratch | ||
| Train | Curriculum learning | ||
| Muthu | NeuroIPS Embedding Papers survey 2012 to 2015 | NIPS | |
| Basics | Efficient BackProp |
[51]: encoder-decoder
Table of readings
read on: - 09 Dec 2019
| Team INDEX | Title & Link | Tags | Our Slide |
|---|---|---|---|
| T14 | CAN: Creative Adversarial Networks Generating “Art” | GAN | OurSlide |
| T26 | Unsupervised Discrete Sentence Representation Learning for Interpretable Neural Dialog Generation | encoder-decoder, dialog, VAE, Interpretable | OurSlide |
| T32 | Which Training Methods for GANs do actually Converge | convergence, optimization, GAN | OurSlide |
[52]: expressive
Table of readings
read on: - 14 Sep 2017
| Presenter | Papers | Paper URL | Our Slides |
|---|---|---|---|
| SE | Equivariance Through Parameter-Sharing, ICML17 1 | ||
| SE | Why Deep Neural Networks for Function Approximation?, ICLR17 2 | ||
| SE | Geometry of Neural Network Loss Surfaces via Random Matrix Theory, 3ICML17 | ||
| Sharp Minima Can Generalize For Deep Nets, ICML17 4 |
read on: - 12 Sep 2017
| Presenter | Papers | Paper URL | Our Slides |
|---|---|---|---|
| Ceyer | A Closer Look at Memorization in Deep Networks, ICML17 1 | ||
| On the Expressive Efficiency of Overlapping Architectures of Deep Learning 2 | DLSSpdf + video | ||
| Mutual Information | Opening the Black Box of Deep Neural Networks via Information 3 | URL + video | |
| ChaoJiang | Toward Deeper Understanding of Neural Networks: The Power of Initialization and a Dual View on Expressivity, NIPS16 |
read on: - 05 Sep 2017
| Presenter | Papers | Paper URL | Our Slides |
|---|---|---|---|
| Rita | On the Expressive Power of Deep Neural Networks 1 | ||
| Arshdeep | Understanding deep learning requires rethinking generalization, ICLR17 2 | ||
| Tianlu | On Large-Batch Training for Deep Learning: Generalization Gap and Sharp Minima, ICLR17 3 |
[53]: few-shot
Table of readings
read on: - 02 Nov 2017
| Presenter | Papers | Paper URL | Our Slides |
|---|---|---|---|
| GaoJi | Neural Architecture Search with Reinforcement Learning, ICLR17 1 | ||
| Ceyer | Learning to learn 2 | DLSS17video | |
| Beilun | Optimization as a Model for Few-Shot Learning, ICLR17 3 | PDF + More | |
| Anant | Neural Optimizer Search with Reinforcement Learning, ICML17 4 |
read on: - 18 Jan 2017
| Presenter | Papers | Paper URL | Our Slides |
|---|---|---|---|
| seq2seq | Sequence to Sequence Learning with Neural Networks | ||
| Set | Pointer Networks | ||
| Set | Order Matters: Sequence to Sequence for Sets | ||
| Point Attention | Multiple Object Recognition with Visual Attention | ||
| Memory | End-To-End Memory Networks | Jack Survey | |
| Memory | Neural Turing Machines | ||
| Memory | Hybrid computing using a neural network with dynamic external memory | ||
| Muthu | Matching Networks for One Shot Learning (NIPS16) 1 | ||
| Jack | Meta-Learning with Memory-Augmented Neural Networks (ICML16) 2 | ||
| Metric | ICML07 Best Paper - Information-Theoretic Metric Learning |
[54]: forcing
Table of readings
[55]: forgetting
Table of readings
read on: - 12 Dec 2019
| Team INDEX | Title & Link | Tags | Our Slide |
|---|---|---|---|
| T2 | Empirical Study of Example Forgetting During Deep Neural Network Learning | Sample Selection, forgetting | OurSlide |
| T29 | Select Via Proxy: Efficient Data Selection For Training Deep Networks | Sample Selection | OurSlide |
| T9 | How SGD Selects the Global Minima in over-parameterized Learning | optimization | OurSlide |
| T10 | Escaping Saddles with Stochastic Gradients | optimization | OurSlide |
| T13 | To What Extent Do Different Neural Networks Learn the Same Representation | subspace | OurSlide |
| T19 | On the Information Bottleneck Theory of Deep Learning | informax | OurSlide |
| T20 | Visualizing the Loss Landscape of Neural Nets | normalization | OurSlide |
| T21 | Using Pre-Training Can Improve Model Robustness and Uncertainty | training, analysis | OurSlide |
| T24 | Norm matters: efficient and accurate normalization schemes in deep networks | normalization | OurSlide |
[56]: fuzzing
Table of readings
read on: - 03 Aug 2018
| Presenter | Papers | Paper URL | Our Slides |
|---|---|---|---|
| GaoJi | Deep Reinforcement Fuzzing, Konstantin Böttinger, Patrice Godefroid, Rishabh Singh | ||
| GaoJi | Reluplex: An Efficient SMT Solver for Verifying Deep Neural Networks, Guy Katz, Clark Barrett, David Dill, Kyle Julian, Mykel Kochenderfer | ||
| GaoJi | DeepTest: Automated Testing of Deep-Neural-Network-driven Autonomous Cars, Yuchi Tian, Kexin Pei, Suman Jana, Baishakhi Ray | ||
| GaoJi | A few Recent (2018) papers on Black-box Adversarial Attacks, like Prior Convictions: Black-Box Adversarial Attacks with Bandits and Priors 1 | ||
| GaoJi | A few Recent papers of Adversarial Attacks on reinforcement learning, like Adversarial Attacks on Neural Network Policies (Sandy Huang, Nicolas Papernot, Ian Goodfellow, Yan Duan, Pieter Abbeel) | ||
| Testing | DeepXplore: Automated Whitebox Testing of Deep Learning Systems |
[57]: gan
Table of readings
read on: - 09 Dec 2019
| Team INDEX | Title & Link | Tags | Our Slide |
|---|---|---|---|
| T14 | CAN: Creative Adversarial Networks Generating “Art” | GAN | OurSlide |
| T26 | Unsupervised Discrete Sentence Representation Learning for Interpretable Neural Dialog Generation | encoder-decoder, dialog, VAE, Interpretable | OurSlide |
| T32 | Which Training Methods for GANs do actually Converge | convergence, optimization, GAN | OurSlide |
read on: - 29 Mar 2019
| Presenter | Papers | Paper URL | Our Slides |
|---|---|---|---|
| QA | A Comparison of Current Graph Database Models | Pdf + PDF2 | Bill PDF |
| QA | Open Domain Question Answering Using Early Fusion of Knowledge Bases and Text | Bill [PDF + GaoJi Pdf | |
| QA | Generative Question Answering: Learning to Answer the Whole Question, Mike Lewis, Angela Fan | Bill PDF + GaoJi Pdf | |
| QA | Learning to Reason Science Exam Questions with Contextual Knowledge Graph Embeddings / Knowledge Graph Embedding via Dynamic Mapping Matrix | PDF + Pdf | Bill PDF + GaoJi Pdf |
| Text | Adversarial Text Generation via Feature-Mover’s Distance | URL | Faizan PDF |
| Text | Content preserving text generation with attribute controls | URL | Faizan PDF |
| Text | Multiple-Attribute Text Rewriting, ICLR, 2019, | URL | Faizan PDF |
| Text | Writeprints: a stylometric approach to identity level identification and similarity detection in cyberSpace | URL | Faizan PDF |
read on: - 15 Mar 2019
| Presenter | Papers | Paper URL | Our Slides |
|---|---|---|---|
| Generate | Maximum-Likelihood Augmented Discrete Generative Adversarial Networks | Tkach PDF + GaoJi Pdf | |
| Generate | Graphical Generative Adversarial Networks | Arshdeep PDF | |
| Generate | GraphRNN: Generating Realistic Graphs with Deep Auto-regressive Models, ICML2018 | Arshdeep PDF | |
| Generate | Inference in probabilistic graphical models by Graph Neural Networks | Arshdeep PDF | |
| Generate | Encoding robust representation for graph generation | Arshdeep PDF | |
| Generate | Junction Tree Variational Autoencoder for Molecular Graph Generation | Tkach PDF + Arshdeep Pdf | |
| Generate | Graph Convolutional Policy Network for Goal-Directed Molecular Graph Generation NeurIPS18 | Tkach PDF | |
| Generate | Towards Variational Generation of Small Graphs | Tkach PDF + Arshdeep Pdf | |
| Generate | Convolutional Imputation of Matrix Networks | Tkach PDF | |
| Generate | Graph Convolutional Matrix Completion | Tkach PDF | |
| Generate | NetGAN: Generating Graphs via Random Walks ICML18 | [ULR] | Tkach PDF |
| Beam | Stochastic Beams and Where to Find Them: The Gumbel-Top-k Trick for Sampling Sequences Without Replacement | URL | Tkach PDF |
read on: - 29 Dec 2018
| Presenter | Papers | Paper URL | Our Slides |
|---|---|---|---|
| Tkach | Boundary-Seeking Generative Adversarial Networks | ||
| Tkach | Maximum-Likelihood Augmented Discrete Generative Adversarial Networks | ||
| Tkach | Generating Sentences from a Continuous Space |
read on: - 21 Dec 2018
| Presenter | Papers | Paper URL | Our Slides |
|---|---|---|---|
| Arshdeep | Constrained Graph Variational Autoencoders for Molecule Design | ||
| Arshdeep | Learning Deep Generative Models of Graphs | ||
| Arshdeep | Graph Convolutional Policy Network for Goal-Directed Molecular Graph Generation | ||
| Jack | Generating and designing DNA with deep generative models |
read on: - 12 Oct 2018
| Presenter | Papers | Paper URL | Our Slides |
|---|---|---|---|
| Jack | A Unified Approach to Interpreting Model Predictions | ||
| Jack | “Why Should I Trust You?”: Explaining the Predictions of Any Classifier | ||
| Jack | Visual Feature Attribution using Wasserstein GANs | ||
| Jack | GAN Dissection: Visualizing and Understanding Generative Adversarial Networks | ||
| GaoJi | Recent Interpretable machine learning papers | ||
| Jennifer | The Building Blocks of Interpretability |
read on: - 23 Aug 2018
| Presenter | Papers | Paper URL | Our Slides |
|---|---|---|---|
| Arshdeep | The Concrete Distribution: A Continuous Relaxation of Discrete Random Variables, Chris J. Maddison, Andriy Mnih, Yee Whye Teh 1 | ||
| GaoJi | Summary Of Several Autoencoder models | ||
| GaoJi | Latent Constraints: Learning to Generate Conditionally from Unconditional Generative Models, Jesse Engel, Matthew Hoffman, Adam Roberts 2 | ||
| GaoJi | Summary of A Few Recent Papers about Discrete Generative models, SeqGAN, MaskGAN, BEGAN, BoundaryGAN | ||
| Arshdeep | Semi-Amortized Variational Autoencoders, Yoon Kim, Sam Wiseman, Andrew C. Miller, David Sontag, Alexander M. Rush 3 | ||
| Arshdeep | Synthesizing Programs for Images using Reinforced Adversarial Learning, Yaroslav Ganin, Tejas Kulkarni, Igor Babuschkin, S.M. Ali Eslami, Oriol Vinyals 4 |
read on: - 20 Apr 2018
| Presenter | Papers | Paper URL | Our Slides |
|---|---|---|---|
| BrandonLiu | Summary of Recent Generative Adversarial Networks (Classified) | ||
| Jack | Generating and designing DNA with deep generative models, Nathan Killoran, Leo J. Lee, Andrew Delong, David Duvenaud, Brendan J. Frey | ||
| GaoJi | More about basics of GAN | ||
| McGan: Mean and Covariance Feature Matching GAN, PMLR 70:2527-2535 | |||
| Wasserstein GAN, ICML17 | |||
| Geometrical Insights for Implicit Generative Modeling, L Bottou, M Arjovsky, D Lopez-Paz, M Oquab |
[58]: gcn
Table of readings
read on: - 05 Jan 2020
| Index | Papers | Our Slides |
|---|---|---|
| 1 | Graph Convolutions: More than You Wanted to Know | Derrick Survey |
| 2 | Spectral Graph Sparsification | Derrick Survey |
| 3 | Complexity Analysis of Graph Convolutional Networks and in Attention based GNN | Derrick Survey |
| 4 | PyTorch-BigGraph: A Large-Scale Graph Embedding System | Derrick Survey |
| 5 | Scalable GNN Updates: More About PyTorch Geometric (PyG) | Derrick Survey |
| 6 | Time and Space Complexity of Graph Convolutional Networks | Derrick Survey |
| 7 | Large Scale GNN and Transformer Models and for Genomics | Jack Survey |
| 8 | Long Range Attention and Visualizing BERT | Jak Survey |
| 9 | Benchmarking Graph Neural Networks | Sanchit Survey |
[59]: gene-network
Table of readings
read on: - 05 Jun 2020
| Index | Papers | Our Slides |
|---|---|---|
| 1 | Protein 3D Structure Computed from Evolutionary Sequence Variation | Arsh Survey |
| 3 | Regulatory network inference on developmental and evolutionary lineages | Arsh Survey |
| 4 | Deep learning in ultrasound image analysis | Zhe Survey |
| 5 | Predicting the sequence specificities of DNA- and RNA-binding proteins by deep learning (DeepBind) | Jack Survey |
| 6 | Canonical and single-cell Hi-C reveal distinct chromatin interaction sub-networks of mammalian transcription factors | Jack Survey |
| 7 | BindSpace decodes transcription factor binding signals by large-scale sequence embedding | Jack Survey |
| 8 | FastXML: A Fast, Accurate and Stable Tree-classifier for eXtreme Multi-label Learning | Jack Survey |
| 9 | Query-Reduction Networks for Question Answering | Bill Survey |
[60]: generalization
Table of readings
read on: - 05 Apr 2020
| Index | Papers | Our Slides |
|---|---|---|
| 1 | Invariant Risk Minimization | Zhe Survey |
| 2 | Causal Machine Learning | Zhe Survey |
| 3 | A Meta-Transfer Objective for Learning to Disentangle Causal Mechanisms | Zhe Survey |
| 3 | Review on Optimization-Based Meta Learning | Zhe Survey |
| 4 | Domain adaptation and counterfactual prediction | Zhe Survey |
| 5 | Gaussian Processes | Zhe Survey |
| 6 | A Framework for Learning Predictive Structures from Multiple Tasks and Unlabeled Data | Zhe Survey |
| 7 | Few-shot domain adaptation by causal mechanism transfer | Zhe Survey |
read on: - 05 Mar 2020
| Index | Papers | Our Slides |
|---|---|---|
| 1 | Actor-Critic Methods for Control | Jake Survey |
| 2 | Generalization in Deep Reinforcement Learning | Jake Survey |
| 3 | Sample Efficient RL (Part 1) | Jake Survey |
| 4 | Sample Efficient RL (Part 2) | Jake Survey |
| 5 | Model-Free Value Methods in Deep RL | Jake Survey |
| 6 | Investigating Human Priors for Playing Video Games | Arsh Survey |
Table of readings
read on: - 12 Dec 2019
| Team INDEX | Title & Link | Tags | Our Slide |
|---|---|---|---|
| T2 | Empirical Study of Example Forgetting During Deep Neural Network Learning | Sample Selection, forgetting | OurSlide |
| T29 | Select Via Proxy: Efficient Data Selection For Training Deep Networks | Sample Selection | OurSlide |
| T9 | How SGD Selects the Global Minima in over-parameterized Learning | optimization | OurSlide |
| T10 | Escaping Saddles with Stochastic Gradients | optimization | OurSlide |
| T13 | To What Extent Do Different Neural Networks Learn the Same Representation | subspace | OurSlide |
| T19 | On the Information Bottleneck Theory of Deep Learning | informax | OurSlide |
| T20 | Visualizing the Loss Landscape of Neural Nets | normalization | OurSlide |
| T21 | Using Pre-Training Can Improve Model Robustness and Uncertainty | training, analysis | OurSlide |
| T24 | Norm matters: efficient and accurate normalization schemes in deep networks | normalization | OurSlide |
read on: - 23 Aug 2018
| Presenter | Papers | Paper URL | Our Slides |
|---|---|---|---|
| Arshdeep | The Concrete Distribution: A Continuous Relaxation of Discrete Random Variables, Chris J. Maddison, Andriy Mnih, Yee Whye Teh 1 | ||
| GaoJi | Summary Of Several Autoencoder models | ||
| GaoJi | Latent Constraints: Learning to Generate Conditionally from Unconditional Generative Models, Jesse Engel, Matthew Hoffman, Adam Roberts 2 | ||
| GaoJi | Summary of A Few Recent Papers about Discrete Generative models, SeqGAN, MaskGAN, BEGAN, BoundaryGAN | ||
| Arshdeep | Semi-Amortized Variational Autoencoders, Yoon Kim, Sam Wiseman, Andrew C. Miller, David Sontag, Alexander M. Rush 3 | ||
| Arshdeep | Synthesizing Programs for Images using Reinforced Adversarial Learning, Yaroslav Ganin, Tejas Kulkarni, Igor Babuschkin, S.M. Ali Eslami, Oriol Vinyals 4 |
read on: - 20 Apr 2018
| Presenter | Papers | Paper URL | Our Slides |
|---|---|---|---|
| BrandonLiu | Summary of Recent Generative Adversarial Networks (Classified) | ||
| Jack | Generating and designing DNA with deep generative models, Nathan Killoran, Leo J. Lee, Andrew Delong, David Duvenaud, Brendan J. Frey | ||
| GaoJi | More about basics of GAN | ||
| McGan: Mean and Covariance Feature Matching GAN, PMLR 70:2527-2535 | |||
| Wasserstein GAN, ICML17 | |||
| Geometrical Insights for Implicit Generative Modeling, L Bottou, M Arjovsky, D Lopez-Paz, M Oquab |
read on: - 10 Jan 2018
| Presenter | Papers | Paper URL | Our Slides |
|---|---|---|---|
| Bill | Google’s Neural Machine Translation System: Bridging the Gap between Human and Machine Translation 1 | ||
| Bill | Measuring the tendency of CNNs to Learn Surface Statistical Regularities Jason Jo, Yoshua Bengio | ||
| Bill | Generating Sentences by Editing Prototypes, Kelvin Guu, Tatsunori B. Hashimoto, Yonatan Oren, Percy Liang 2 | ||
| Bill | On the importance of single directions for generalization, Ari S. Morcos, David G.T. Barrett, Neil C. Rabinowitz, Matthew Botvinick |
read on: - 16 Nov 2017
| Presenter | Papers | Paper URL | Our Slides |
|---|---|---|---|
| Arshdeep | Generalization and Equilibrium in Generative Adversarial Nets (ICML17) 1 | PDF + video | |
| Arshdeep | Mode Regularized Generative Adversarial Networks (ICLR17) 2 | ||
| Bargav | Improving Generative Adversarial Networks with Denoising Feature Matching, ICLR17 3 | ||
| Anant | Generative Models and Model Criticism via Optimized Maximum Mean Discrepancy, ICLR17 4 | PDF + code |
read on: - 14 Sep 2017
| Presenter | Papers | Paper URL | Our Slides |
|---|---|---|---|
| SE | Equivariance Through Parameter-Sharing, ICML17 1 | ||
| SE | Why Deep Neural Networks for Function Approximation?, ICLR17 2 | ||
| SE | Geometry of Neural Network Loss Surfaces via Random Matrix Theory, 3ICML17 | ||
| Sharp Minima Can Generalize For Deep Nets, ICML17 4 |
read on: - 05 Sep 2017
| Presenter | Papers | Paper URL | Our Slides |
|---|---|---|---|
| Rita | On the Expressive Power of Deep Neural Networks 1 | ||
| Arshdeep | Understanding deep learning requires rethinking generalization, ICLR17 2 | ||
| Tianlu | On Large-Batch Training for Deep Learning: Generalization Gap and Sharp Minima, ICLR17 3 |
[61]: generative
Table of readings
read on: - 05 Feb 2020
| Index | Papers | Our Slides |
|---|---|---|
| 1 | Beta VAE, Ladder VAE, Causal VAE | Arsh Survey |
| 2 | Learnt Prior VAE | Arsh Survey |
| 3 | Multitask Graph Autoencoder | Arsh Survey |
| 4 | Introduction to component analysi | Zhe Survey |
| 5 | Normalizing flow | Zhe Survey |
| 6 | Nonlinear ICA | Zhe Survey |
| 7 | Deep Convolutional Inverse Graphics Network | Zhe Survey |
Table of readings
read on: - 29 Mar 2019
| Presenter | Papers | Paper URL | Our Slides |
|---|---|---|---|
| QA | A Comparison of Current Graph Database Models | Pdf + PDF2 | Bill PDF |
| QA | Open Domain Question Answering Using Early Fusion of Knowledge Bases and Text | Bill [PDF + GaoJi Pdf | |
| QA | Generative Question Answering: Learning to Answer the Whole Question, Mike Lewis, Angela Fan | Bill PDF + GaoJi Pdf | |
| QA | Learning to Reason Science Exam Questions with Contextual Knowledge Graph Embeddings / Knowledge Graph Embedding via Dynamic Mapping Matrix | PDF + Pdf | Bill PDF + GaoJi Pdf |
| Text | Adversarial Text Generation via Feature-Mover’s Distance | URL | Faizan PDF |
| Text | Content preserving text generation with attribute controls | URL | Faizan PDF |
| Text | Multiple-Attribute Text Rewriting, ICLR, 2019, | URL | Faizan PDF |
| Text | Writeprints: a stylometric approach to identity level identification and similarity detection in cyberSpace | URL | Faizan PDF |
read on: - 15 Mar 2019
| Presenter | Papers | Paper URL | Our Slides |
|---|---|---|---|
| Generate | Maximum-Likelihood Augmented Discrete Generative Adversarial Networks | Tkach PDF + GaoJi Pdf | |
| Generate | Graphical Generative Adversarial Networks | Arshdeep PDF | |
| Generate | GraphRNN: Generating Realistic Graphs with Deep Auto-regressive Models, ICML2018 | Arshdeep PDF | |
| Generate | Inference in probabilistic graphical models by Graph Neural Networks | Arshdeep PDF | |
| Generate | Encoding robust representation for graph generation | Arshdeep PDF | |
| Generate | Junction Tree Variational Autoencoder for Molecular Graph Generation | Tkach PDF + Arshdeep Pdf | |
| Generate | Graph Convolutional Policy Network for Goal-Directed Molecular Graph Generation NeurIPS18 | Tkach PDF | |
| Generate | Towards Variational Generation of Small Graphs | Tkach PDF + Arshdeep Pdf | |
| Generate | Convolutional Imputation of Matrix Networks | Tkach PDF | |
| Generate | Graph Convolutional Matrix Completion | Tkach PDF | |
| Generate | NetGAN: Generating Graphs via Random Walks ICML18 | [ULR] | Tkach PDF |
| Beam | Stochastic Beams and Where to Find Them: The Gumbel-Top-k Trick for Sampling Sequences Without Replacement | URL | Tkach PDF |
read on: - 29 Dec 2018
| Presenter | Papers | Paper URL | Our Slides |
|---|---|---|---|
| Tkach | Boundary-Seeking Generative Adversarial Networks | ||
| Tkach | Maximum-Likelihood Augmented Discrete Generative Adversarial Networks | ||
| Tkach | Generating Sentences from a Continuous Space |
read on: - 21 Dec 2018
| Presenter | Papers | Paper URL | Our Slides |
|---|---|---|---|
| Arshdeep | Constrained Graph Variational Autoencoders for Molecule Design | ||
| Arshdeep | Learning Deep Generative Models of Graphs | ||
| Arshdeep | Graph Convolutional Policy Network for Goal-Directed Molecular Graph Generation | ||
| Jack | Generating and designing DNA with deep generative models |
read on: - 13 Oct 2018
| Presenter | Papers | Paper URL | Our Slides |
|---|---|---|---|
| Arshdeep | deepCRISPR: optimized CRISPR guide RNA design by deep learning , Genome Biology 2018 | ||
| Arshdeep | The CRISPR tool kit for genome editing and beyond, Mazhar Adli | ||
| Eric | Intro of Genetic Engineering | ||
| Eric | Prediction of off-target activities for the end-to-end design of CRISPR guide RNAs | ||
| Brandon | Generative Modeling for Protein Structure | URL |
read on: - 23 Aug 2018
| Presenter | Papers | Paper URL | Our Slides |
|---|---|---|---|
| Arshdeep | The Concrete Distribution: A Continuous Relaxation of Discrete Random Variables, Chris J. Maddison, Andriy Mnih, Yee Whye Teh 1 | ||
| GaoJi | Summary Of Several Autoencoder models | ||
| GaoJi | Latent Constraints: Learning to Generate Conditionally from Unconditional Generative Models, Jesse Engel, Matthew Hoffman, Adam Roberts 2 | ||
| GaoJi | Summary of A Few Recent Papers about Discrete Generative models, SeqGAN, MaskGAN, BEGAN, BoundaryGAN | ||
| Arshdeep | Semi-Amortized Variational Autoencoders, Yoon Kim, Sam Wiseman, Andrew C. Miller, David Sontag, Alexander M. Rush 3 | ||
| Arshdeep | Synthesizing Programs for Images using Reinforced Adversarial Learning, Yaroslav Ganin, Tejas Kulkarni, Igor Babuschkin, S.M. Ali Eslami, Oriol Vinyals 4 |
read on: - 13 Aug 2018
| Presenter | Papers | Paper URL | Our Slides |
|---|---|---|---|
| Arshdeep | DeepLesion: automated mining of large-scale lesion annotations and universal lesion detection with deep learning. | ||
| Arshdeep | Solving the RNA design problem with reinforcement learning, PLOSCB 1 | ||
| Arshdeep | Deep learning sequence-based ab initio prediction of variant effects on expression and disease risk 2 | ||
| Arshdeep | Towards Gene Expression Convolutions using Gene Interaction Graphs, Francis Dutil, Joseph Paul Cohen, Martin Weiss, Georgy Derevyanko, Yoshua Bengio 3 | ||
| Brandon | Kipoi: Accelerating the Community Exchange and Reuse of Predictive Models for Genomics | ||
| Arshdeep | Feedback GAN (FBGAN) for DNA: a Novel Feedback-Loop Architecture for Optimizing Protein Functions 2 |
read on: - 12 May 2018
| Presenter | Papers | Paper URL | Our Slides |
|---|---|---|---|
| Bill | Intriguing Properties of Adversarial Examples, Ekin D. Cubuk, Barret Zoph, Samuel S. Schoenholz, Quoc V. Le 1 | ||
| Bill | Adversarial Spheres 2 | ||
| Bill | Adversarial Transformation Networks: Learning to Generate Adversarial Examples, Shumeet Baluja, Ian Fischer 3 | ||
| Bill | Thermometer encoding: one hot way to resist adversarial examples 4 | ||
| Adversarial Logit Pairing , Harini Kannan, Alexey Kurakin, Ian Goodfellow 5 |
read on: - 20 Apr 2018
| Presenter | Papers | Paper URL | Our Slides |
|---|---|---|---|
| BrandonLiu | Summary of Recent Generative Adversarial Networks (Classified) | ||
| Jack | Generating and designing DNA with deep generative models, Nathan Killoran, Leo J. Lee, Andrew Delong, David Duvenaud, Brendan J. Frey | ||
| GaoJi | More about basics of GAN | ||
| McGan: Mean and Covariance Feature Matching GAN, PMLR 70:2527-2535 | |||
| Wasserstein GAN, ICML17 | |||
| Geometrical Insights for Implicit Generative Modeling, L Bottou, M Arjovsky, D Lopez-Paz, M Oquab |
read on: - 10 Jan 2018
| Presenter | Papers | Paper URL | Our Slides |
|---|---|---|---|
| Bill | Google’s Neural Machine Translation System: Bridging the Gap between Human and Machine Translation 1 | ||
| Bill | Measuring the tendency of CNNs to Learn Surface Statistical Regularities Jason Jo, Yoshua Bengio | ||
| Bill | Generating Sentences by Editing Prototypes, Kelvin Guu, Tatsunori B. Hashimoto, Yonatan Oren, Percy Liang 2 | ||
| Bill | On the importance of single directions for generalization, Ari S. Morcos, David G.T. Barrett, Neil C. Rabinowitz, Matthew Botvinick |
read on: - 16 Nov 2017
| Presenter | Papers | Paper URL | Our Slides |
|---|---|---|---|
| Arshdeep | Generalization and Equilibrium in Generative Adversarial Nets (ICML17) 1 | PDF + video | |
| Arshdeep | Mode Regularized Generative Adversarial Networks (ICLR17) 2 | ||
| Bargav | Improving Generative Adversarial Networks with Denoising Feature Matching, ICLR17 3 | ||
| Anant | Generative Models and Model Criticism via Optimized Maximum Mean Discrepancy, ICLR17 4 | PDF + code |
read on: - 14 Nov 2017
| Presenter | Papers | Paper URL | Our Slides |
|---|---|---|---|
| ChaoJiang | Courville - Generative Models II | DLSS17Slide + video | |
| GaoJi | Attend, Infer, Repeat: Fast Scene Understanding with Generative Models, NIPS16 1 | PDF + talk | |
| Arshdeep | Composing graphical models with neural networks for structured representations and fast inference, NIPS16 2 | ||
| Johnson - Graphical Models and Deep Learning | DLSSSlide + video | ||
| Parallel Multiscale Autoregressive Density Estimation, ICML17 3 | |||
| Beilun | Conditional Image Generation with Pixel CNN Decoders, NIPS16 4 | ||
| Shijia | Marrying Graphical Models & Deep Learning | DLSS17 + Video |
read on: - 28 Sep 2017
| Presenter | Papers | Paper URL | Our Slides |
|---|---|---|---|
| Jack | Attend, Adapt and Transfer: Attentive Deep Architecture for Adaptive Transfer from multiple sources in the same domain, ICLR17 1 | ||
| Arshdeep | Bidirectional Attention Flow for Machine Comprehension, ICLR17 2 | PDF + code | |
| Ceyer | Image-to-Markup Generation with Coarse-to-Fine Attention, ICML17 | PDF + code | |
| ChaoJiang | Can Active Memory Replace Attention? ; Samy Bengio, NIPS16 3 | ||
| An Information-Theoretic Framework for Fast and Robust Unsupervised Learning via Neural Population Infomax, ICLR17 |
[62]: genomics
Table of readings
read on: - 13 Oct 2018
| Presenter | Papers | Paper URL | Our Slides |
|---|---|---|---|
| Arshdeep | deepCRISPR: optimized CRISPR guide RNA design by deep learning , Genome Biology 2018 | ||
| Arshdeep | The CRISPR tool kit for genome editing and beyond, Mazhar Adli | ||
| Eric | Intro of Genetic Engineering | ||
| Eric | Prediction of off-target activities for the end-to-end design of CRISPR guide RNAs | ||
| Brandon | Generative Modeling for Protein Structure | URL |
read on: - 13 Aug 2018
| Presenter | Papers | Paper URL | Our Slides |
|---|---|---|---|
| Arshdeep | DeepLesion: automated mining of large-scale lesion annotations and universal lesion detection with deep learning. | ||
| Arshdeep | Solving the RNA design problem with reinforcement learning, PLOSCB 1 | ||
| Arshdeep | Deep learning sequence-based ab initio prediction of variant effects on expression and disease risk 2 | ||
| Arshdeep | Towards Gene Expression Convolutions using Gene Interaction Graphs, Francis Dutil, Joseph Paul Cohen, Martin Weiss, Georgy Derevyanko, Yoshua Bengio 3 | ||
| Brandon | Kipoi: Accelerating the Community Exchange and Reuse of Predictive Models for Genomics | ||
| Arshdeep | Feedback GAN (FBGAN) for DNA: a Novel Feedback-Loop Architecture for Optimizing Protein Functions 2 |
[63]: geometric
Table of readings
read on: - 22 Feb 2019
| Presenter | Papers | Paper URL | Our Slides |
|---|---|---|---|
| spherical | Spherical CNNs | Fuwen PDF + Arshdeep Pdf | |
| dynamic | Dynamic graph cnn for learning on point clouds, 2018 | Fuwen PDF | |
| basics | Geometric Deep Learning (simple introduction video) | URL | |
| matching | All Graphs Lead to Rome: Learning Geometric and Cycle-Consistent Representations with Graph Convolutional Networks | Fuwen PDF | |
| completion | Geometric matrix completion with recurrent multi-graph neural networks | Fuwen PDF | |
| Tutorial | Geometric Deep Learning on Graphs and Manifolds | URL | Arsh PDF |
| matching | Similarity Learning with Higher-Order Proximity for Brain Network Analysis | Arsh PDF | |
| pairwise | Pixel to Graph with Associative Embedding | Fuwen PDF | |
| 3D | 3D steerable cnns: Learning rotationally equivariant features in volumetric data | URL | Fuwen PDF |
read on: - 15 Feb 2019
| Presenter | Papers | Paper URL | Our Slides |
|---|---|---|---|
| Bio | KDEEP: Protein–Ligand Absolute Binding Affinity Prediction via 3D-Convolutional Neural Networks, 2018 1 | Eli Pdf | |
| Bio | Molecular geometry prediction using a deep generative graph neural network | Eli Pdf | |
| Bio | Visualizing convolutional neural network protein-ligand scoring | PDF() | Eli PDF |
| Bio | Deep generative models of genetic variation capture mutation effects | PDF() | Eli PDF |
| Bio | Attentive cross-modal paratope prediction | Eli PDF |
[64]: graph
Table of readings
read on: - 05 Jan 2020
| Index | Papers | Our Slides |
|---|---|---|
| 1 | A Flexible Generative Framework for Graph-based Semi-supervised Learning | Arsh Survey |
| 2 | Learning Discrete Structures for Graph Neural Networks | Arsh Survey |
| 4 | Graph Markov Neural Nets | Arsh Survey |
| Graph Markov Neural Networks | Jack Survey | |
| 5 | GLoMo: Unsupervisedly Learned Relational Graphs as Transferable Representations | Arsh Survey |
| 6 | Subgraph Neural Networks | Arsh Survey |
| 7 | Pointer Graph Networks | Arsh Survey |
| 8 | Modeling Relational Data with Graph Convolutional Networks | Arsh Survey |
| 9 | Graph Learning | Zhe Survey |
| 8 | Neural Relational Inference | Zhe Survey |
Table of readings
read on: - 29 Mar 2019
| Presenter | Papers | Paper URL | Our Slides |
|---|---|---|---|
| QA | A Comparison of Current Graph Database Models | Pdf + PDF2 | Bill PDF |
| QA | Open Domain Question Answering Using Early Fusion of Knowledge Bases and Text | Bill [PDF + GaoJi Pdf | |
| QA | Generative Question Answering: Learning to Answer the Whole Question, Mike Lewis, Angela Fan | Bill PDF + GaoJi Pdf | |
| QA | Learning to Reason Science Exam Questions with Contextual Knowledge Graph Embeddings / Knowledge Graph Embedding via Dynamic Mapping Matrix | PDF + Pdf | Bill PDF + GaoJi Pdf |
| Text | Adversarial Text Generation via Feature-Mover’s Distance | URL | Faizan PDF |
| Text | Content preserving text generation with attribute controls | URL | Faizan PDF |
| Text | Multiple-Attribute Text Rewriting, ICLR, 2019, | URL | Faizan PDF |
| Text | Writeprints: a stylometric approach to identity level identification and similarity detection in cyberSpace | URL | Faizan PDF |
read on: - 22 Mar 2019
| Presenter | Papers | Paper URL | Our Slides |
|---|---|---|---|
| Scalable | FastGCN: Fast Learning with Graph Convolutional Networks via Importance Sampling | Ryan PDF + Arshdeep Pdf | |
| Scalable | MILE: A Multi-Level Framework for Scalable Graph Embedding | Ryan PDF | |
| Scalable | LanczosNet: Multi-Scale Deep Graph Convolutional Networks | Ryan PDF | |
| Scalable | Demystifying Parallel and Distributed Deep Learning: An In-Depth Concurrency Analysis | Derrick PDF | |
| Scalable | Towards Federated learning at Scale: System Design | URL | Derrick PDF |
| Scalable | DNN Dataflow Choice Is Overrated | Derrick PDF | |
| Scalable | Towards Efficient Large-Scale Graph Neural Network Computing | Derrick PDF | |
| Scalable | PyTorch Geometric | URL | |
| Scalable | PyTorch BigGraph | URL | |
| Scalable | Simplifying Graph Convolutional Networks | ||
| Scalable | Cluster-GCN: An Efficient Algorithm for Training Deep and Large Graph Convolutional Networks |
read on: - 15 Mar 2019
| Presenter | Papers | Paper URL | Our Slides |
|---|---|---|---|
| Generate | Maximum-Likelihood Augmented Discrete Generative Adversarial Networks | Tkach PDF + GaoJi Pdf | |
| Generate | Graphical Generative Adversarial Networks | Arshdeep PDF | |
| Generate | GraphRNN: Generating Realistic Graphs with Deep Auto-regressive Models, ICML2018 | Arshdeep PDF | |
| Generate | Inference in probabilistic graphical models by Graph Neural Networks | Arshdeep PDF | |
| Generate | Encoding robust representation for graph generation | Arshdeep PDF | |
| Generate | Junction Tree Variational Autoencoder for Molecular Graph Generation | Tkach PDF + Arshdeep Pdf | |
| Generate | Graph Convolutional Policy Network for Goal-Directed Molecular Graph Generation NeurIPS18 | Tkach PDF | |
| Generate | Towards Variational Generation of Small Graphs | Tkach PDF + Arshdeep Pdf | |
| Generate | Convolutional Imputation of Matrix Networks | Tkach PDF | |
| Generate | Graph Convolutional Matrix Completion | Tkach PDF | |
| Generate | NetGAN: Generating Graphs via Random Walks ICML18 | [ULR] | Tkach PDF |
| Beam | Stochastic Beams and Where to Find Them: The Gumbel-Top-k Trick for Sampling Sequences Without Replacement | URL | Tkach PDF |
read on: - 06 Mar 2019
| Presenter | Papers | Paper URL | Our Slides |
|---|---|---|---|
| Robust | Adversarial Attacks on Graph Structured Data | Faizan [PDF + GaoJi Pdf | |
| Robust | KDD’18 Adversarial Attacks on Neural Networks for Graph Data | Faizan PDF + GaoJi Pdf | |
| Robust | Attacking Binarized Neural Networks | Faizan PDF |
read on: - 22 Feb 2019
| Presenter | Papers | Paper URL | Our Slides |
|---|---|---|---|
| spherical | Spherical CNNs | Fuwen PDF + Arshdeep Pdf | |
| dynamic | Dynamic graph cnn for learning on point clouds, 2018 | Fuwen PDF | |
| basics | Geometric Deep Learning (simple introduction video) | URL | |
| matching | All Graphs Lead to Rome: Learning Geometric and Cycle-Consistent Representations with Graph Convolutional Networks | Fuwen PDF | |
| completion | Geometric matrix completion with recurrent multi-graph neural networks | Fuwen PDF | |
| Tutorial | Geometric Deep Learning on Graphs and Manifolds | URL | Arsh PDF |
| matching | Similarity Learning with Higher-Order Proximity for Brain Network Analysis | Arsh PDF | |
| pairwise | Pixel to Graph with Associative Embedding | Fuwen PDF | |
| 3D | 3D steerable cnns: Learning rotationally equivariant features in volumetric data | URL | Fuwen PDF |
read on: - 01 Feb 2019
| Presenter | Papers | Paper URL | Our Slides |
|---|---|---|---|
| Matching | Deep Learning of Graph Matching, | PDF+ PDF | Jack Pdf |
| Matching | Graph Edit Distance Computation via Graph Neural Networks | Jack Pdf | |
| Basics | Link Prediction Based on Graph Neural Networks | Jack Pdf | |
| Basics | Supervised Community Detection with Line Graph Neural Networks | Jack Pdf | |
| Basics | Graph mining: Laws, generators, and algorithms | Arshdeep PDF | |
| pooling | Hierarchical graph representation learning with differentiable pooling | Eamon PDF |
read on: - 21 Dec 2018
| Presenter | Papers | Paper URL | Our Slides |
|---|---|---|---|
| Arshdeep | Constrained Graph Variational Autoencoders for Molecule Design | ||
| Arshdeep | Learning Deep Generative Models of Graphs | ||
| Arshdeep | Graph Convolutional Policy Network for Goal-Directed Molecular Graph Generation | ||
| Jack | Generating and designing DNA with deep generative models |
read on: - 20 Dec 2018
| Presenter | Papers | Paper URL | Our Slides |
|---|---|---|---|
| Bill | Seq2SQL: Generating Structured Queries from Natural Language using Reinforcement Learning | ||
| Chao | Deep EHR: A Survey of Recent Advances in Deep Learning Techniques for Electronic Health Record (EHR) Analysis (I) | ||
| Chao | Deep EHR: A Survey of Recent Advances in Deep Learning Techniques for Electronic Health Record (EHR) Analysis (II) | ||
| Derrick | Deep EHR: A Survey of Recent Advances in Deep Learning Techniques for Electronic Health Record (EHR) Analysis (III) | ||
| Chao | Reading Wikipedia to Answer Open-Domain Questions | ||
| Jennifer | Open Domain Question Answering Using Early Fusion of Knowledge Bases and Text |
read on: - 16 Oct 2018
| Presenter | Papers | Paper URL | Our Slides |
|---|---|---|---|
| Eric | Modeling polypharmacy side effects with graph convolutional networks | ||
| Eric | Protein Interface Prediction using Graph Convolutional Networks | ||
| Eric | Structure biology meets data science: does anything change | URL | |
| Eric | DeepSite: protein-binding site predictor using 3D-convolutional neural networks | URL |
read on: - 12 Jan 2017
| Presenter | Papers | Paper URL | Our Slides |
|---|---|---|---|
| QA | Learning to rank with (a lot of) word features | ||
| Relation | A semantic matching energy function for learning with multi-relational data | ||
| Relation | Translating embeddings for modeling multi-relational data | ||
| QA | Reading wikipedia to answer open-domain questions | ||
| QA | Question answering with subgraph embeddings |
[65]: graph-attention
Table of readings
read on: - 05 Jan 2020
| Index | Papers | Our Slides |
|---|---|---|
| 1 | Graph Convolutions: More than You Wanted to Know | Derrick Survey |
| 2 | Spectral Graph Sparsification | Derrick Survey |
| 3 | Complexity Analysis of Graph Convolutional Networks and in Attention based GNN | Derrick Survey |
| 4 | PyTorch-BigGraph: A Large-Scale Graph Embedding System | Derrick Survey |
| 5 | Scalable GNN Updates: More About PyTorch Geometric (PyG) | Derrick Survey |
| 6 | Time and Space Complexity of Graph Convolutional Networks | Derrick Survey |
| 7 | Large Scale GNN and Transformer Models and for Genomics | Jack Survey |
| 8 | Long Range Attention and Visualizing BERT | Jak Survey |
| 9 | Benchmarking Graph Neural Networks | Sanchit Survey |
[66]: graphical-model
Table of readings
read on: - 15 Mar 2019
| Presenter | Papers | Paper URL | Our Slides |
|---|---|---|---|
| Generate | Maximum-Likelihood Augmented Discrete Generative Adversarial Networks | Tkach PDF + GaoJi Pdf | |
| Generate | Graphical Generative Adversarial Networks | Arshdeep PDF | |
| Generate | GraphRNN: Generating Realistic Graphs with Deep Auto-regressive Models, ICML2018 | Arshdeep PDF | |
| Generate | Inference in probabilistic graphical models by Graph Neural Networks | Arshdeep PDF | |
| Generate | Encoding robust representation for graph generation | Arshdeep PDF | |
| Generate | Junction Tree Variational Autoencoder for Molecular Graph Generation | Tkach PDF + Arshdeep Pdf | |
| Generate | Graph Convolutional Policy Network for Goal-Directed Molecular Graph Generation NeurIPS18 | Tkach PDF | |
| Generate | Towards Variational Generation of Small Graphs | Tkach PDF + Arshdeep Pdf | |
| Generate | Convolutional Imputation of Matrix Networks | Tkach PDF | |
| Generate | Graph Convolutional Matrix Completion | Tkach PDF | |
| Generate | NetGAN: Generating Graphs via Random Walks ICML18 | [ULR] | Tkach PDF |
| Beam | Stochastic Beams and Where to Find Them: The Gumbel-Top-k Trick for Sampling Sequences Without Replacement | URL | Tkach PDF |
read on: - 14 Nov 2017
| Presenter | Papers | Paper URL | Our Slides |
|---|---|---|---|
| ChaoJiang | Courville - Generative Models II | DLSS17Slide + video | |
| GaoJi | Attend, Infer, Repeat: Fast Scene Understanding with Generative Models, NIPS16 1 | PDF + talk | |
| Arshdeep | Composing graphical models with neural networks for structured representations and fast inference, NIPS16 2 | ||
| Johnson - Graphical Models and Deep Learning | DLSSSlide + video | ||
| Parallel Multiscale Autoregressive Density Estimation, ICML17 3 | |||
| Beilun | Conditional Image Generation with Pixel CNN Decoders, NIPS16 4 | ||
| Shijia | Marrying Graphical Models & Deep Learning | DLSS17 + Video |
[67]: hash
Table of readings
read on: - 20 Jan 2017
| Presenter | Papers | Paper URL | Our Slides |
|---|---|---|---|
| scalable | Sanjiv Kumar (Columbia EECS 6898), Lecture: Introduction to large-scale machine learning 2010 [^1] | ||
| data scalable | Alex Smola - Berkeley SML: Scalable Machine Learning: Syllabus 2012 [^2] | PDF 2014 + PDF | |
| Binary | Binarized Neural Networks: Training Deep Neural Networks with Weights and Activations Constrained to +1 or -1 | ||
| Model | Binary embeddings with structured hashed projections 1 | ||
| Model | Deep Compression: Compressing Deep Neural Networks (ICLR 2016) 2 |
[68]: heterogeneous
Table of readings
read on: - 17 Feb 2019
| Presenter | Papers | Paper URL | Our Slides |
|---|---|---|---|
| Program | Neural network-based graph embedding for cross-platform binary code similarity detection | Pdf + Pdf | Faizan PDF + GaoJi Pdf |
| Program | Deep Program Reidentification: A Graph Neural Network Solution | Weilin PDF | |
| Program | Heterogeneous Graph Neural Networks for Malicious Account Detection | Weilin Pdf | |
| Program | Learning to represent programs with graphs | Pdf 1 |
[69]: hierarchical
Table of readings
read on: - 22 Mar 2019
| Presenter | Papers | Paper URL | Our Slides |
|---|---|---|---|
| Scalable | FastGCN: Fast Learning with Graph Convolutional Networks via Importance Sampling | Ryan PDF + Arshdeep Pdf | |
| Scalable | MILE: A Multi-Level Framework for Scalable Graph Embedding | Ryan PDF | |
| Scalable | LanczosNet: Multi-Scale Deep Graph Convolutional Networks | Ryan PDF | |
| Scalable | Demystifying Parallel and Distributed Deep Learning: An In-Depth Concurrency Analysis | Derrick PDF | |
| Scalable | Towards Federated learning at Scale: System Design | URL | Derrick PDF |
| Scalable | DNN Dataflow Choice Is Overrated | Derrick PDF | |
| Scalable | Towards Efficient Large-Scale Graph Neural Network Computing | Derrick PDF | |
| Scalable | PyTorch Geometric | URL | |
| Scalable | PyTorch BigGraph | URL | |
| Scalable | Simplifying Graph Convolutional Networks | ||
| Scalable | Cluster-GCN: An Efficient Algorithm for Training Deep and Large Graph Convolutional Networks |
read on: - 30 Nov 2017
| Presenter | Papers | Paper URL | Our Slides |
|---|---|---|---|
| Ceyer | Reinforcement Learning with Unsupervised Auxiliary Tasks, ICLR17 1 | ||
| Beilun | Why is Posterior Sampling Better than Optimism for Reinforcement Learning? Ian Osband, Benjamin Van Roy 2 | ||
| Ji | Deeply AggreVaTeD: Differentiable Imitation Learning for Sequential Prediction, ICML17 3 | ||
| Xueying | End-to-End Differentiable Adversarial Imitation Learning, ICML17 4 | ||
| Deep Value Networks Learn to Evaluate and Iteratively Refine Structured Outputs, ICML17 | |||
| FeUdal Networks for Hierarchical Reinforcement Learning, ICML17 5 |
read on: - 17 Oct 2017
| Presenter | Papers | Paper URL | Our Slides |
|---|---|---|---|
| Jack | Learning to Query, Reason, and Answer Questions On Ambiguous Texts, ICLR17 1 | ||
| Arshdeep | Making Neural Programming Architectures Generalize via Recursion, ICLR17 2 | ||
| Xueying | Towards Deep Interpretability (MUS-ROVER II): Learning Hierarchical Representations of Tonal Music, ICLR17 3 |
[70]: high-dimensional
Table of readings
read on: - 23 Oct 2017
| Presenter | Papers | Paper URL | Our Slides |
|---|---|---|---|
| GaoJi | Delving into Transferable Adversarial Examples and Black-box Attacks,ICLR17 1 | ||
| Shijia | On Detecting Adversarial Perturbations, ICLR17 2 | ||
| Anant | Parseval Networks: Improving Robustness to Adversarial Examples, ICML17 3 | ||
| Bargav | Being Robust (in High Dimensions) Can Be Practical, ICML17 4 |
[71]: human-alignment
Table of readings
read on: - 03 Dec 2022
| Papers | Paper URL | Abstract |
|---|---|---|
| Training language models to follow instructions with human feedback | URL | “further fine-tune this supervised model using reinforcement learning from human feedback. We call the resulting models InstructGPT.” |
| Deep reinforcement learning from human preferences | URL | “explore goals defined in terms of (non-expert) human preferences between pairs of trajectory segments. We show that this approach can effectively solve complex RL tasks without access to the reward function” |
[72]: hyperparameter
Table of readings
read on: - 25 Oct 2018
| Presenter | Papers | Paper URL | Our Slides |
|---|---|---|---|
| Arshdeep | Learning Transferable Architectures for Scalable Image Recognition | ||
| Arshdeep | FractalNet: Ultra-Deep Neural Networks without Residuals |
read on: - 07 Nov 2017
| Presenter | Papers | Paper URL | Our Slides |
|---|---|---|---|
| GaoJi | Forward and Reverse Gradient-Based Hyperparameter Optimization, ICML17 1 | ||
| Chaojiang | Adaptive Neural Networks for Efficient Inference, ICML17 2 | ||
| Bargav | Practical Gauss-Newton Optimisation for Deep Learning, ICML17 3 | ||
| Rita | How to Escape Saddle Points Efficiently, ICML17 4 | ||
| Batched High-dimensional Bayesian Optimization via Structural Kernel Learning |
[73]: image-synthesis
Table of readings
read on: - 01 Dec 2022
Stable diffusion
- URL
- “High-Resolution Image Synthesis with Latent Diffusion Models”
DreamBooth: Fine Tuning Text-to-Image Diffusion Models for Subject-Driven Generation
- URL
- “personalization” of text-to-image diffusion models. Given as input just a few images of a subject, we fine-tune a pretrained text-to-image model such that it learns to bind a unique identifier with that specific subject. .”
LoRA: Low-Rank Adaptation of Large Language Models
- URL
-
“propose Low-Rank Adaptation, or LoRA, which freezes the pre-trained model weights and injects trainable rank decomposition matrices into each layer of the Transformer architecture, greatly reducing the number of trainable parameters for downstream tasks. Compared to GPT-3 175B fine-tuned with Adam, LoRA can reduce the number of trainable parameters by 10,000 times and the GPU memory requirement by 3 times.”
An Image is Worth One Word: Personalizing Text-to-Image Generation using Textual Inversion
- https://arxiv.org/abs/2208.01618
- Rinon Gal, Yuval Alaluf, Yuval Atzmon, Or Patashnik, Amit H. Bermano, Gal Chechik, Daniel Cohen-Or
- Text-to-image models offer unprecedented freedom to guide creation through natural language. Yet, it is unclear how such freedom can be exercised to generate images of specific unique concepts, modify their appearance, or compose them in new roles and novel scenes. In other words, we ask: how can we use language-guided models to turn our cat into a painting, or imagine a new product based on our favorite toy? Here we present a simple approach that allows such creative freedom. Using only 3-5 images of a user-provided concept, like an object or a style, we learn to represent it through new “words” in the embedding space of a frozen text-to-image model. These “words” can be composed into natural language sentences, guiding personalized creation in an intuitive way. Notably, we find evidence that a single word embedding is sufficient for capturing unique and varied concepts. We compare our approach to a wide range of baselines, and demonstrate that it can more faithfully portray the concepts across a range of applications and tasks.
[74]: imitation-learning
Table of readings
read on: - 30 Nov 2017
| Presenter | Papers | Paper URL | Our Slides |
|---|---|---|---|
| Ceyer | Reinforcement Learning with Unsupervised Auxiliary Tasks, ICLR17 1 | ||
| Beilun | Why is Posterior Sampling Better than Optimism for Reinforcement Learning? Ian Osband, Benjamin Van Roy 2 | ||
| Ji | Deeply AggreVaTeD: Differentiable Imitation Learning for Sequential Prediction, ICML17 3 | ||
| Xueying | End-to-End Differentiable Adversarial Imitation Learning, ICML17 4 | ||
| Deep Value Networks Learn to Evaluate and Iteratively Refine Structured Outputs, ICML17 | |||
| FeUdal Networks for Hierarchical Reinforcement Learning, ICML17 5 |
[75]: imputation
Table of readings
read on: - 15 Mar 2019
| Presenter | Papers | Paper URL | Our Slides |
|---|---|---|---|
| Generate | Maximum-Likelihood Augmented Discrete Generative Adversarial Networks | Tkach PDF + GaoJi Pdf | |
| Generate | Graphical Generative Adversarial Networks | Arshdeep PDF | |
| Generate | GraphRNN: Generating Realistic Graphs with Deep Auto-regressive Models, ICML2018 | Arshdeep PDF | |
| Generate | Inference in probabilistic graphical models by Graph Neural Networks | Arshdeep PDF | |
| Generate | Encoding robust representation for graph generation | Arshdeep PDF | |
| Generate | Junction Tree Variational Autoencoder for Molecular Graph Generation | Tkach PDF + Arshdeep Pdf | |
| Generate | Graph Convolutional Policy Network for Goal-Directed Molecular Graph Generation NeurIPS18 | Tkach PDF | |
| Generate | Towards Variational Generation of Small Graphs | Tkach PDF + Arshdeep Pdf | |
| Generate | Convolutional Imputation of Matrix Networks | Tkach PDF | |
| Generate | Graph Convolutional Matrix Completion | Tkach PDF | |
| Generate | NetGAN: Generating Graphs via Random Walks ICML18 | [ULR] | Tkach PDF |
| Beam | Stochastic Beams and Where to Find Them: The Gumbel-Top-k Trick for Sampling Sequences Without Replacement | URL | Tkach PDF |
[76]: influence-functions
Table of readings
read on: - 22 Jul 2017
| Presenter | Papers | Paper URL | Our Slides |
|---|---|---|---|
| GaoJi | A few useful things to know about machine learning | ||
| GaoJi | A few papers related to testing learning, e.g., Understanding Black-box Predictions via Influence Functions | ||
| GaoJi | Automated White-box Testing of Deep Learning Systems 1 | ||
| GaoJi | Testing and Validating Machine Learning Classifiers by Metamorphic Testing 2 | ||
| GaoJi | Software testing: a research travelogue (2000–2014) |
[77]: infomax
Table of readings
read on: - 11 Oct 2018
| Presenter | Papers | Paper URL | Our Slides |
|---|---|---|---|
| Arshdeep | Relational inductive biases, deep learning, and graph networks | ||
| Arshdeep | Discriminative Embeddings of Latent Variable Models for Structured Data | ||
| Jack | Deep Graph Infomax |
read on: - 12 Sep 2017
| Presenter | Papers | Paper URL | Our Slides |
|---|---|---|---|
| Ceyer | A Closer Look at Memorization in Deep Networks, ICML17 1 | ||
| On the Expressive Efficiency of Overlapping Architectures of Deep Learning 2 | DLSSpdf + video | ||
| Mutual Information | Opening the Black Box of Deep Neural Networks via Information 3 | URL + video | |
| ChaoJiang | Toward Deeper Understanding of Neural Networks: The Power of Initialization and a Dual View on Expressivity, NIPS16 |
Table of readings
read on: - 28 Sep 2017
| Presenter | Papers | Paper URL | Our Slides |
|---|---|---|---|
| Jack | Attend, Adapt and Transfer: Attentive Deep Architecture for Adaptive Transfer from multiple sources in the same domain, ICLR17 1 | ||
| Arshdeep | Bidirectional Attention Flow for Machine Comprehension, ICLR17 2 | PDF + code | |
| Ceyer | Image-to-Markup Generation with Coarse-to-Fine Attention, ICML17 | PDF + code | |
| ChaoJiang | Can Active Memory Replace Attention? ; Samy Bengio, NIPS16 3 | ||
| An Information-Theoretic Framework for Fast and Robust Unsupervised Learning via Neural Population Infomax, ICLR17 |
[78]: informax
Table of readings
read on: - 12 Dec 2019
| Team INDEX | Title & Link | Tags | Our Slide |
|---|---|---|---|
| T2 | Empirical Study of Example Forgetting During Deep Neural Network Learning | Sample Selection, forgetting | OurSlide |
| T29 | Select Via Proxy: Efficient Data Selection For Training Deep Networks | Sample Selection | OurSlide |
| T9 | How SGD Selects the Global Minima in over-parameterized Learning | optimization | OurSlide |
| T10 | Escaping Saddles with Stochastic Gradients | optimization | OurSlide |
| T13 | To What Extent Do Different Neural Networks Learn the Same Representation | subspace | OurSlide |
| T19 | On the Information Bottleneck Theory of Deep Learning | informax | OurSlide |
| T20 | Visualizing the Loss Landscape of Neural Nets | normalization | OurSlide |
| T21 | Using Pre-Training Can Improve Model Robustness and Uncertainty | training, analysis | OurSlide |
| T24 | Norm matters: efficient and accurate normalization schemes in deep networks | normalization | OurSlide |
[79]: interpretable
Table of readings
read on: - 05 Aug 2020
| Index | Papers | Our Slides |
|---|---|---|
| 0 | A survey on Interpreting Deep Learning Models | Eli Survey |
| Interpretable Machine Learning: Definitions,Methods, Applications | Arsh Survey | |
| 1 | Explaining Explanations: Axiomatic Feature Interactions for Deep Networks | Arsh Survey |
| 2 | Shapley Value review | Arsh Survey |
| L-Shapley and C-Shapley: Efficient Model Interpretation for Structured Data | Bill Survey | |
| Consistent Individualized Feature Attribution for Tree Ensembles | bill Survey | |
| Summary for A value for n-person games | Pan Survey | |
| L-Shapley and C-Shapley: Efficient Model Interpretation for Structured Data | Rishab Survey | |
| 3 | Hierarchical Interpretations of Neural Network Predictions | Arsh Survey |
| Hierarchical Interpretations of Neural Network Predictions | Rishab Survey | |
| 4 | Beyond Word Importance: Contextual Decomposition to Extract Interactions from LSTMs | Arsh Survey |
| Beyond Word Importance: Contextual Decomposition to Extract Interactions from LSTMs | Rishab Survey | |
| 5 | Towards Hierarchical Importance Attribution: Explaining Compositional Semantics for Neural Sequence Models | Rishab Survey |
| Sanchit Survey | ||
| Generating Hierarchical Explanations on Text Classification via Feature Interaction Detection | Sanchit Survey | |
| 6 | This Looks Like That: Deep Learning for Interpretable Image Recognition | Pan Survey |
| 7 | AllenNLP Interpret | Rishab Survey |
| 8 | DISCOVERY OF NATURAL LANGUAGE CONCEPTS IN INDIVIDUAL UNITS OF CNNs | Rishab Survey |
| 9 | How Does BERT Answer Questions? A Layer-Wise Analysis of Transformer Representations | Rishab Survey |
| 10 | Attention is not Explanation | Sanchit Survey |
| Pan Survey | ||
| 11 | Axiomatic Attribution for Deep Networks | Sanchit Survey |
| 12 | Grad-CAM: Visual Explanations from Deep Networks via Gradient-based Localization | Sanchit Survey |
| 13 | Learning Variational Word Masks to Improve the Interpretability of Neural Text Classifier | Sanchit Survey |
| 14 | “Why Should I Trust You?”Explaining the Predictions of Any Classifier | Yu Survey |
| 15 | INTERPRETATIONS ARE USEFUL: PENALIZING EXPLANATIONS TO ALIGN NEURAL NETWORKS WITH PRIOR KNOWLEDGE | Pan Survey |
read on: - 05 Apr 2019
| Presenter | Papers | Paper URL | Our Slides |
|---|---|---|---|
| Understand | Faithful and Customizable Explanations of Black Box Models | Derrick PDF | |
| Understand | A causal framework for explaining the predictions of black-box sequence-to-sequence models, EMNLP17 | GaoJi PDF + Bill Pdf | |
| Understand | How Powerful are Graph Neural Networks? / Deeper Insights into Graph Convolutional Networks for Semi-Supervised Learning | Pdf + Pdf | GaoJi PDF |
| Understand | Interpretable Graph Convolutional Neural Networks for Inference on Noisy Knowledge Graphs + GNN Explainer: A Tool for Post-hoc Explanation of Graph Neural Networks | Pdf + PDF | GaoJi PDF |
| Understand | Attention is not Explanation, 2019 | ||
| Understand | Understanding attention in graph neural networks, 2019 |
read on: - 02 Dec 2018
| Presenter | Papers | Paper URL | Our Slides |
|---|---|---|---|
| Jennifer | Adversarial Attacks Against Medical Deep Learning Systems | ||
| Jennifer | Adversarial-Playground: A Visualization Suite Showing How Adversarial Examples Fool Deep Learning | ||
| Jennifer | Black-box Generation of Adversarial Text Sequences to Evade Deep Learning Classifiers | ||
| Jennifer | CleverHans | ||
| Ji | Ji-f18-New papers about adversarial attack |
read on: - 20 Nov 2018
| Presenter | Papers | Paper URL | Our Slides |
|---|---|---|---|
| Bill | Adversarial Examples that Fool both Computer Vision and Time-Limited Humans | ||
| Bill | Adversarial Attacks Against Medical Deep Learning Systems | ||
| Bill | TensorFuzz: Debugging Neural Networks with Coverage-Guided Fuzzing | ||
| Bill | Distilling the Knowledge in a Neural Network | ||
| Bill | Defensive Distillation is Not Robust to Adversarial Examples | ||
| Bill | Adversarial Logit Pairing , Harini Kannan, Alexey Kurakin, Ian Goodfellow |
read on: - 12 May 2018
| Presenter | Papers | Paper URL | Our Slides |
|---|---|---|---|
| Bill | Intriguing Properties of Adversarial Examples, Ekin D. Cubuk, Barret Zoph, Samuel S. Schoenholz, Quoc V. Le 1 | ||
| Bill | Adversarial Spheres 2 | ||
| Bill | Adversarial Transformation Networks: Learning to Generate Adversarial Examples, Shumeet Baluja, Ian Fischer 3 | ||
| Bill | Thermometer encoding: one hot way to resist adversarial examples 4 | ||
| Adversarial Logit Pairing , Harini Kannan, Alexey Kurakin, Ian Goodfellow 5 |
read on: - 10 Oct 2017
| Presenter | Papers | Paper URL | Our Slides |
|---|---|---|---|
| Rita | Learning Important Features Through Propagating Activation Differences, ICML17 1 | ||
| GaoJi | Examples are not Enough, Learn to Criticize! Model Criticism for Interpretable Machine Learning, NIPS16 2 | ||
| Rita | Learning Kernels with Random Features, Aman Sinha*; John Duchi, 3 |
read on: - 21 Sep 2017
| Presenter | Papers | Paper URL | Our Slides |
|---|---|---|---|
| Shijia | Outrageously Large Neural Networks: The Sparsely-Gated Mixture-of-Experts Layer, (Dean), ICLR17 1 | ||
| Ceyer | Sequence Modeling via Segmentations, ICML17 2 | ||
| Arshdeep | Input Switched Affine Networks: An RNN Architecture Designed for Interpretability, ICML17 3 |
read on: - 19 Jan 2017
| Presenter | Papers | Paper URL | Our Slides |
|---|---|---|---|
| AE | Intriguing properties of neural networks / | ||
| AE | Explaining and Harnessing Adversarial Examples | ||
| AE | Towards Deep Learning Models Resistant to Adversarial Attacks | ||
| AE | DeepFool: a simple and accurate method to fool deep neural networks | ||
| AE | Towards Evaluating the Robustness of Neural Networks by Carlini and Wagner | ||
| Data | Basic Survey of ImageNet - LSVRC competition | URL | |
| Understand | Understanding Black-box Predictions via Influence Functions | ||
| Understand | Deep inside convolutional networks: Visualising image classification models and saliency maps | ||
| Understand | BeenKim, Interpretable Machine Learning, ICML17 Tutorial [^1] | ||
| provable | Provable defenses against adversarial examples via the convex outer adversarial polytope, Eric Wong, J. Zico Kolter, | URL |
Table of readings
read on: - 12 Oct 2018
| Presenter | Papers | Paper URL | Our Slides |
|---|---|---|---|
| Jack | A Unified Approach to Interpreting Model Predictions | ||
| Jack | “Why Should I Trust You?”: Explaining the Predictions of Any Classifier | ||
| Jack | Visual Feature Attribution using Wasserstein GANs | ||
| Jack | GAN Dissection: Visualizing and Understanding Generative Adversarial Networks | ||
| GaoJi | Recent Interpretable machine learning papers | ||
| Jennifer | The Building Blocks of Interpretability |
[80]: invariant
Table of readings
read on: - 22 Feb 2019
| Presenter | Papers | Paper URL | Our Slides |
|---|---|---|---|
| spherical | Spherical CNNs | Fuwen PDF + Arshdeep Pdf | |
| dynamic | Dynamic graph cnn for learning on point clouds, 2018 | Fuwen PDF | |
| basics | Geometric Deep Learning (simple introduction video) | URL | |
| matching | All Graphs Lead to Rome: Learning Geometric and Cycle-Consistent Representations with Graph Convolutional Networks | Fuwen PDF | |
| completion | Geometric matrix completion with recurrent multi-graph neural networks | Fuwen PDF | |
| Tutorial | Geometric Deep Learning on Graphs and Manifolds | URL | Arsh PDF |
| matching | Similarity Learning with Higher-Order Proximity for Brain Network Analysis | Arsh PDF | |
| pairwise | Pixel to Graph with Associative Embedding | Fuwen PDF | |
| 3D | 3D steerable cnns: Learning rotationally equivariant features in volumetric data | URL | Fuwen PDF |
read on: - 25 Jan 2019
| Presenter | Papers | Paper URL | Our Notes |
|---|---|---|---|
| Basics | GraphSAGE: Large-scale Graph Representation Learning by Jure Leskovec Stanford University | URL + PDF | |
| Basics | Convolutional Neural Networks on Graphs with Fast Localized Spectral Filtering by Xavier Bresson | URL + PDF | Ryan Pdf |
| Basics | Gated Graph Sequence Neural Networks by Microsoft Research | URL + PDF | Faizan Pdf |
| Basics | DeepWalk - Turning Graphs into Features via Network Embeddings | URL + PDF | |
| Basics | Spectral Networks and Locally Connected Networks on Graphs 1 | GaoJi slides + Bill Pdf | |
| Basics | A Comprehensive Survey on Graph Neural Networks/ Graph Neural Networks: A Review of Methods and Applications | Jack Pdf | |
| GCN | Semi-Supervised Classification with Graph Convolutional Networks | Jack Pdf |
read on: - 21 Jan 2017
| Presenter | Papers | Paper URL | Our Slides |
|---|---|---|---|
| DeepBind | Predicting the sequence specificities of DNA- and RNA-binding proteins by deep learning | ||
| DeepSEA | Deep learning sequence-based ab initio prediction of variant effects on expression and disease risk | ||
| DeepSEA | Deep Supervised and Convolutional Generative Stochastic Network for Protein Secondary Structure Prediction, ICML 2014 | ||
| BioBasics | A method for integrating and ranking the evidence for biochemical pathways by mining reactions from text, Bioinformatics13 | ||
| BioBasics | Efficient counting of k-mers in DNA sequences using a Bloom filter. Melsted P, Pritchard JK. BMC Bioinformatics. 2011 | ||
| BioBasics | Fast String Kernels using Inexact Matching for Protein Sequence, JMLR 2004 | ||
| BioBasics | NIPS09: Locality-Sensitive Binary Codes from Shift-Invariant Kernels | ||
| MedSignal | Segmenting Time Series: A Survey and Novel Approach, |
[81]: knowledge-graph
Table of readings
read on: - 05 Apr 2019
| Presenter | Papers | Paper URL | Our Slides |
|---|---|---|---|
| Understand | Faithful and Customizable Explanations of Black Box Models | Derrick PDF | |
| Understand | A causal framework for explaining the predictions of black-box sequence-to-sequence models, EMNLP17 | GaoJi PDF + Bill Pdf | |
| Understand | How Powerful are Graph Neural Networks? / Deeper Insights into Graph Convolutional Networks for Semi-Supervised Learning | Pdf + Pdf | GaoJi PDF |
| Understand | Interpretable Graph Convolutional Neural Networks for Inference on Noisy Knowledge Graphs + GNN Explainer: A Tool for Post-hoc Explanation of Graph Neural Networks | Pdf + PDF | GaoJi PDF |
| Understand | Attention is not Explanation, 2019 | ||
| Understand | Understanding attention in graph neural networks, 2019 |
read on: - 29 Mar 2019
| Presenter | Papers | Paper URL | Our Slides |
|---|---|---|---|
| QA | A Comparison of Current Graph Database Models | Pdf + PDF2 | Bill PDF |
| QA | Open Domain Question Answering Using Early Fusion of Knowledge Bases and Text | Bill [PDF + GaoJi Pdf | |
| QA | Generative Question Answering: Learning to Answer the Whole Question, Mike Lewis, Angela Fan | Bill PDF + GaoJi Pdf | |
| QA | Learning to Reason Science Exam Questions with Contextual Knowledge Graph Embeddings / Knowledge Graph Embedding via Dynamic Mapping Matrix | PDF + Pdf | Bill PDF + GaoJi Pdf |
| Text | Adversarial Text Generation via Feature-Mover’s Distance | URL | Faizan PDF |
| Text | Content preserving text generation with attribute controls | URL | Faizan PDF |
| Text | Multiple-Attribute Text Rewriting, ICLR, 2019, | URL | Faizan PDF |
| Text | Writeprints: a stylometric approach to identity level identification and similarity detection in cyberSpace | URL | Faizan PDF |
[82]: language-model
Table of readings
read on: - 03 Dec 2022
| Papers | Paper URL | Abstract |
|---|---|---|
| Training language models to follow instructions with human feedback | URL | “further fine-tune this supervised model using reinforcement learning from human feedback. We call the resulting models InstructGPT.” |
| Deep reinforcement learning from human preferences | URL | “explore goals defined in terms of (non-expert) human preferences between pairs of trajectory segments. We show that this approach can effectively solve complex RL tasks without access to the reward function” |
read on: - 01 Oct 2022
Emergent Abilities of Large Language Models
- URL
- “an ability to be emergent if it is not present in smaller models but is present in larger models. Thus, emergent abilities cannot be predicted simply by extrapolating the performance of smaller models.”
Language Models are Few-Shot Learners
- URL
- “GPT-3, 175B autoregerssive LLM; show that scaling up language models greatly improves task-agnostic, few-shot performance, sometimes even reaching competitiveness with prior state-of-the-art fine-tuning approaches.”
On the Opportunities and Risks of Foundation Models
- URL
-
” a thorough account of the opportunities and risks of foundation models, ranging from their capabilities (e.g., language, vision, robotics, reasoning, human interaction) and technical principles(e.g., model architectures, training procedures, data, systems, security, evaluation, theory) to their applications (e.g., law, healthcare, education) and societal impact (e.g., inequity, misuse, economic and environmental impact, legal and ethical considerations).”
The Power of Scale for Parameter-Efficient Prompt Tuning
- https://arxiv.org/abs/2104.08691
- Brian Lester, Rami Al-Rfou, Noah Constant
- In this work, we explore “prompt tuning”, a simple yet effective mechanism for learning “soft prompts” to condition frozen language models to perform specific downstream tasks. Unlike the discrete text prompts used by GPT-3, soft prompts are learned through backpropagation and can be tuned to incorporate signal from any number of labeled examples. Our end-to-end learned approach outperforms GPT-3’s “few-shot” learning by a large margin. More remarkably, through ablations on model size using T5, we show that prompt tuning becomes more competitive with scale: as models exceed billions of parameters, our method “closes the gap” and matches the strong performance of model tuning (where all model weights are tuned). This finding is especially relevant in that large models are costly to share and serve, and the ability to reuse one frozen model for multiple downstream tasks can ease this burden. Our method can be seen as a simplification of the recently proposed “prefix tuning” of Li and Liang (2021), and we provide a comparison to this and other similar approaches. Finally, we show that conditioning a frozen model with soft prompts confers benefits in robustness to domain transfer, as compared to full model tuning.
read on: - 01 Sep 2022
| Papers | Paper URL | Abstract |
|---|---|---|
| Evolutionary-scale prediction of atomic level protein structure with a language model | URL | “show that direct inference of structure from primary sequence using a large language model enables an order of magnitude speed-up in high resolution structure prediction. Leveraging the insight that language models learn evolutionary patterns across millions of sequences, we train models up to 15B parameters,…” |
| DiffDock: Diffusion Steps, Twists, and Turns for Molecular Docking | URL | “Recent deep learning methods that treat docking as a regression problem have decreased runtime compared to traditional search-based methods but have yet to offer substantial improvements in accuracy. We instead frame molecular docking as a generative modeling problem and develop DiffDock, a diffusion generative model over the non-Euclidean manifold of ligand poses. To do so, we map this manifold to the product space of the degrees of freedom (translational, rotational, and torsional) involved in docking and develop an efficient diffusion process on this space.” |
[83]: language-processing
Table of readings
read on: - 05 Jun 2020
| Index | Papers | Our Slides |
|---|---|---|
| 1 | Protein 3D Structure Computed from Evolutionary Sequence Variation | Arsh Survey |
| 3 | Regulatory network inference on developmental and evolutionary lineages | Arsh Survey |
| 4 | Deep learning in ultrasound image analysis | Zhe Survey |
| 5 | Predicting the sequence specificities of DNA- and RNA-binding proteins by deep learning (DeepBind) | Jack Survey |
| 6 | Canonical and single-cell Hi-C reveal distinct chromatin interaction sub-networks of mammalian transcription factors | Jack Survey |
| 7 | BindSpace decodes transcription factor binding signals by large-scale sequence embedding | Jack Survey |
| 8 | FastXML: A Fast, Accurate and Stable Tree-classifier for eXtreme Multi-label Learning | Jack Survey |
| 9 | Query-Reduction Networks for Question Answering | Bill Survey |
[84]: learn2learn
Table of readings
read on: - 22 Jun 2017
| Presenter | Papers | Paper URL | Our Slides |
|---|---|---|---|
| Arshdeep | Image Question Answering using Convolutional Neural Network with Dynamic Parameter Prediction 1 | ||
| Arshdeep | Decoupled Neural Interfaces Using Synthetic Gradients 2 | ||
| Arshdeep | Diet Networks: Thin Parameters for Fat Genomics 3 | ||
| Arshdeep | Metric Learning with Adaptive Density Discrimination 4 |
read on: - 02 Jun 2017
| Presenter | Papers | Paper URL | Our Slides |
|---|---|---|---|
| Arshdeep | HyperNetworks, David Ha, Andrew Dai, Quoc V. Le ICLR 2017 1 | ||
| Arshdeep | Learning feed-forward one-shot learners 2 | ||
| Arshdeep | Learning to Learn by gradient descent by gradient descent 3 | ||
| Arshdeep | Dynamic Filter Networks 4 https://arxiv.org/abs/1605.09673 |
[85]: loss
Table of readings
read on: - 11 Dec 2019
| Team INDEX | Title & Link | Tags | Our Slide | |
|---|---|---|---|---|
| T5 | Deep Structured Prediction with Nonlinear Output Transformations | structured | OurSlide | |
| T12 | Large Margin Deep Networks for Classification | OurSlide | large-margin | |
| T15 | Wide Activation for Efficient and Accurate Image Super-Resolution | CNN | OurSlide | |
| T17 | Ordered Neurons: Integrating Tree Structures into Recurrent Neural Networks | RNN | OurSlide | |
| T28 | Processing of missing data by neural networks | imputation | OurSlide | |
| T27 | Implicit Acceleration by Overparameterization | analysis | OurSlide |
[86]: low-rank
Table of readings
read on: - 05 Feb 2020
| Index | Papers | Our Slides |
|---|---|---|
| 1 | Beta VAE, Ladder VAE, Causal VAE | Arsh Survey |
| 2 | Learnt Prior VAE | Arsh Survey |
| 3 | Multitask Graph Autoencoder | Arsh Survey |
| 4 | Introduction to component analysi | Zhe Survey |
| 5 | Normalizing flow | Zhe Survey |
| 6 | Nonlinear ICA | Zhe Survey |
| 7 | Deep Convolutional Inverse Graphics Network | Zhe Survey |
read on: - 22 Jun 2017
| Presenter | Papers | Paper URL | Our Slides |
|---|---|---|---|
| Arshdeep | Image Question Answering using Convolutional Neural Network with Dynamic Parameter Prediction 1 | ||
| Arshdeep | Decoupled Neural Interfaces Using Synthetic Gradients 2 | ||
| Arshdeep | Diet Networks: Thin Parameters for Fat Genomics 3 | ||
| Arshdeep | Metric Learning with Adaptive Density Discrimination 4 |
read on: - 02 Jun 2017
| Presenter | Papers | Paper URL | Our Slides |
|---|---|---|---|
| Arshdeep | HyperNetworks, David Ha, Andrew Dai, Quoc V. Le ICLR 2017 1 | ||
| Arshdeep | Learning feed-forward one-shot learners 2 | ||
| Arshdeep | Learning to Learn by gradient descent by gradient descent 3 | ||
| Arshdeep | Dynamic Filter Networks 4 https://arxiv.org/abs/1605.09673 |
read on: - 20 Jan 2017
| Presenter | Papers | Paper URL | Our Slides |
|---|---|---|---|
| scalable | Sanjiv Kumar (Columbia EECS 6898), Lecture: Introduction to large-scale machine learning 2010 [^1] | ||
| data scalable | Alex Smola - Berkeley SML: Scalable Machine Learning: Syllabus 2012 [^2] | PDF 2014 + PDF | |
| Binary | Binarized Neural Networks: Training Deep Neural Networks with Weights and Activations Constrained to +1 or -1 | ||
| Model | Binary embeddings with structured hashed projections 1 | ||
| Model | Deep Compression: Compressing Deep Neural Networks (ICLR 2016) 2 |
[87]: manifold
Table of readings
read on: - 22 Feb 2019
| Presenter | Papers | Paper URL | Our Slides |
|---|---|---|---|
| spherical | Spherical CNNs | Fuwen PDF + Arshdeep Pdf | |
| dynamic | Dynamic graph cnn for learning on point clouds, 2018 | Fuwen PDF | |
| basics | Geometric Deep Learning (simple introduction video) | URL | |
| matching | All Graphs Lead to Rome: Learning Geometric and Cycle-Consistent Representations with Graph Convolutional Networks | Fuwen PDF | |
| completion | Geometric matrix completion with recurrent multi-graph neural networks | Fuwen PDF | |
| Tutorial | Geometric Deep Learning on Graphs and Manifolds | URL | Arsh PDF |
| matching | Similarity Learning with Higher-Order Proximity for Brain Network Analysis | Arsh PDF | |
| pairwise | Pixel to Graph with Associative Embedding | Fuwen PDF | |
| 3D | 3D steerable cnns: Learning rotationally equivariant features in volumetric data | URL | Fuwen PDF |
[88]: markov
Table of readings
read on: - 05 Jan 2020
| Index | Papers | Our Slides |
|---|---|---|
| 1 | A Flexible Generative Framework for Graph-based Semi-supervised Learning | Arsh Survey |
| 2 | Learning Discrete Structures for Graph Neural Networks | Arsh Survey |
| 4 | Graph Markov Neural Nets | Arsh Survey |
| Graph Markov Neural Networks | Jack Survey | |
| 5 | GLoMo: Unsupervisedly Learned Relational Graphs as Transferable Representations | Arsh Survey |
| 6 | Subgraph Neural Networks | Arsh Survey |
| 7 | Pointer Graph Networks | Arsh Survey |
| 8 | Modeling Relational Data with Graph Convolutional Networks | Arsh Survey |
| 9 | Graph Learning | Zhe Survey |
| 8 | Neural Relational Inference | Zhe Survey |
[89]: matching
Table of readings
read on: - 22 Feb 2019
| Presenter | Papers | Paper URL | Our Slides |
|---|---|---|---|
| spherical | Spherical CNNs | Fuwen PDF + Arshdeep Pdf | |
| dynamic | Dynamic graph cnn for learning on point clouds, 2018 | Fuwen PDF | |
| basics | Geometric Deep Learning (simple introduction video) | URL | |
| matching | All Graphs Lead to Rome: Learning Geometric and Cycle-Consistent Representations with Graph Convolutional Networks | Fuwen PDF | |
| completion | Geometric matrix completion with recurrent multi-graph neural networks | Fuwen PDF | |
| Tutorial | Geometric Deep Learning on Graphs and Manifolds | URL | Arsh PDF |
| matching | Similarity Learning with Higher-Order Proximity for Brain Network Analysis | Arsh PDF | |
| pairwise | Pixel to Graph with Associative Embedding | Fuwen PDF | |
| 3D | 3D steerable cnns: Learning rotationally equivariant features in volumetric data | URL | Fuwen PDF |
read on: - 01 Feb 2019
| Presenter | Papers | Paper URL | Our Slides |
|---|---|---|---|
| Matching | Deep Learning of Graph Matching, | PDF+ PDF | Jack Pdf |
| Matching | Graph Edit Distance Computation via Graph Neural Networks | Jack Pdf | |
| Basics | Link Prediction Based on Graph Neural Networks | Jack Pdf | |
| Basics | Supervised Community Detection with Line Graph Neural Networks | Jack Pdf | |
| Basics | Graph mining: Laws, generators, and algorithms | Arshdeep PDF | |
| pooling | Hierarchical graph representation learning with differentiable pooling | Eamon PDF |
[90]: matching-net
Table of readings
read on: - 18 Jan 2017
| Presenter | Papers | Paper URL | Our Slides |
|---|---|---|---|
| seq2seq | Sequence to Sequence Learning with Neural Networks | ||
| Set | Pointer Networks | ||
| Set | Order Matters: Sequence to Sequence for Sets | ||
| Point Attention | Multiple Object Recognition with Visual Attention | ||
| Memory | End-To-End Memory Networks | Jack Survey | |
| Memory | Neural Turing Machines | ||
| Memory | Hybrid computing using a neural network with dynamic external memory | ||
| Muthu | Matching Networks for One Shot Learning (NIPS16) 1 | ||
| Jack | Meta-Learning with Memory-Augmented Neural Networks (ICML16) 2 | ||
| Metric | ICML07 Best Paper - Information-Theoretic Metric Learning |
[91]: matrix-completion
Table of readings
read on: - 15 Mar 2019
| Presenter | Papers | Paper URL | Our Slides |
|---|---|---|---|
| Generate | Maximum-Likelihood Augmented Discrete Generative Adversarial Networks | Tkach PDF + GaoJi Pdf | |
| Generate | Graphical Generative Adversarial Networks | Arshdeep PDF | |
| Generate | GraphRNN: Generating Realistic Graphs with Deep Auto-regressive Models, ICML2018 | Arshdeep PDF | |
| Generate | Inference in probabilistic graphical models by Graph Neural Networks | Arshdeep PDF | |
| Generate | Encoding robust representation for graph generation | Arshdeep PDF | |
| Generate | Junction Tree Variational Autoencoder for Molecular Graph Generation | Tkach PDF + Arshdeep Pdf | |
| Generate | Graph Convolutional Policy Network for Goal-Directed Molecular Graph Generation NeurIPS18 | Tkach PDF | |
| Generate | Towards Variational Generation of Small Graphs | Tkach PDF + Arshdeep Pdf | |
| Generate | Convolutional Imputation of Matrix Networks | Tkach PDF | |
| Generate | Graph Convolutional Matrix Completion | Tkach PDF | |
| Generate | NetGAN: Generating Graphs via Random Walks ICML18 | [ULR] | Tkach PDF |
| Beam | Stochastic Beams and Where to Find Them: The Gumbel-Top-k Trick for Sampling Sequences Without Replacement | URL | Tkach PDF |
[92]: memorization
Table of readings
read on: - 12 Sep 2017
| Presenter | Papers | Paper URL | Our Slides |
|---|---|---|---|
| Ceyer | A Closer Look at Memorization in Deep Networks, ICML17 1 | ||
| On the Expressive Efficiency of Overlapping Architectures of Deep Learning 2 | DLSSpdf + video | ||
| Mutual Information | Opening the Black Box of Deep Neural Networks via Information 3 | URL + video | |
| ChaoJiang | Toward Deeper Understanding of Neural Networks: The Power of Initialization and a Dual View on Expressivity, NIPS16 |
[93]: memory
Table of readings
read on: - 03 Oct 2017
| Presenter | Papers | Paper URL | Our Slides |
|---|---|---|---|
| Tianlu | Ask Me Anything: Dynamic Memory Networks for Natural Language Processing, ICML17 1 | PDF + code | |
| Jack | Reasoning with Memory Augmented Neural Networks for Language Comprehension, ICLR17 2 | ||
| Xueying | State-Frequency Memory Recurrent Neural Networks, ICML17 3 |
read on: - 28 Sep 2017
| Presenter | Papers | Paper URL | Our Slides |
|---|---|---|---|
| Jack | Attend, Adapt and Transfer: Attentive Deep Architecture for Adaptive Transfer from multiple sources in the same domain, ICLR17 1 | ||
| Arshdeep | Bidirectional Attention Flow for Machine Comprehension, ICLR17 2 | PDF + code | |
| Ceyer | Image-to-Markup Generation with Coarse-to-Fine Attention, ICML17 | PDF + code | |
| ChaoJiang | Can Active Memory Replace Attention? ; Samy Bengio, NIPS16 3 | ||
| An Information-Theoretic Framework for Fast and Robust Unsupervised Learning via Neural Population Infomax, ICLR17 |
read on: - 07 Sep 2017
| Presenter | Papers | Paper URL | Our Slides |
|---|---|---|---|
| Beilun | Learning Deep Parsimonious Representations, NIPS16 1 | ||
| Jack | Dense Associative Memory for Pattern Recognition, NIPS16 2 | PDF + video |
read on: - 18 Jan 2017
| Presenter | Papers | Paper URL | Our Slides |
|---|---|---|---|
| seq2seq | Sequence to Sequence Learning with Neural Networks | ||
| Set | Pointer Networks | ||
| Set | Order Matters: Sequence to Sequence for Sets | ||
| Point Attention | Multiple Object Recognition with Visual Attention | ||
| Memory | End-To-End Memory Networks | Jack Survey | |
| Memory | Neural Turing Machines | ||
| Memory | Hybrid computing using a neural network with dynamic external memory | ||
| Muthu | Matching Networks for One Shot Learning (NIPS16) 1 | ||
| Jack | Meta-Learning with Memory-Augmented Neural Networks (ICML16) 2 | ||
| Metric | ICML07 Best Paper - Information-Theoretic Metric Learning |
[94]: meta-learning
Table of readings
read on: - 18 Jan 2017
| Presenter | Papers | Paper URL | Our Slides |
|---|---|---|---|
| seq2seq | Sequence to Sequence Learning with Neural Networks | ||
| Set | Pointer Networks | ||
| Set | Order Matters: Sequence to Sequence for Sets | ||
| Point Attention | Multiple Object Recognition with Visual Attention | ||
| Memory | End-To-End Memory Networks | Jack Survey | |
| Memory | Neural Turing Machines | ||
| Memory | Hybrid computing using a neural network with dynamic external memory | ||
| Muthu | Matching Networks for One Shot Learning (NIPS16) 1 | ||
| Jack | Meta-Learning with Memory-Augmented Neural Networks (ICML16) 2 | ||
| Metric | ICML07 Best Paper - Information-Theoretic Metric Learning |
[95]: metamorphic
Table of readings
read on: - 22 Jul 2017
| Presenter | Papers | Paper URL | Our Slides |
|---|---|---|---|
| GaoJi | A few useful things to know about machine learning | ||
| GaoJi | A few papers related to testing learning, e.g., Understanding Black-box Predictions via Influence Functions | ||
| GaoJi | Automated White-box Testing of Deep Learning Systems 1 | ||
| GaoJi | Testing and Validating Machine Learning Classifiers by Metamorphic Testing 2 | ||
| GaoJi | Software testing: a research travelogue (2000–2014) |
[96]: metric-learning
Table of readings
read on: - 27 Aug 2018
| Presenter | Papers | Paper URL | Our Slides |
|---|---|---|---|
| Derrick | GloVe: Global Vectors for Word Representation | ||
| Derrick | PARL.AI: A unified platform for sharing, training and evaluating dialog models across many tasks. | URL | |
| Derrick | scalable nearest neighbor algorithms for high dimensional data (PAMI14) 1 | ||
| Derrick | StarSpace: Embed All The Things! | ||
| Derrick | Weaver: Deep Co-Encoding of Questions and Documents for Machine Reading, Martin Raison, Pierre-Emmanuel Mazaré, Rajarshi Das, Antoine Bordes |
read on: - 18 Jan 2017
| Presenter | Papers | Paper URL | Our Slides |
|---|---|---|---|
| seq2seq | Sequence to Sequence Learning with Neural Networks | ||
| Set | Pointer Networks | ||
| Set | Order Matters: Sequence to Sequence for Sets | ||
| Point Attention | Multiple Object Recognition with Visual Attention | ||
| Memory | End-To-End Memory Networks | Jack Survey | |
| Memory | Neural Turing Machines | ||
| Memory | Hybrid computing using a neural network with dynamic external memory | ||
| Muthu | Matching Networks for One Shot Learning (NIPS16) 1 | ||
| Jack | Meta-Learning with Memory-Augmented Neural Networks (ICML16) 2 | ||
| Metric | ICML07 Best Paper - Information-Theoretic Metric Learning |
[97]: mimic
Table of readings
read on: - 22 Apr 2017
| Presenter | Papers | Paper URL | Our Slides |
|---|---|---|---|
| Muthu | Optimization Methods for Large-Scale Machine Learning, Léon Bottou, Frank E. Curtis, Jorge Nocedal 1 | ||
| Muthu | Fast Training of Recurrent Networks Based on EM Algorithm (1998) 2 | ||
| Muthu | FitNets: Hints for Thin Deep Nets, ICLR15 3 | ||
| Muthu | Two NIPS 2015 Deep Learning Optimization Papers | ||
| Muthu | Difference Target Propagation (2015) 4 |
[98]: mobile
Table of readings
read on: - 25 Mar 2019
| Presenter | Papers | Paper URL | Our Slides |
|---|---|---|---|
| Edge | MobileNets: Efficient Convolutional Neural Networks for Mobile Vision Applications | ||
| Edge | XNOR-Net: ImageNet Classification Using Binary Convolutional Neural Networks | URL | Ryan PDF |
| Edge | DeepX: A Software Accelerator for Low-Power Deep Learning Inference on Mobile Devices | Eamon PDF | |
| Edge | Loss-aware Binarization of Deep Networks, ICLR17 | Ryan PDF | |
| Edge | Espresso: Efficient Forward Propagation for Binary Deep Neural Networks | Eamon PDF | |
| Dynamic | Drop an Octave: Reducing Spatial Redundancy in Convolutional Neural Networks with Octave Convolution | Weilin PDF | |
| Dynamic | Dynamic Scheduling For Dynamic Control Flow in Deep Learning Systems | ||
| Dynamic | Cavs: An Efficient Runtime System for Dynamic Neural Networks |
[99]: model-as-sample
Table of readings
read on: - 10 Dec 2019
| Team INDEX | Title & Link | Tags | Our Slide |
|---|---|---|---|
| T3 | Deletion-Robust Submodular Maximization: Data Summarization with Privacy and Fairness Constraints | submodular, coreset, safety | OurSlide |
| T6 | Decision Boundary Analysis of Adversarial Examples | adversarial-examples | OurSlide |
| T8 | Robustness may be at odds with accuracy | robustness | OurSlide |
| T18 | Towards Reverse-Engineering Black-Box Neural Networks | meta, model-as-sample, safety, privacy | OurSlide |
| T23 | The Odds are Odd: A Statistical Test for Detecting Adversarial Examples | adversarial-examples | OurSlide |
| T25 | Learning how to explain neural networks: PatternNet and PatternAttribution | Attribution, Interpretable | OurSlide |
| T31 | Detecting Statistical Interactions from Neural Network Weights | Interpretable, Relational | OurSlide |
[100]: model-criticism
Table of readings
read on: - 16 Nov 2017
| Presenter | Papers | Paper URL | Our Slides |
|---|---|---|---|
| Arshdeep | Generalization and Equilibrium in Generative Adversarial Nets (ICML17) 1 | PDF + video | |
| Arshdeep | Mode Regularized Generative Adversarial Networks (ICLR17) 2 | ||
| Bargav | Improving Generative Adversarial Networks with Denoising Feature Matching, ICLR17 3 | ||
| Anant | Generative Models and Model Criticism via Optimized Maximum Mean Discrepancy, ICLR17 4 | PDF + code |
read on: - 10 Oct 2017
| Presenter | Papers | Paper URL | Our Slides |
|---|---|---|---|
| Rita | Learning Important Features Through Propagating Activation Differences, ICML17 1 | ||
| GaoJi | Examples are not Enough, Learn to Criticize! Model Criticism for Interpretable Machine Learning, NIPS16 2 | ||
| Rita | Learning Kernels with Random Features, Aman Sinha*; John Duchi, 3 |
[101]: molecule
Table of readings
read on: - 15 Mar 2019
| Presenter | Papers | Paper URL | Our Slides |
|---|---|---|---|
| Generate | Maximum-Likelihood Augmented Discrete Generative Adversarial Networks | Tkach PDF + GaoJi Pdf | |
| Generate | Graphical Generative Adversarial Networks | Arshdeep PDF | |
| Generate | GraphRNN: Generating Realistic Graphs with Deep Auto-regressive Models, ICML2018 | Arshdeep PDF | |
| Generate | Inference in probabilistic graphical models by Graph Neural Networks | Arshdeep PDF | |
| Generate | Encoding robust representation for graph generation | Arshdeep PDF | |
| Generate | Junction Tree Variational Autoencoder for Molecular Graph Generation | Tkach PDF + Arshdeep Pdf | |
| Generate | Graph Convolutional Policy Network for Goal-Directed Molecular Graph Generation NeurIPS18 | Tkach PDF | |
| Generate | Towards Variational Generation of Small Graphs | Tkach PDF + Arshdeep Pdf | |
| Generate | Convolutional Imputation of Matrix Networks | Tkach PDF | |
| Generate | Graph Convolutional Matrix Completion | Tkach PDF | |
| Generate | NetGAN: Generating Graphs via Random Walks ICML18 | [ULR] | Tkach PDF |
| Beam | Stochastic Beams and Where to Find Them: The Gumbel-Top-k Trick for Sampling Sequences Without Replacement | URL | Tkach PDF |
read on: - 15 Feb 2019
| Presenter | Papers | Paper URL | Our Slides |
|---|---|---|---|
| Bio | KDEEP: Protein–Ligand Absolute Binding Affinity Prediction via 3D-Convolutional Neural Networks, 2018 1 | Eli Pdf | |
| Bio | Molecular geometry prediction using a deep generative graph neural network | Eli Pdf | |
| Bio | Visualizing convolutional neural network protein-ligand scoring | PDF() | Eli PDF |
| Bio | Deep generative models of genetic variation capture mutation effects | PDF() | Eli PDF |
| Bio | Attentive cross-modal paratope prediction | Eli PDF |
read on: - 21 Dec 2018
| Presenter | Papers | Paper URL | Our Slides |
|---|---|---|---|
| Arshdeep | Constrained Graph Variational Autoencoders for Molecule Design | ||
| Arshdeep | Learning Deep Generative Models of Graphs | ||
| Arshdeep | Graph Convolutional Policy Network for Goal-Directed Molecular Graph Generation | ||
| Jack | Generating and designing DNA with deep generative models |
read on: - 16 Oct 2018
| Presenter | Papers | Paper URL | Our Slides |
|---|---|---|---|
| Eric | Modeling polypharmacy side effects with graph convolutional networks | ||
| Eric | Protein Interface Prediction using Graph Convolutional Networks | ||
| Eric | Structure biology meets data science: does anything change | URL | |
| Eric | DeepSite: protein-binding site predictor using 3D-convolutional neural networks | URL |
[102]: multi-label
Table of readings
read on: - 11 May 2018
| Presenter | Papers | Paper URL | Our Slides |
|---|---|---|---|
| Chao | Maximizing Subset Accuracy with Recurrent Neural Networks in Multi-label Classification | ||
| Jack | FastXML: A Fast, Accurate and Stable Tree-classifier for eXtreme Multi-label Learning | ||
| BasicMLC | Multi-Label Classification: An Overview | ||
| SPEN | Structured Prediction Energy Networks | ||
| InfNet | Learning Approximate Inference Networks for Structured Prediction | ||
| SPENMLC | Deep Value Networks | ||
| Adversarial | Semantic Segmentation using Adversarial Networks | ||
| EmbedMLC | StarSpace: Embed All The Things! | ||
| deepMLC | CNN-RNN: A Unified Framework for Multi-label Image Classification/ CVPR 2016 | ||
| deepMLC | Order-Free RNN with Visual Attention for Multi-Label Classification / AAAI 2018 |
[103]: multi-task
Table of readings
read on: - 05 Apr 2020
| Index | Papers | Our Slides |
|---|---|---|
| 1 | Invariant Risk Minimization | Zhe Survey |
| 2 | Causal Machine Learning | Zhe Survey |
| 3 | A Meta-Transfer Objective for Learning to Disentangle Causal Mechanisms | Zhe Survey |
| 3 | Review on Optimization-Based Meta Learning | Zhe Survey |
| 4 | Domain adaptation and counterfactual prediction | Zhe Survey |
| 5 | Gaussian Processes | Zhe Survey |
| 6 | A Framework for Learning Predictive Structures from Multiple Tasks and Unlabeled Data | Zhe Survey |
| 7 | Few-shot domain adaptation by causal mechanism transfer | Zhe Survey |
read on: - 21 Nov 2017
| Presenter | Papers | Paper URL | Our Slides |
|---|---|---|---|
| Jack | Hasselt - Deep Reinforcement Learning | RLSS17.pdf + video | |
| Tianlu | Roux - RL in the Industry | RLSS17.pdf + video | PDF / PDF-Bandit |
| Xueying | Singh - Steps Towards Continual Learning | pdf + video | |
| GaoJi | Distral: Robust Multitask Reinforcement Learning 1 |
Table of readings
read on: - 07 Dec 2019
| Team INDEX | Title & Link | Tags | Our Slide |
|---|---|---|---|
| T11 | Parameter-Efficient Transfer Learning for NLP | meta, BERT, text, Transfer | OurSlide |
| T22 | Deep Asymmetric Multi-task Feature Learning | meta, regularization, Multi-task | OurSlide |
[104]: mutual-information
Table of readings
read on: - 05 May 2020
| Index | Papers | Our Slides |
|---|---|---|
| 1 | Review on Semi-Supervised Learning | Zhe Survey |
| 2 | Review on Generative Adversarial Networks | Zhe Survey |
| 3 | Information theory in deep learning | Zhe Survey |
| 4 | Lagrange Optimization | Zhe Survey |
| 5 | Deep Learning and Information Theory, and Graph Neural Network | Derrick Survey |
| 6 | Loss Functions for Deep Structured Models | Jack Survey |
| 7 | Group Sparsity and Optimization | Zhe Survey |
[105]: neural-programming
Table of readings
read on: - 17 Oct 2017
| Presenter | Papers | Paper URL | Our Slides |
|---|---|---|---|
| Jack | Learning to Query, Reason, and Answer Questions On Ambiguous Texts, ICLR17 1 | ||
| Arshdeep | Making Neural Programming Architectures Generalize via Recursion, ICLR17 2 | ||
| Xueying | Towards Deep Interpretability (MUS-ROVER II): Learning Hierarchical Representations of Tonal Music, ICLR17 3 |
[106]: neuroscience
Table of readings
[107]: nlp
Table of readings
read on: - 29 Mar 2019
| Presenter | Papers | Paper URL | Our Slides |
|---|---|---|---|
| QA | A Comparison of Current Graph Database Models | Pdf + PDF2 | Bill PDF |
| QA | Open Domain Question Answering Using Early Fusion of Knowledge Bases and Text | Bill [PDF + GaoJi Pdf | |
| QA | Generative Question Answering: Learning to Answer the Whole Question, Mike Lewis, Angela Fan | Bill PDF + GaoJi Pdf | |
| QA | Learning to Reason Science Exam Questions with Contextual Knowledge Graph Embeddings / Knowledge Graph Embedding via Dynamic Mapping Matrix | PDF + Pdf | Bill PDF + GaoJi Pdf |
| Text | Adversarial Text Generation via Feature-Mover’s Distance | URL | Faizan PDF |
| Text | Content preserving text generation with attribute controls | URL | Faizan PDF |
| Text | Multiple-Attribute Text Rewriting, ICLR, 2019, | URL | Faizan PDF |
| Text | Writeprints: a stylometric approach to identity level identification and similarity detection in cyberSpace | URL | Faizan PDF |
read on: - 22 Mar 2019
| Presenter | Papers | Paper URL | Our Slides |
|---|---|---|---|
| Scalable | FastGCN: Fast Learning with Graph Convolutional Networks via Importance Sampling | Ryan PDF + Arshdeep Pdf | |
| Scalable | MILE: A Multi-Level Framework for Scalable Graph Embedding | Ryan PDF | |
| Scalable | LanczosNet: Multi-Scale Deep Graph Convolutional Networks | Ryan PDF | |
| Scalable | Demystifying Parallel and Distributed Deep Learning: An In-Depth Concurrency Analysis | Derrick PDF | |
| Scalable | Towards Federated learning at Scale: System Design | URL | Derrick PDF |
| Scalable | DNN Dataflow Choice Is Overrated | Derrick PDF | |
| Scalable | Towards Efficient Large-Scale Graph Neural Network Computing | Derrick PDF | |
| Scalable | PyTorch Geometric | URL | |
| Scalable | PyTorch BigGraph | URL | |
| Scalable | Simplifying Graph Convolutional Networks | ||
| Scalable | Cluster-GCN: An Efficient Algorithm for Training Deep and Large Graph Convolutional Networks |
read on: - 15 Mar 2019
| Presenter | Papers | Paper URL | Our Slides |
|---|---|---|---|
| Generate | Maximum-Likelihood Augmented Discrete Generative Adversarial Networks | Tkach PDF + GaoJi Pdf | |
| Generate | Graphical Generative Adversarial Networks | Arshdeep PDF | |
| Generate | GraphRNN: Generating Realistic Graphs with Deep Auto-regressive Models, ICML2018 | Arshdeep PDF | |
| Generate | Inference in probabilistic graphical models by Graph Neural Networks | Arshdeep PDF | |
| Generate | Encoding robust representation for graph generation | Arshdeep PDF | |
| Generate | Junction Tree Variational Autoencoder for Molecular Graph Generation | Tkach PDF + Arshdeep Pdf | |
| Generate | Graph Convolutional Policy Network for Goal-Directed Molecular Graph Generation NeurIPS18 | Tkach PDF | |
| Generate | Towards Variational Generation of Small Graphs | Tkach PDF + Arshdeep Pdf | |
| Generate | Convolutional Imputation of Matrix Networks | Tkach PDF | |
| Generate | Graph Convolutional Matrix Completion | Tkach PDF | |
| Generate | NetGAN: Generating Graphs via Random Walks ICML18 | [ULR] | Tkach PDF |
| Beam | Stochastic Beams and Where to Find Them: The Gumbel-Top-k Trick for Sampling Sequences Without Replacement | URL | Tkach PDF |
read on: - 02 Dec 2018
| Presenter | Papers | Paper URL | Our Slides |
|---|---|---|---|
| Jennifer | Adversarial Attacks Against Medical Deep Learning Systems | ||
| Jennifer | Adversarial-Playground: A Visualization Suite Showing How Adversarial Examples Fool Deep Learning | ||
| Jennifer | Black-box Generation of Adversarial Text Sequences to Evade Deep Learning Classifiers | ||
| Jennifer | CleverHans | ||
| Ji | Ji-f18-New papers about adversarial attack |
read on: - 10 Jan 2018
| Presenter | Papers | Paper URL | Our Slides |
|---|---|---|---|
| Bill | Google’s Neural Machine Translation System: Bridging the Gap between Human and Machine Translation 1 | ||
| Bill | Measuring the tendency of CNNs to Learn Surface Statistical Regularities Jason Jo, Yoshua Bengio | ||
| Bill | Generating Sentences by Editing Prototypes, Kelvin Guu, Tatsunori B. Hashimoto, Yonatan Oren, Percy Liang 2 | ||
| Bill | On the importance of single directions for generalization, Ari S. Morcos, David G.T. Barrett, Neil C. Rabinowitz, Matthew Botvinick |
read on: - 10 Jan 2018
| Presenter | Papers | Paper URL | Our Slides |
|---|---|---|---|
| Bill | Google’s Neural Machine Translation System: Bridging the Gap between Human and Machine Translation 1 | ||
| Bill | Measuring the tendency of CNNs to Learn Surface Statistical Regularities Jason Jo, Yoshua Bengio | ||
| Bill | Generating Sentences by Editing Prototypes, Kelvin Guu, Tatsunori B. Hashimoto, Yonatan Oren, Percy Liang 2 | ||
| Bill | On the importance of single directions for generalization, Ari S. Morcos, David G.T. Barrett, Neil C. Rabinowitz, Matthew Botvinick |
read on: - 12 Jan 2017
| Presenter | Papers | Paper URL | Our Slides |
|---|---|---|---|
| NLP | A Neural Probabilistic Language Model | ||
| Text | Bag of Tricks for Efficient Text Classification | ||
| Text | Character-level Convolutional Networks for Text Classification | ||
| NLP | BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding | ||
| seq2seq | Neural Machine Translation by Jointly Learning to Align and Translate | ||
| NLP | Natural Language Processing (almost) from Scratch | ||
| Train | Curriculum learning | ||
| Muthu | NeuroIPS Embedding Papers survey 2012 to 2015 | NIPS | |
| Basics | Efficient BackProp |
[108]: noise
Table of readings
read on: - 05 Apr 2019
| Presenter | Papers | Paper URL | Our Slides |
|---|---|---|---|
| Understand | Faithful and Customizable Explanations of Black Box Models | Derrick PDF | |
| Understand | A causal framework for explaining the predictions of black-box sequence-to-sequence models, EMNLP17 | GaoJi PDF + Bill Pdf | |
| Understand | How Powerful are Graph Neural Networks? / Deeper Insights into Graph Convolutional Networks for Semi-Supervised Learning | Pdf + Pdf | GaoJi PDF |
| Understand | Interpretable Graph Convolutional Neural Networks for Inference on Noisy Knowledge Graphs + GNN Explainer: A Tool for Post-hoc Explanation of Graph Neural Networks | Pdf + PDF | GaoJi PDF |
| Understand | Attention is not Explanation, 2019 | ||
| Understand | Understanding attention in graph neural networks, 2019 |
read on: - 26 Oct 2017
| Presenter | Papers | Paper URL | Our Slides |
|---|---|---|---|
| Tianlu | Robustness of classifiers: from adversarial to random noise, NIPS16 | PDF 1 | |
| Anant | Blind Attacks on Machine Learners, 2 NIPS16 | ||
| Data Noising as Smoothing in Neural Network Language Models (Ng), ICLR17 3 | |||
| The Robustness of Estimator Composition, NIPS16 4 |
read on: - 17 Oct 2017
| Presenter | Papers | Paper URL | Our Slides |
|---|---|---|---|
| Jack | Learning to Query, Reason, and Answer Questions On Ambiguous Texts, ICLR17 1 | ||
| Arshdeep | Making Neural Programming Architectures Generalize via Recursion, ICLR17 2 | ||
| Xueying | Towards Deep Interpretability (MUS-ROVER II): Learning Hierarchical Representations of Tonal Music, ICLR17 3 |
[109]: nonparametric
Table of readings
read on: - 21 Sep 2017
| Presenter | Papers | Paper URL | Our Slides |
|---|---|---|---|
| Shijia | Outrageously Large Neural Networks: The Sparsely-Gated Mixture-of-Experts Layer, (Dean), ICLR17 1 | ||
| Ceyer | Sequence Modeling via Segmentations, ICML17 2 | ||
| Arshdeep | Input Switched Affine Networks: An RNN Architecture Designed for Interpretability, ICML17 3 |
read on: - 19 Sep 2017
| Presenter | Papers | Paper URL | Our Slides |
|---|---|---|---|
| Jack | Learning End-to-End Goal-Oriented Dialog, ICLR17 1 | ||
| Bargav | Nonparametric Neural Networks, ICLR17 2 | ||
| Bargav | Learning Structured Sparsity in Deep Neural Networks, NIPS16 3 | ||
| Arshdeep | Learning the Number of Neurons in Deep Networks, NIPS16 4 |
[110]: normalization
Table of readings
read on: - 12 Dec 2019
| Team INDEX | Title & Link | Tags | Our Slide |
|---|---|---|---|
| T2 | Empirical Study of Example Forgetting During Deep Neural Network Learning | Sample Selection, forgetting | OurSlide |
| T29 | Select Via Proxy: Efficient Data Selection For Training Deep Networks | Sample Selection | OurSlide |
| T9 | How SGD Selects the Global Minima in over-parameterized Learning | optimization | OurSlide |
| T10 | Escaping Saddles with Stochastic Gradients | optimization | OurSlide |
| T13 | To What Extent Do Different Neural Networks Learn the Same Representation | subspace | OurSlide |
| T19 | On the Information Bottleneck Theory of Deep Learning | informax | OurSlide |
| T20 | Visualizing the Loss Landscape of Neural Nets | normalization | OurSlide |
| T21 | Using Pre-Training Can Improve Model Robustness and Uncertainty | training, analysis | OurSlide |
| T24 | Norm matters: efficient and accurate normalization schemes in deep networks | normalization | OurSlide |
[111]: ntm
Table of readings
read on: - 18 Jan 2017
| Presenter | Papers | Paper URL | Our Slides |
|---|---|---|---|
| seq2seq | Sequence to Sequence Learning with Neural Networks | ||
| Set | Pointer Networks | ||
| Set | Order Matters: Sequence to Sequence for Sets | ||
| Point Attention | Multiple Object Recognition with Visual Attention | ||
| Memory | End-To-End Memory Networks | Jack Survey | |
| Memory | Neural Turing Machines | ||
| Memory | Hybrid computing using a neural network with dynamic external memory | ||
| Muthu | Matching Networks for One Shot Learning (NIPS16) 1 | ||
| Jack | Meta-Learning with Memory-Augmented Neural Networks (ICML16) 2 | ||
| Metric | ICML07 Best Paper - Information-Theoretic Metric Learning |
[112]: optimization
Table of readings
read on: - 09 Nov 2017
| Presenter | Papers | Paper URL | Our Slides |
|---|---|---|---|
| Shijia | Professor Forcing: A New Algorithm for Training Recurrent Networks, 1 NIPS16 | PDF + Video | |
| Beilun+Arshdeep | Mollifying Networks, Bengio, ICLR17 2 | PDF / PDF2 |
read on: - 07 Nov 2017
| Presenter | Papers | Paper URL | Our Slides |
|---|---|---|---|
| GaoJi | Forward and Reverse Gradient-Based Hyperparameter Optimization, ICML17 1 | ||
| Chaojiang | Adaptive Neural Networks for Efficient Inference, ICML17 2 | ||
| Bargav | Practical Gauss-Newton Optimisation for Deep Learning, ICML17 3 | ||
| Rita | How to Escape Saddle Points Efficiently, ICML17 4 | ||
| Batched High-dimensional Bayesian Optimization via Structural Kernel Learning |
read on: - 02 Nov 2017
| Presenter | Papers | Paper URL | Our Slides |
|---|---|---|---|
| GaoJi | Neural Architecture Search with Reinforcement Learning, ICLR17 1 | ||
| Ceyer | Learning to learn 2 | DLSS17video | |
| Beilun | Optimization as a Model for Few-Shot Learning, ICLR17 3 | PDF + More | |
| Anant | Neural Optimizer Search with Reinforcement Learning, ICML17 4 |
Table of readings
read on: - 05 May 2020
| Index | Papers | Our Slides |
|---|---|---|
| 1 | Review on Semi-Supervised Learning | Zhe Survey |
| 2 | Review on Generative Adversarial Networks | Zhe Survey |
| 3 | Information theory in deep learning | Zhe Survey |
| 4 | Lagrange Optimization | Zhe Survey |
| 5 | Deep Learning and Information Theory, and Graph Neural Network | Derrick Survey |
| 6 | Loss Functions for Deep Structured Models | Jack Survey |
| 7 | Group Sparsity and Optimization | Zhe Survey |
read on: - 12 Dec 2019
| Team INDEX | Title & Link | Tags | Our Slide |
|---|---|---|---|
| T2 | Empirical Study of Example Forgetting During Deep Neural Network Learning | Sample Selection, forgetting | OurSlide |
| T29 | Select Via Proxy: Efficient Data Selection For Training Deep Networks | Sample Selection | OurSlide |
| T9 | How SGD Selects the Global Minima in over-parameterized Learning | optimization | OurSlide |
| T10 | Escaping Saddles with Stochastic Gradients | optimization | OurSlide |
| T13 | To What Extent Do Different Neural Networks Learn the Same Representation | subspace | OurSlide |
| T19 | On the Information Bottleneck Theory of Deep Learning | informax | OurSlide |
| T20 | Visualizing the Loss Landscape of Neural Nets | normalization | OurSlide |
| T21 | Using Pre-Training Can Improve Model Robustness and Uncertainty | training, analysis | OurSlide |
| T24 | Norm matters: efficient and accurate normalization schemes in deep networks | normalization | OurSlide |
read on: - 31 Oct 2017
| Presenter | Papers | Paper URL | Our Slides |
|---|---|---|---|
| Ceyer | An overview of gradient optimization algorithms, 1 | ||
| Shijia | Osborne - Probabilistic numerics for deep learning 2 | DLSS 2017 + Video | PDF / PDF2 |
| Jack | Automated Curriculum Learning for Neural Networks, ICML17 3 | ||
| DLSS17 | Johnson - Automatic Differentiation 4 | slide + video |
read on: - 22 Jun 2017
| Presenter | Papers | Paper URL | Our Slides |
|---|---|---|---|
| Arshdeep | Image Question Answering using Convolutional Neural Network with Dynamic Parameter Prediction 1 | ||
| Arshdeep | Decoupled Neural Interfaces Using Synthetic Gradients 2 | ||
| Arshdeep | Diet Networks: Thin Parameters for Fat Genomics 3 | ||
| Arshdeep | Metric Learning with Adaptive Density Discrimination 4 |
read on: - 02 Jun 2017
| Presenter | Papers | Paper URL | Our Slides |
|---|---|---|---|
| Arshdeep | HyperNetworks, David Ha, Andrew Dai, Quoc V. Le ICLR 2017 1 | ||
| Arshdeep | Learning feed-forward one-shot learners 2 | ||
| Arshdeep | Learning to Learn by gradient descent by gradient descent 3 | ||
| Arshdeep | Dynamic Filter Networks 4 https://arxiv.org/abs/1605.09673 |
read on: - 22 Apr 2017
| Presenter | Papers | Paper URL | Our Slides |
|---|---|---|---|
| Muthu | Optimization Methods for Large-Scale Machine Learning, Léon Bottou, Frank E. Curtis, Jorge Nocedal 1 | ||
| Muthu | Fast Training of Recurrent Networks Based on EM Algorithm (1998) 2 | ||
| Muthu | FitNets: Hints for Thin Deep Nets, ICLR15 3 | ||
| Muthu | Two NIPS 2015 Deep Learning Optimization Papers | ||
| Muthu | Difference Target Propagation (2015) 4 |
[113]: parallel
Table of readings
read on: - 22 Mar 2019
| Presenter | Papers | Paper URL | Our Slides |
|---|---|---|---|
| Scalable | FastGCN: Fast Learning with Graph Convolutional Networks via Importance Sampling | Ryan PDF + Arshdeep Pdf | |
| Scalable | MILE: A Multi-Level Framework for Scalable Graph Embedding | Ryan PDF | |
| Scalable | LanczosNet: Multi-Scale Deep Graph Convolutional Networks | Ryan PDF | |
| Scalable | Demystifying Parallel and Distributed Deep Learning: An In-Depth Concurrency Analysis | Derrick PDF | |
| Scalable | Towards Federated learning at Scale: System Design | URL | Derrick PDF |
| Scalable | DNN Dataflow Choice Is Overrated | Derrick PDF | |
| Scalable | Towards Efficient Large-Scale Graph Neural Network Computing | Derrick PDF | |
| Scalable | PyTorch Geometric | URL | |
| Scalable | PyTorch BigGraph | URL | |
| Scalable | Simplifying Graph Convolutional Networks | ||
| Scalable | Cluster-GCN: An Efficient Algorithm for Training Deep and Large Graph Convolutional Networks |
read on: - 20 Jan 2017
| Presenter | Papers | Paper URL | Our Slides |
|---|---|---|---|
| scalable | Sanjiv Kumar (Columbia EECS 6898), Lecture: Introduction to large-scale machine learning 2010 [^1] | ||
| data scalable | Alex Smola - Berkeley SML: Scalable Machine Learning: Syllabus 2012 [^2] | PDF 2014 + PDF | |
| Binary | Binarized Neural Networks: Training Deep Neural Networks with Weights and Activations Constrained to +1 or -1 | ||
| Model | Binary embeddings with structured hashed projections 1 | ||
| Model | Deep Compression: Compressing Deep Neural Networks (ICLR 2016) 2 |
[114]: parsimonious
Table of readings
[115]: planning
Table of readings
read on: - 28 Nov 2017
| Presenter | Papers | Paper URL | Our Slides |
|---|---|---|---|
| Anant | The Predictron: End-to-End Learning and Planning, ICLR17 1 | ||
| ChaoJiang | Szepesvari - Theory of RL 2 | RLSS.pdf + Video | |
| GaoJi | Mastering the game of Go without human knowledge / Nature 2017 3 | ||
| Thomas - Safe Reinforcement Learning | RLSS17.pdf + video | ||
| Sutton - Temporal-Difference Learning | RLSS17.pdf + Video |
[116]: pointer
Table of readings
read on: - 18 Jan 2017
| Presenter | Papers | Paper URL | Our Slides |
|---|---|---|---|
| seq2seq | Sequence to Sequence Learning with Neural Networks | ||
| Set | Pointer Networks | ||
| Set | Order Matters: Sequence to Sequence for Sets | ||
| Point Attention | Multiple Object Recognition with Visual Attention | ||
| Memory | End-To-End Memory Networks | Jack Survey | |
| Memory | Neural Turing Machines | ||
| Memory | Hybrid computing using a neural network with dynamic external memory | ||
| Muthu | Matching Networks for One Shot Learning (NIPS16) 1 | ||
| Jack | Meta-Learning with Memory-Augmented Neural Networks (ICML16) 2 | ||
| Metric | ICML07 Best Paper - Information-Theoretic Metric Learning |
[117]: privacy
Table of readings
read on: - 12 Oct 2017
| Presenter | Papers | Paper URL | Our Slides |
|---|---|---|---|
| Xueying | Semi-supervised Knowledge Transfer for Deep Learning from Private Training Data, ICLR17 1 | ||
| Bargav | Deep Learning with Differential Privacy, CCS16 2 | PDF + video | |
| Bargav | Privacy-Preserving Deep Learning, CCS15 3 | ||
| Xueying | Domain Separation Networks, NIPS16 4 |
read on: - 22 Feb 2017
| Presenter | Papers | Paper URL | Our Slides |
|---|---|---|---|
| Tobin | Summary of A few Papers on: Machine Learning and Cryptography, (e.g., learning to Protect Communications with Adversarial Neural Cryptography) 1 | ||
| Tobin | Privacy Aware Learning (NIPS12) 2 | ||
| Tobin | Can Machine Learning be Secure?(2006) |
Table of readings
read on: - 10 Dec 2019
| Team INDEX | Title & Link | Tags | Our Slide |
|---|---|---|---|
| T3 | Deletion-Robust Submodular Maximization: Data Summarization with Privacy and Fairness Constraints | submodular, coreset, safety | OurSlide |
| T6 | Decision Boundary Analysis of Adversarial Examples | adversarial-examples | OurSlide |
| T8 | Robustness may be at odds with accuracy | robustness | OurSlide |
| T18 | Towards Reverse-Engineering Black-Box Neural Networks | meta, model-as-sample, safety, privacy | OurSlide |
| T23 | The Odds are Odd: A Statistical Test for Detecting Adversarial Examples | adversarial-examples | OurSlide |
| T25 | Learning how to explain neural networks: PatternNet and PatternAttribution | Attribution, Interpretable | OurSlide |
| T31 | Detecting Statistical Interactions from Neural Network Weights | Interpretable, Relational | OurSlide |
[118]: program
Table of readings
read on: - 17 Feb 2019
| Presenter | Papers | Paper URL | Our Slides |
|---|---|---|---|
| Program | Neural network-based graph embedding for cross-platform binary code similarity detection | Pdf + Pdf | Faizan PDF + GaoJi Pdf |
| Program | Deep Program Reidentification: A Graph Neural Network Solution | Weilin PDF | |
| Program | Heterogeneous Graph Neural Networks for Malicious Account Detection | Weilin Pdf | |
| Program | Learning to represent programs with graphs | Pdf 1 |
read on: - 23 Aug 2018
| Presenter | Papers | Paper URL | Our Slides |
|---|---|---|---|
| Arshdeep | The Concrete Distribution: A Continuous Relaxation of Discrete Random Variables, Chris J. Maddison, Andriy Mnih, Yee Whye Teh 1 | ||
| GaoJi | Summary Of Several Autoencoder models | ||
| GaoJi | Latent Constraints: Learning to Generate Conditionally from Unconditional Generative Models, Jesse Engel, Matthew Hoffman, Adam Roberts 2 | ||
| GaoJi | Summary of A Few Recent Papers about Discrete Generative models, SeqGAN, MaskGAN, BEGAN, BoundaryGAN | ||
| Arshdeep | Semi-Amortized Variational Autoencoders, Yoon Kim, Sam Wiseman, Andrew C. Miller, David Sontag, Alexander M. Rush 3 | ||
| Arshdeep | Synthesizing Programs for Images using Reinforced Adversarial Learning, Yaroslav Ganin, Tejas Kulkarni, Igor Babuschkin, S.M. Ali Eslami, Oriol Vinyals 4 |
[119]: propagation
Table of readings
read on: - 22 Apr 2017
| Presenter | Papers | Paper URL | Our Slides |
|---|---|---|---|
| Muthu | Optimization Methods for Large-Scale Machine Learning, Léon Bottou, Frank E. Curtis, Jorge Nocedal 1 | ||
| Muthu | Fast Training of Recurrent Networks Based on EM Algorithm (1998) 2 | ||
| Muthu | FitNets: Hints for Thin Deep Nets, ICLR15 3 | ||
| Muthu | Two NIPS 2015 Deep Learning Optimization Papers | ||
| Muthu | Difference Target Propagation (2015) 4 |
[120]: protein
Table of readings
read on: - 01 Sep 2022
| Papers | Paper URL | Abstract |
|---|---|---|
| Evolutionary-scale prediction of atomic level protein structure with a language model | URL | “show that direct inference of structure from primary sequence using a large language model enables an order of magnitude speed-up in high resolution structure prediction. Leveraging the insight that language models learn evolutionary patterns across millions of sequences, we train models up to 15B parameters,…” |
| DiffDock: Diffusion Steps, Twists, and Turns for Molecular Docking | URL | “Recent deep learning methods that treat docking as a regression problem have decreased runtime compared to traditional search-based methods but have yet to offer substantial improvements in accuracy. We instead frame molecular docking as a generative modeling problem and develop DiffDock, a diffusion generative model over the non-Euclidean manifold of ligand poses. To do so, we map this manifold to the product space of the degrees of freedom (translational, rotational, and torsional) involved in docking and develop an efficient diffusion process on this space.” |
read on: - 05 Jun 2020
| Index | Papers | Our Slides |
|---|---|---|
| 1 | Protein 3D Structure Computed from Evolutionary Sequence Variation | Arsh Survey |
| 3 | Regulatory network inference on developmental and evolutionary lineages | Arsh Survey |
| 4 | Deep learning in ultrasound image analysis | Zhe Survey |
| 5 | Predicting the sequence specificities of DNA- and RNA-binding proteins by deep learning (DeepBind) | Jack Survey |
| 6 | Canonical and single-cell Hi-C reveal distinct chromatin interaction sub-networks of mammalian transcription factors | Jack Survey |
| 7 | BindSpace decodes transcription factor binding signals by large-scale sequence embedding | Jack Survey |
| 8 | FastXML: A Fast, Accurate and Stable Tree-classifier for eXtreme Multi-label Learning | Jack Survey |
| 9 | Query-Reduction Networks for Question Answering | Bill Survey |
Table of readings
read on: - 15 Feb 2019
| Presenter | Papers | Paper URL | Our Slides |
|---|---|---|---|
| Bio | KDEEP: Protein–Ligand Absolute Binding Affinity Prediction via 3D-Convolutional Neural Networks, 2018 1 | Eli Pdf | |
| Bio | Molecular geometry prediction using a deep generative graph neural network | Eli Pdf | |
| Bio | Visualizing convolutional neural network protein-ligand scoring | PDF() | Eli PDF |
| Bio | Deep generative models of genetic variation capture mutation effects | PDF() | Eli PDF |
| Bio | Attentive cross-modal paratope prediction | Eli PDF |
read on: - 16 Oct 2018
| Presenter | Papers | Paper URL | Our Slides |
|---|---|---|---|
| Eric | Modeling polypharmacy side effects with graph convolutional networks | ||
| Eric | Protein Interface Prediction using Graph Convolutional Networks | ||
| Eric | Structure biology meets data science: does anything change | URL | |
| Eric | DeepSite: protein-binding site predictor using 3D-convolutional neural networks | URL |
read on: - 13 Oct 2018
| Presenter | Papers | Paper URL | Our Slides |
|---|---|---|---|
| Arshdeep | deepCRISPR: optimized CRISPR guide RNA design by deep learning , Genome Biology 2018 | ||
| Arshdeep | The CRISPR tool kit for genome editing and beyond, Mazhar Adli | ||
| Eric | Intro of Genetic Engineering | ||
| Eric | Prediction of off-target activities for the end-to-end design of CRISPR guide RNAs | ||
| Brandon | Generative Modeling for Protein Structure | URL |
read on: - 21 Jan 2017
| Presenter | Papers | Paper URL | Our Slides |
|---|---|---|---|
| DeepBind | Predicting the sequence specificities of DNA- and RNA-binding proteins by deep learning | ||
| DeepSEA | Deep learning sequence-based ab initio prediction of variant effects on expression and disease risk | ||
| DeepSEA | Deep Supervised and Convolutional Generative Stochastic Network for Protein Secondary Structure Prediction, ICML 2014 | ||
| BioBasics | A method for integrating and ranking the evidence for biochemical pathways by mining reactions from text, Bioinformatics13 | ||
| BioBasics | Efficient counting of k-mers in DNA sequences using a Bloom filter. Melsted P, Pritchard JK. BMC Bioinformatics. 2011 | ||
| BioBasics | Fast String Kernels using Inexact Matching for Protein Sequence, JMLR 2004 | ||
| BioBasics | NIPS09: Locality-Sensitive Binary Codes from Shift-Invariant Kernels | ||
| MedSignal | Segmenting Time Series: A Survey and Novel Approach, |
[121]: pruning
Table of readings
read on: - 20 Jan 2017
| Presenter | Papers | Paper URL | Our Slides |
|---|---|---|---|
| scalable | Sanjiv Kumar (Columbia EECS 6898), Lecture: Introduction to large-scale machine learning 2010 [^1] | ||
| data scalable | Alex Smola - Berkeley SML: Scalable Machine Learning: Syllabus 2012 [^2] | PDF 2014 + PDF | |
| Binary | Binarized Neural Networks: Training Deep Neural Networks with Weights and Activations Constrained to +1 or -1 | ||
| Model | Binary embeddings with structured hashed projections 1 | ||
| Model | Deep Compression: Compressing Deep Neural Networks (ICLR 2016) 2 |
[122]: qa
Table of readings
read on: - 29 Mar 2019
| Presenter | Papers | Paper URL | Our Slides |
|---|---|---|---|
| QA | A Comparison of Current Graph Database Models | Pdf + PDF2 | Bill PDF |
| QA | Open Domain Question Answering Using Early Fusion of Knowledge Bases and Text | Bill [PDF + GaoJi Pdf | |
| QA | Generative Question Answering: Learning to Answer the Whole Question, Mike Lewis, Angela Fan | Bill PDF + GaoJi Pdf | |
| QA | Learning to Reason Science Exam Questions with Contextual Knowledge Graph Embeddings / Knowledge Graph Embedding via Dynamic Mapping Matrix | PDF + Pdf | Bill PDF + GaoJi Pdf |
| Text | Adversarial Text Generation via Feature-Mover’s Distance | URL | Faizan PDF |
| Text | Content preserving text generation with attribute controls | URL | Faizan PDF |
| Text | Multiple-Attribute Text Rewriting, ICLR, 2019, | URL | Faizan PDF |
| Text | Writeprints: a stylometric approach to identity level identification and similarity detection in cyberSpace | URL | Faizan PDF |
read on: - 20 Dec 2018
| Presenter | Papers | Paper URL | Our Slides |
|---|---|---|---|
| Bill | Seq2SQL: Generating Structured Queries from Natural Language using Reinforcement Learning | ||
| Chao | Deep EHR: A Survey of Recent Advances in Deep Learning Techniques for Electronic Health Record (EHR) Analysis (I) | ||
| Chao | Deep EHR: A Survey of Recent Advances in Deep Learning Techniques for Electronic Health Record (EHR) Analysis (II) | ||
| Derrick | Deep EHR: A Survey of Recent Advances in Deep Learning Techniques for Electronic Health Record (EHR) Analysis (III) | ||
| Chao | Reading Wikipedia to Answer Open-Domain Questions | ||
| Jennifer | Open Domain Question Answering Using Early Fusion of Knowledge Bases and Text |
read on: - 27 Aug 2018
| Presenter | Papers | Paper URL | Our Slides |
|---|---|---|---|
| Derrick | GloVe: Global Vectors for Word Representation | ||
| Derrick | PARL.AI: A unified platform for sharing, training and evaluating dialog models across many tasks. | URL | |
| Derrick | scalable nearest neighbor algorithms for high dimensional data (PAMI14) 1 | ||
| Derrick | StarSpace: Embed All The Things! | ||
| Derrick | Weaver: Deep Co-Encoding of Questions and Documents for Machine Reading, Martin Raison, Pierre-Emmanuel Mazaré, Rajarshi Das, Antoine Bordes |
read on: - 17 Oct 2017
| Presenter | Papers | Paper URL | Our Slides |
|---|---|---|---|
| Jack | Learning to Query, Reason, and Answer Questions On Ambiguous Texts, ICLR17 1 | ||
| Arshdeep | Making Neural Programming Architectures Generalize via Recursion, ICLR17 2 | ||
| Xueying | Towards Deep Interpretability (MUS-ROVER II): Learning Hierarchical Representations of Tonal Music, ICLR17 3 |
read on: - 03 Oct 2017
| Presenter | Papers | Paper URL | Our Slides |
|---|---|---|---|
| Tianlu | Ask Me Anything: Dynamic Memory Networks for Natural Language Processing, ICML17 1 | PDF + code | |
| Jack | Reasoning with Memory Augmented Neural Networks for Language Comprehension, ICLR17 2 | ||
| Xueying | State-Frequency Memory Recurrent Neural Networks, ICML17 3 |
read on: - 26 Sep 2017
| Presenter | Papers | Paper URL | Our Slides |
|---|---|---|---|
| Rita | Paying More Attention to Attention: Improving the Performance of Convolutional Neural Networks via Attention Transfer, ICLR17 1 | ||
| Tianlu | Dynamic Coattention Networks For Question Answering, ICLR17 2 | PDF + code | |
| ChaoJiang | Structured Attention Networks, ICLR17 3 | PDF + code |
read on: - 21 Sep 2017
| Presenter | Papers | Paper URL | Our Slides |
|---|---|---|---|
| Shijia | Outrageously Large Neural Networks: The Sparsely-Gated Mixture-of-Experts Layer, (Dean), ICLR17 1 | ||
| Ceyer | Sequence Modeling via Segmentations, ICML17 2 | ||
| Arshdeep | Input Switched Affine Networks: An RNN Architecture Designed for Interpretability, ICML17 3 |
read on: - 19 Sep 2017
| Presenter | Papers | Paper URL | Our Slides |
|---|---|---|---|
| Jack | Learning End-to-End Goal-Oriented Dialog, ICLR17 1 | ||
| Bargav | Nonparametric Neural Networks, ICLR17 2 | ||
| Bargav | Learning Structured Sparsity in Deep Neural Networks, NIPS16 3 | ||
| Arshdeep | Learning the Number of Neurons in Deep Networks, NIPS16 4 |
read on: - 12 Jan 2017
| Presenter | Papers | Paper URL | Our Slides |
|---|---|---|---|
| QA | Learning to rank with (a lot of) word features | ||
| Relation | A semantic matching energy function for learning with multi-relational data | ||
| Relation | Translating embeddings for modeling multi-relational data | ||
| QA | Reading wikipedia to answer open-domain questions | ||
| QA | Question answering with subgraph embeddings |
[123]: quantization
Table of readings
read on: - 06 Dec 2019
| Team INDEX | Title & Link | Tags | Our Slide |
|---|---|---|---|
| T33 | The High-Dimensional Geometry of Binary Neural Networks | Quantization, binarization, scalable | OurSlide |
| T34 | Modern Neural Networks Generalize on Small Data Sets | small-data, analysis, ensemble | OurSlide |
| T4 | Cognitive Scheduler for Heterogeneous High Performance Computing System | system-application | OurSlide |
[124]: random
Table of readings
read on: - 15 Mar 2019
| Presenter | Papers | Paper URL | Our Slides |
|---|---|---|---|
| Generate | Maximum-Likelihood Augmented Discrete Generative Adversarial Networks | Tkach PDF + GaoJi Pdf | |
| Generate | Graphical Generative Adversarial Networks | Arshdeep PDF | |
| Generate | GraphRNN: Generating Realistic Graphs with Deep Auto-regressive Models, ICML2018 | Arshdeep PDF | |
| Generate | Inference in probabilistic graphical models by Graph Neural Networks | Arshdeep PDF | |
| Generate | Encoding robust representation for graph generation | Arshdeep PDF | |
| Generate | Junction Tree Variational Autoencoder for Molecular Graph Generation | Tkach PDF + Arshdeep Pdf | |
| Generate | Graph Convolutional Policy Network for Goal-Directed Molecular Graph Generation NeurIPS18 | Tkach PDF | |
| Generate | Towards Variational Generation of Small Graphs | Tkach PDF + Arshdeep Pdf | |
| Generate | Convolutional Imputation of Matrix Networks | Tkach PDF | |
| Generate | Graph Convolutional Matrix Completion | Tkach PDF | |
| Generate | NetGAN: Generating Graphs via Random Walks ICML18 | [ULR] | Tkach PDF |
| Beam | Stochastic Beams and Where to Find Them: The Gumbel-Top-k Trick for Sampling Sequences Without Replacement | URL | Tkach PDF |
read on: - 10 Oct 2017
| Presenter | Papers | Paper URL | Our Slides |
|---|---|---|---|
| Rita | Learning Important Features Through Propagating Activation Differences, ICML17 1 | ||
| GaoJi | Examples are not Enough, Learn to Criticize! Model Criticism for Interpretable Machine Learning, NIPS16 2 | ||
| Rita | Learning Kernels with Random Features, Aman Sinha*; John Duchi, 3 |
read on: - 21 Jan 2017
| Presenter | Papers | Paper URL | Our Slides |
|---|---|---|---|
| DeepBind | Predicting the sequence specificities of DNA- and RNA-binding proteins by deep learning | ||
| DeepSEA | Deep learning sequence-based ab initio prediction of variant effects on expression and disease risk | ||
| DeepSEA | Deep Supervised and Convolutional Generative Stochastic Network for Protein Secondary Structure Prediction, ICML 2014 | ||
| BioBasics | A method for integrating and ranking the evidence for biochemical pathways by mining reactions from text, Bioinformatics13 | ||
| BioBasics | Efficient counting of k-mers in DNA sequences using a Bloom filter. Melsted P, Pritchard JK. BMC Bioinformatics. 2011 | ||
| BioBasics | Fast String Kernels using Inexact Matching for Protein Sequence, JMLR 2004 | ||
| BioBasics | NIPS09: Locality-Sensitive Binary Codes from Shift-Invariant Kernels | ||
| MedSignal | Segmenting Time Series: A Survey and Novel Approach, |
read on: - 20 Jan 2017
| Presenter | Papers | Paper URL | Our Slides |
|---|---|---|---|
| scalable | Sanjiv Kumar (Columbia EECS 6898), Lecture: Introduction to large-scale machine learning 2010 [^1] | ||
| data scalable | Alex Smola - Berkeley SML: Scalable Machine Learning: Syllabus 2012 [^2] | PDF 2014 + PDF | |
| Binary | Binarized Neural Networks: Training Deep Neural Networks with Weights and Activations Constrained to +1 or -1 | ||
| Model | Binary embeddings with structured hashed projections 1 | ||
| Model | Deep Compression: Compressing Deep Neural Networks (ICLR 2016) 2 |
[125]: recommendation
Table of readings
read on: - 20 Dec 2018
| Presenter | Papers | Paper URL | Our Slides |
|---|---|---|---|
| Bill | Seq2SQL: Generating Structured Queries from Natural Language using Reinforcement Learning | ||
| Chao | Deep EHR: A Survey of Recent Advances in Deep Learning Techniques for Electronic Health Record (EHR) Analysis (I) | ||
| Chao | Deep EHR: A Survey of Recent Advances in Deep Learning Techniques for Electronic Health Record (EHR) Analysis (II) | ||
| Derrick | Deep EHR: A Survey of Recent Advances in Deep Learning Techniques for Electronic Health Record (EHR) Analysis (III) | ||
| Chao | Reading Wikipedia to Answer Open-Domain Questions | ||
| Jennifer | Open Domain Question Answering Using Early Fusion of Knowledge Bases and Text |
read on: - 12 Jan 2017
| Presenter | Papers | Paper URL | Our Slides |
|---|---|---|---|
| QA | Learning to rank with (a lot of) word features | ||
| Relation | A semantic matching energy function for learning with multi-relational data | ||
| Relation | Translating embeddings for modeling multi-relational data | ||
| QA | Reading wikipedia to answer open-domain questions | ||
| QA | Question answering with subgraph embeddings |
[126]: regularization
Table of readings
read on: - 05 Jul 2020
| Index | Papers | Our Slides |
|---|---|---|
| 1 | BIAS ALSO MATTERS: BIAS ATTRIBUTION FOR DEEP NEURAL NETWORK EXPLANATION | Arsh Survey |
| 2 | Data Shapley: Equitable Valuation of Data for Machine Learning | Arsh Survey |
| What is your data worth? Equitable Valuation of Data | Sanchit Survey | |
| 3 | Neural Network Attributions: A Causal Perspective | Zhe Survey |
| 4 | Defending Against Neural Fake News | Eli Survey |
| 5 | Interpretation of Neural Networks is Fragile | Eli Survey |
| Interpretation of Neural Networks is Fragile | Pan Survey | |
| 6 | Parsimonious Black-Box Adversarial Attacks Via Efficient Combinatorial Optimization | Eli Survey |
| 7 | Retrofitting Word Vectors to Semantic Lexicons | Morris Survey |
| 8 | On Evaluation of Adversarial Perturbations for Sequence-to-Sequence Models | Morris Survey |
| 9 | Towards Deep Learning Models Resistant to Adversarial Attacks | Pan Survey |
| 10 | Robust Attribution Regularization | Pan Survey |
| 11 | Sanity Checks for Saliency Maps | Sanchit Survey |
| 12 | Survey of data generation and evaluation in Interpreting DNN pipelines | Sanchit Survey |
| 13 | Think Architecture First: Benchmarking Deep Learning Interpretability in Time Series Predictions | Sanchit Survey |
| 14 | Universal Adversarial Triggers for Attacking and Analyzing NLP | Sanchit Survey |
| 15 | Apricot: Submodular selection for data summarization in Python | Arsh Survey |
read on: - 07 Dec 2019
| Team INDEX | Title & Link | Tags | Our Slide |
|---|---|---|---|
| T11 | Parameter-Efficient Transfer Learning for NLP | meta, BERT, text, Transfer | OurSlide |
| T22 | Deep Asymmetric Multi-task Feature Learning | meta, regularization, Multi-task | OurSlide |
[127]: relational
Table of readings
read on: - 05 Jan 2020
| Index | Papers | Our Slides |
|---|---|---|
| 1 | A Flexible Generative Framework for Graph-based Semi-supervised Learning | Arsh Survey |
| 2 | Learning Discrete Structures for Graph Neural Networks | Arsh Survey |
| 4 | Graph Markov Neural Nets | Arsh Survey |
| Graph Markov Neural Networks | Jack Survey | |
| 5 | GLoMo: Unsupervisedly Learned Relational Graphs as Transferable Representations | Arsh Survey |
| 6 | Subgraph Neural Networks | Arsh Survey |
| 7 | Pointer Graph Networks | Arsh Survey |
| 8 | Modeling Relational Data with Graph Convolutional Networks | Arsh Survey |
| 9 | Graph Learning | Zhe Survey |
| 8 | Neural Relational Inference | Zhe Survey |
read on: - 10 Dec 2019
| Team INDEX | Title & Link | Tags | Our Slide |
|---|---|---|---|
| T3 | Deletion-Robust Submodular Maximization: Data Summarization with Privacy and Fairness Constraints | submodular, coreset, safety | OurSlide |
| T6 | Decision Boundary Analysis of Adversarial Examples | adversarial-examples | OurSlide |
| T8 | Robustness may be at odds with accuracy | robustness | OurSlide |
| T18 | Towards Reverse-Engineering Black-Box Neural Networks | meta, model-as-sample, safety, privacy | OurSlide |
| T23 | The Odds are Odd: A Statistical Test for Detecting Adversarial Examples | adversarial-examples | OurSlide |
| T25 | Learning how to explain neural networks: PatternNet and PatternAttribution | Attribution, Interpretable | OurSlide |
| T31 | Detecting Statistical Interactions from Neural Network Weights | Interpretable, Relational | OurSlide |
Table of readings
read on: - 15 Feb 2019
| Presenter | Papers | Paper URL | Our Slides |
|---|---|---|---|
| Bio | KDEEP: Protein–Ligand Absolute Binding Affinity Prediction via 3D-Convolutional Neural Networks, 2018 1 | Eli Pdf | |
| Bio | Molecular geometry prediction using a deep generative graph neural network | Eli Pdf | |
| Bio | Visualizing convolutional neural network protein-ligand scoring | PDF() | Eli PDF |
| Bio | Deep generative models of genetic variation capture mutation effects | PDF() | Eli PDF |
| Bio | Attentive cross-modal paratope prediction | Eli PDF |
read on: - 01 Feb 2019
| Presenter | Papers | Paper URL | Our Slides |
|---|---|---|---|
| Matching | Deep Learning of Graph Matching, | PDF+ PDF | Jack Pdf |
| Matching | Graph Edit Distance Computation via Graph Neural Networks | Jack Pdf | |
| Basics | Link Prediction Based on Graph Neural Networks | Jack Pdf | |
| Basics | Supervised Community Detection with Line Graph Neural Networks | Jack Pdf | |
| Basics | Graph mining: Laws, generators, and algorithms | Arshdeep PDF | |
| pooling | Hierarchical graph representation learning with differentiable pooling | Eamon PDF |
read on: - 20 Dec 2018
| Presenter | Papers | Paper URL | Our Slides |
|---|---|---|---|
| Bill | Seq2SQL: Generating Structured Queries from Natural Language using Reinforcement Learning | ||
| Chao | Deep EHR: A Survey of Recent Advances in Deep Learning Techniques for Electronic Health Record (EHR) Analysis (I) | ||
| Chao | Deep EHR: A Survey of Recent Advances in Deep Learning Techniques for Electronic Health Record (EHR) Analysis (II) | ||
| Derrick | Deep EHR: A Survey of Recent Advances in Deep Learning Techniques for Electronic Health Record (EHR) Analysis (III) | ||
| Chao | Reading Wikipedia to Answer Open-Domain Questions | ||
| Jennifer | Open Domain Question Answering Using Early Fusion of Knowledge Bases and Text |
read on: - 11 Oct 2018
| Presenter | Papers | Paper URL | Our Slides |
|---|---|---|---|
| Arshdeep | Relational inductive biases, deep learning, and graph networks | ||
| Arshdeep | Discriminative Embeddings of Latent Variable Models for Structured Data | ||
| Jack | Deep Graph Infomax |
read on: - 03 May 2018
| Presenter | Papers | Paper URL | Our Slides |
|---|---|---|---|
| Arshdeep | Show, Attend and Tell: Neural Image Caption Generation with Visual Attention 1 | ||
| Arshdeep | Latent Alignment and Variational Attention 2 | ||
| Arshdeep | Modularity Matters: Learning Invariant Relational Reasoning Tasks, Jason Jo, Vikas Verma, Yoshua Bengio 3 |
read on: - 28 Sep 2017
| Presenter | Papers | Paper URL | Our Slides |
|---|---|---|---|
| Jack | Attend, Adapt and Transfer: Attentive Deep Architecture for Adaptive Transfer from multiple sources in the same domain, ICLR17 1 | ||
| Arshdeep | Bidirectional Attention Flow for Machine Comprehension, ICLR17 2 | PDF + code | |
| Ceyer | Image-to-Markup Generation with Coarse-to-Fine Attention, ICML17 | PDF + code | |
| ChaoJiang | Can Active Memory Replace Attention? ; Samy Bengio, NIPS16 3 | ||
| An Information-Theoretic Framework for Fast and Robust Unsupervised Learning via Neural Population Infomax, ICLR17 |
read on: - 26 Sep 2017
| Presenter | Papers | Paper URL | Our Slides |
|---|---|---|---|
| Rita | Paying More Attention to Attention: Improving the Performance of Convolutional Neural Networks via Attention Transfer, ICLR17 1 | ||
| Tianlu | Dynamic Coattention Networks For Question Answering, ICLR17 2 | PDF + code | |
| ChaoJiang | Structured Attention Networks, ICLR17 3 | PDF + code |
read on: - 21 Jan 2017
| Presenter | Papers | Paper URL | Our Slides |
|---|---|---|---|
| DeepBind | Predicting the sequence specificities of DNA- and RNA-binding proteins by deep learning | ||
| DeepSEA | Deep learning sequence-based ab initio prediction of variant effects on expression and disease risk | ||
| DeepSEA | Deep Supervised and Convolutional Generative Stochastic Network for Protein Secondary Structure Prediction, ICML 2014 | ||
| BioBasics | A method for integrating and ranking the evidence for biochemical pathways by mining reactions from text, Bioinformatics13 | ||
| BioBasics | Efficient counting of k-mers in DNA sequences using a Bloom filter. Melsted P, Pritchard JK. BMC Bioinformatics. 2011 | ||
| BioBasics | Fast String Kernels using Inexact Matching for Protein Sequence, JMLR 2004 | ||
| BioBasics | NIPS09: Locality-Sensitive Binary Codes from Shift-Invariant Kernels | ||
| MedSignal | Segmenting Time Series: A Survey and Novel Approach, |
read on: - 12 Jan 2017
| Presenter | Papers | Paper URL | Our Slides |
|---|---|---|---|
| QA | Learning to rank with (a lot of) word features | ||
| Relation | A semantic matching energy function for learning with multi-relational data | ||
| Relation | Translating embeddings for modeling multi-relational data | ||
| QA | Reading wikipedia to answer open-domain questions | ||
| QA | Question answering with subgraph embeddings |
read on: - 12 Jan 2017
| Presenter | Papers | Paper URL | Our Slides |
|---|---|---|---|
| NLP | A Neural Probabilistic Language Model | ||
| Text | Bag of Tricks for Efficient Text Classification | ||
| Text | Character-level Convolutional Networks for Text Classification | ||
| NLP | BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding | ||
| seq2seq | Neural Machine Translation by Jointly Learning to Align and Translate | ||
| NLP | Natural Language Processing (almost) from Scratch | ||
| Train | Curriculum learning | ||
| Muthu | NeuroIPS Embedding Papers survey 2012 to 2015 | NIPS | |
| Basics | Efficient BackProp |
[128]: rl
Table of readings
read on: - 03 Dec 2022
| Papers | Paper URL | Abstract |
|---|---|---|
| Training language models to follow instructions with human feedback | URL | “further fine-tune this supervised model using reinforcement learning from human feedback. We call the resulting models InstructGPT.” |
| Deep reinforcement learning from human preferences | URL | “explore goals defined in terms of (non-expert) human preferences between pairs of trajectory segments. We show that this approach can effectively solve complex RL tasks without access to the reward function” |
read on: - 03 Jun 2022
Decision Transformer: Reinforcement Learning via Sequence Modeling
- Lili Chen, Kevin Lu, Aravind Rajeswaran, Kimin Lee, Aditya Grover, Michael Laskin, Pieter Abbeel, Aravind Srinivas, Igor Mordatch
- https://arxiv.org/abs/2106.01345
- We introduce a framework that abstracts Reinforcement Learning (RL) as a sequence modeling problem. This allows us to draw upon the simplicity and scalability of the Transformer architecture, and associated advances in language modeling such as GPT-x and BERT. In particular, we present Decision Transformer, an architecture that casts the problem of RL as conditional sequence modeling. Unlike prior approaches to RL that fit value functions or compute policy gradients, Decision Transformer simply outputs the optimal actions by leveraging a causally masked Transformer. By conditioning an autoregressive model on the desired return (reward), past states, and actions, our Decision Transformer model can generate future actions that achieve the desired return. Despite its simplicity, Decision Transformer matches or exceeds the performance of state-of-the-art model-free offline RL baselines on Atari, OpenAI Gym, and Key-to-Door tasks.
Prompting Decision Transformer for Few-Shot Policy Generalization
- Mengdi Xu, Yikang Shen, Shun Zhang, Yuchen Lu, Ding Zhao, Joshua B. Tenenbaum, Chuang Gan
- https://arxiv.org/abs/2206.13499
- Humans can leverage prior experience and learn novel tasks from a handful of demonstrations. In contrast to offline meta-reinforcement learning, which aims to achieve quick adaptation through better algorithm design, we investigate the effect of architecture inductive bias on the few-shot learning capability. We propose a Prompt-based Decision Transformer (Prompt-DT), which leverages the sequential modeling ability of the Transformer architecture and the prompt framework to achieve few-shot adaptation in offline RL. We design the trajectory prompt, which contains segments of the few-shot demonstrations, and encodes task-specific information to guide policy generation. Our experiments in five MuJoCo control benchmarks show that Prompt-DT is a strong few-shot learner without any extra finetuning on unseen target tasks. Prompt-DT outperforms its variants and strong meta offline RL baselines by a large margin with a trajectory prompt containing only a few timesteps. Prompt-DT is also robust to prompt length changes and can generalize to out-of-distribution (OOD) environments.
read on: - 03 May 2022
| Papers | Paper URL | Abstract |
| A Generalist Agent | URL | Gato, works as a multi-modal, multi-task, multi-embodiment generalist policy. The same network with the same weights can play Atari, caption images, chat, stack blocks with a real robot arm and much more, deciding based on its context whether to output text, joint torques, button presses, or other tokens. |
| Why should we prefer offline reinforcement learning over behavioral cloning? ICLR 2022 | URL | natural to ask: when can an offline RL method outperform BC with an equal amount of expert data, even when BC is a natural choice? |
| Uni[MASK]: Unified Inference in Sequential Decision Problems | URL | show how sequential decision making tasks can be thought of in terms of corresponding input maskings, enabling the training of a single model to perform all tasks at once. applies naturally to sequential decision making, where many well-studied tasks like behavior cloning, offline RL, inverse dynamics, and waypoint conditioning correspond to different sequence maskings over a sequence of states, actions, and returns. |
read on: - 05 Mar 2020
| Index | Papers | Our Slides |
|---|---|---|
| 1 | Actor-Critic Methods for Control | Jake Survey |
| 2 | Generalization in Deep Reinforcement Learning | Jake Survey |
| 3 | Sample Efficient RL (Part 1) | Jake Survey |
| 4 | Sample Efficient RL (Part 2) | Jake Survey |
| 5 | Model-Free Value Methods in Deep RL | Jake Survey |
| 6 | Investigating Human Priors for Playing Video Games | Arsh Survey |
read on: - 08 Dec 2019
| Team INDEX | Title & Link | Tags | Our Slide |
|---|---|---|---|
| T1 | Safe Reinforcement Learning via Shielding | RL, safety, verification | OurSlide |
read on: - 15 Mar 2019
| Presenter | Papers | Paper URL | Our Slides |
|---|---|---|---|
| Generate | Maximum-Likelihood Augmented Discrete Generative Adversarial Networks | Tkach PDF + GaoJi Pdf | |
| Generate | Graphical Generative Adversarial Networks | Arshdeep PDF | |
| Generate | GraphRNN: Generating Realistic Graphs with Deep Auto-regressive Models, ICML2018 | Arshdeep PDF | |
| Generate | Inference in probabilistic graphical models by Graph Neural Networks | Arshdeep PDF | |
| Generate | Encoding robust representation for graph generation | Arshdeep PDF | |
| Generate | Junction Tree Variational Autoencoder for Molecular Graph Generation | Tkach PDF + Arshdeep Pdf | |
| Generate | Graph Convolutional Policy Network for Goal-Directed Molecular Graph Generation NeurIPS18 | Tkach PDF | |
| Generate | Towards Variational Generation of Small Graphs | Tkach PDF + Arshdeep Pdf | |
| Generate | Convolutional Imputation of Matrix Networks | Tkach PDF | |
| Generate | Graph Convolutional Matrix Completion | Tkach PDF | |
| Generate | NetGAN: Generating Graphs via Random Walks ICML18 | [ULR] | Tkach PDF |
| Beam | Stochastic Beams and Where to Find Them: The Gumbel-Top-k Trick for Sampling Sequences Without Replacement | URL | Tkach PDF |
read on: - 03 Aug 2018
| Presenter | Papers | Paper URL | Our Slides |
|---|---|---|---|
| GaoJi | Deep Reinforcement Fuzzing, Konstantin Böttinger, Patrice Godefroid, Rishabh Singh | ||
| GaoJi | Reluplex: An Efficient SMT Solver for Verifying Deep Neural Networks, Guy Katz, Clark Barrett, David Dill, Kyle Julian, Mykel Kochenderfer | ||
| GaoJi | DeepTest: Automated Testing of Deep-Neural-Network-driven Autonomous Cars, Yuchi Tian, Kexin Pei, Suman Jana, Baishakhi Ray | ||
| GaoJi | A few Recent (2018) papers on Black-box Adversarial Attacks, like Prior Convictions: Black-Box Adversarial Attacks with Bandits and Priors 1 | ||
| GaoJi | A few Recent papers of Adversarial Attacks on reinforcement learning, like Adversarial Attacks on Neural Network Policies (Sandy Huang, Nicolas Papernot, Ian Goodfellow, Yan Duan, Pieter Abbeel) | ||
| Testing | DeepXplore: Automated Whitebox Testing of Deep Learning Systems |
read on: - 21 Nov 2017
| Presenter | Papers | Paper URL | Our Slides |
|---|---|---|---|
| Jack | Hasselt - Deep Reinforcement Learning | RLSS17.pdf + video | |
| Tianlu | Roux - RL in the Industry | RLSS17.pdf + video | PDF / PDF-Bandit |
| Xueying | Singh - Steps Towards Continual Learning | pdf + video | |
| GaoJi | Distral: Robust Multitask Reinforcement Learning 1 |
read on: - 02 Nov 2017
| Presenter | Papers | Paper URL | Our Slides |
|---|---|---|---|
| GaoJi | Neural Architecture Search with Reinforcement Learning, ICLR17 1 | ||
| Ceyer | Learning to learn 2 | DLSS17video | |
| Beilun | Optimization as a Model for Few-Shot Learning, ICLR17 3 | PDF + More | |
| Anant | Neural Optimizer Search with Reinforcement Learning, ICML17 4 |
[129]: rna
Table of readings
read on: - 13 Aug 2018
| Presenter | Papers | Paper URL | Our Slides |
|---|---|---|---|
| Arshdeep | DeepLesion: automated mining of large-scale lesion annotations and universal lesion detection with deep learning. | ||
| Arshdeep | Solving the RNA design problem with reinforcement learning, PLOSCB 1 | ||
| Arshdeep | Deep learning sequence-based ab initio prediction of variant effects on expression and disease risk 2 | ||
| Arshdeep | Towards Gene Expression Convolutions using Gene Interaction Graphs, Francis Dutil, Joseph Paul Cohen, Martin Weiss, Georgy Derevyanko, Yoshua Bengio 3 | ||
| Brandon | Kipoi: Accelerating the Community Exchange and Reuse of Predictive Models for Genomics | ||
| Arshdeep | Feedback GAN (FBGAN) for DNA: a Novel Feedback-Loop Architecture for Optimizing Protein Functions 2 |
read on: - 21 Jan 2017
| Presenter | Papers | Paper URL | Our Slides |
|---|---|---|---|
| DeepBind | Predicting the sequence specificities of DNA- and RNA-binding proteins by deep learning | ||
| DeepSEA | Deep learning sequence-based ab initio prediction of variant effects on expression and disease risk | ||
| DeepSEA | Deep Supervised and Convolutional Generative Stochastic Network for Protein Secondary Structure Prediction, ICML 2014 | ||
| BioBasics | A method for integrating and ranking the evidence for biochemical pathways by mining reactions from text, Bioinformatics13 | ||
| BioBasics | Efficient counting of k-mers in DNA sequences using a Bloom filter. Melsted P, Pritchard JK. BMC Bioinformatics. 2011 | ||
| BioBasics | Fast String Kernels using Inexact Matching for Protein Sequence, JMLR 2004 | ||
| BioBasics | NIPS09: Locality-Sensitive Binary Codes from Shift-Invariant Kernels | ||
| MedSignal | Segmenting Time Series: A Survey and Novel Approach, |
[130]: rnn
Table of readings
read on: - 11 Dec 2019
| Team INDEX | Title & Link | Tags | Our Slide | |
|---|---|---|---|---|
| T5 | Deep Structured Prediction with Nonlinear Output Transformations | structured | OurSlide | |
| T12 | Large Margin Deep Networks for Classification | OurSlide | large-margin | |
| T15 | Wide Activation for Efficient and Accurate Image Super-Resolution | CNN | OurSlide | |
| T17 | Ordered Neurons: Integrating Tree Structures into Recurrent Neural Networks | RNN | OurSlide | |
| T28 | Processing of missing data by neural networks | imputation | OurSlide | |
| T27 | Implicit Acceleration by Overparameterization | analysis | OurSlide |
read on: - 15 Mar 2019
| Presenter | Papers | Paper URL | Our Slides |
|---|---|---|---|
| Generate | Maximum-Likelihood Augmented Discrete Generative Adversarial Networks | Tkach PDF + GaoJi Pdf | |
| Generate | Graphical Generative Adversarial Networks | Arshdeep PDF | |
| Generate | GraphRNN: Generating Realistic Graphs with Deep Auto-regressive Models, ICML2018 | Arshdeep PDF | |
| Generate | Inference in probabilistic graphical models by Graph Neural Networks | Arshdeep PDF | |
| Generate | Encoding robust representation for graph generation | Arshdeep PDF | |
| Generate | Junction Tree Variational Autoencoder for Molecular Graph Generation | Tkach PDF + Arshdeep Pdf | |
| Generate | Graph Convolutional Policy Network for Goal-Directed Molecular Graph Generation NeurIPS18 | Tkach PDF | |
| Generate | Towards Variational Generation of Small Graphs | Tkach PDF + Arshdeep Pdf | |
| Generate | Convolutional Imputation of Matrix Networks | Tkach PDF | |
| Generate | Graph Convolutional Matrix Completion | Tkach PDF | |
| Generate | NetGAN: Generating Graphs via Random Walks ICML18 | [ULR] | Tkach PDF |
| Beam | Stochastic Beams and Where to Find Them: The Gumbel-Top-k Trick for Sampling Sequences Without Replacement | URL | Tkach PDF |
read on: - 11 May 2018
| Presenter | Papers | Paper URL | Our Slides |
|---|---|---|---|
| Chao | Maximizing Subset Accuracy with Recurrent Neural Networks in Multi-label Classification | ||
| Jack | FastXML: A Fast, Accurate and Stable Tree-classifier for eXtreme Multi-label Learning | ||
| BasicMLC | Multi-Label Classification: An Overview | ||
| SPEN | Structured Prediction Energy Networks | ||
| InfNet | Learning Approximate Inference Networks for Structured Prediction | ||
| SPENMLC | Deep Value Networks | ||
| Adversarial | Semantic Segmentation using Adversarial Networks | ||
| EmbedMLC | StarSpace: Embed All The Things! | ||
| deepMLC | CNN-RNN: A Unified Framework for Multi-label Image Classification/ CVPR 2016 | ||
| deepMLC | Order-Free RNN with Visual Attention for Multi-Label Classification / AAAI 2018 |
[131]: robustness
Table of readings
read on: - 05 Jul 2020
| Index | Papers | Our Slides |
|---|---|---|
| 1 | BIAS ALSO MATTERS: BIAS ATTRIBUTION FOR DEEP NEURAL NETWORK EXPLANATION | Arsh Survey |
| 2 | Data Shapley: Equitable Valuation of Data for Machine Learning | Arsh Survey |
| What is your data worth? Equitable Valuation of Data | Sanchit Survey | |
| 3 | Neural Network Attributions: A Causal Perspective | Zhe Survey |
| 4 | Defending Against Neural Fake News | Eli Survey |
| 5 | Interpretation of Neural Networks is Fragile | Eli Survey |
| Interpretation of Neural Networks is Fragile | Pan Survey | |
| 6 | Parsimonious Black-Box Adversarial Attacks Via Efficient Combinatorial Optimization | Eli Survey |
| 7 | Retrofitting Word Vectors to Semantic Lexicons | Morris Survey |
| 8 | On Evaluation of Adversarial Perturbations for Sequence-to-Sequence Models | Morris Survey |
| 9 | Towards Deep Learning Models Resistant to Adversarial Attacks | Pan Survey |
| 10 | Robust Attribution Regularization | Pan Survey |
| 11 | Sanity Checks for Saliency Maps | Sanchit Survey |
| 12 | Survey of data generation and evaluation in Interpreting DNN pipelines | Sanchit Survey |
| 13 | Think Architecture First: Benchmarking Deep Learning Interpretability in Time Series Predictions | Sanchit Survey |
| 14 | Universal Adversarial Triggers for Attacking and Analyzing NLP | Sanchit Survey |
| 15 | Apricot: Submodular selection for data summarization in Python | Arsh Survey |
read on: - 10 Dec 2019
| Team INDEX | Title & Link | Tags | Our Slide |
|---|---|---|---|
| T3 | Deletion-Robust Submodular Maximization: Data Summarization with Privacy and Fairness Constraints | submodular, coreset, safety | OurSlide |
| T6 | Decision Boundary Analysis of Adversarial Examples | adversarial-examples | OurSlide |
| T8 | Robustness may be at odds with accuracy | robustness | OurSlide |
| T18 | Towards Reverse-Engineering Black-Box Neural Networks | meta, model-as-sample, safety, privacy | OurSlide |
| T23 | The Odds are Odd: A Statistical Test for Detecting Adversarial Examples | adversarial-examples | OurSlide |
| T25 | Learning how to explain neural networks: PatternNet and PatternAttribution | Attribution, Interpretable | OurSlide |
| T31 | Detecting Statistical Interactions from Neural Network Weights | Interpretable, Relational | OurSlide |
read on: - 15 Mar 2019
| Presenter | Papers | Paper URL | Our Slides |
|---|---|---|---|
| Generate | Maximum-Likelihood Augmented Discrete Generative Adversarial Networks | Tkach PDF + GaoJi Pdf | |
| Generate | Graphical Generative Adversarial Networks | Arshdeep PDF | |
| Generate | GraphRNN: Generating Realistic Graphs with Deep Auto-regressive Models, ICML2018 | Arshdeep PDF | |
| Generate | Inference in probabilistic graphical models by Graph Neural Networks | Arshdeep PDF | |
| Generate | Encoding robust representation for graph generation | Arshdeep PDF | |
| Generate | Junction Tree Variational Autoencoder for Molecular Graph Generation | Tkach PDF + Arshdeep Pdf | |
| Generate | Graph Convolutional Policy Network for Goal-Directed Molecular Graph Generation NeurIPS18 | Tkach PDF | |
| Generate | Towards Variational Generation of Small Graphs | Tkach PDF + Arshdeep Pdf | |
| Generate | Convolutional Imputation of Matrix Networks | Tkach PDF | |
| Generate | Graph Convolutional Matrix Completion | Tkach PDF | |
| Generate | NetGAN: Generating Graphs via Random Walks ICML18 | [ULR] | Tkach PDF |
| Beam | Stochastic Beams and Where to Find Them: The Gumbel-Top-k Trick for Sampling Sequences Without Replacement | URL | Tkach PDF |
read on: - 26 Oct 2017
| Presenter | Papers | Paper URL | Our Slides |
|---|---|---|---|
| Tianlu | Robustness of classifiers: from adversarial to random noise, NIPS16 | PDF 1 | |
| Anant | Blind Attacks on Machine Learners, 2 NIPS16 | ||
| Data Noising as Smoothing in Neural Network Language Models (Ng), ICLR17 3 | |||
| The Robustness of Estimator Composition, NIPS16 4 |
read on: - 23 Oct 2017
| Presenter | Papers | Paper URL | Our Slides |
|---|---|---|---|
| GaoJi | Delving into Transferable Adversarial Examples and Black-box Attacks,ICLR17 1 | ||
| Shijia | On Detecting Adversarial Perturbations, ICLR17 2 | ||
| Anant | Parseval Networks: Improving Robustness to Adversarial Examples, ICML17 3 | ||
| Bargav | Being Robust (in High Dimensions) Can Be Practical, ICML17 4 |
read on: - 22 Jul 2017
| Presenter | Papers | Paper URL | Our Slides |
|---|---|---|---|
| GaoJi | A few useful things to know about machine learning | ||
| GaoJi | A few papers related to testing learning, e.g., Understanding Black-box Predictions via Influence Functions | ||
| GaoJi | Automated White-box Testing of Deep Learning Systems 1 | ||
| GaoJi | Testing and Validating Machine Learning Classifiers by Metamorphic Testing 2 | ||
| GaoJi | Software testing: a research travelogue (2000–2014) |
read on: - 19 Jan 2017
| Presenter | Papers | Paper URL | Our Slides |
|---|---|---|---|
| AE | Intriguing properties of neural networks / | ||
| AE | Explaining and Harnessing Adversarial Examples | ||
| AE | Towards Deep Learning Models Resistant to Adversarial Attacks | ||
| AE | DeepFool: a simple and accurate method to fool deep neural networks | ||
| AE | Towards Evaluating the Robustness of Neural Networks by Carlini and Wagner | ||
| Data | Basic Survey of ImageNet - LSVRC competition | URL | |
| Understand | Understanding Black-box Predictions via Influence Functions | ||
| Understand | Deep inside convolutional networks: Visualising image classification models and saliency maps | ||
| Understand | BeenKim, Interpretable Machine Learning, ICML17 Tutorial [^1] | ||
| provable | Provable defenses against adversarial examples via the convex outer adversarial polytope, Eric Wong, J. Zico Kolter, | URL |
[132]: safety
Table of readings
read on: - 10 Dec 2019
| Team INDEX | Title & Link | Tags | Our Slide |
|---|---|---|---|
| T3 | Deletion-Robust Submodular Maximization: Data Summarization with Privacy and Fairness Constraints | submodular, coreset, safety | OurSlide |
| T6 | Decision Boundary Analysis of Adversarial Examples | adversarial-examples | OurSlide |
| T8 | Robustness may be at odds with accuracy | robustness | OurSlide |
| T18 | Towards Reverse-Engineering Black-Box Neural Networks | meta, model-as-sample, safety, privacy | OurSlide |
| T23 | The Odds are Odd: A Statistical Test for Detecting Adversarial Examples | adversarial-examples | OurSlide |
| T25 | Learning how to explain neural networks: PatternNet and PatternAttribution | Attribution, Interpretable | OurSlide |
| T31 | Detecting Statistical Interactions from Neural Network Weights | Interpretable, Relational | OurSlide |
[133]: sample-selection
Table of readings
read on: - 12 Dec 2019
| Team INDEX | Title & Link | Tags | Our Slide |
|---|---|---|---|
| T2 | Empirical Study of Example Forgetting During Deep Neural Network Learning | Sample Selection, forgetting | OurSlide |
| T29 | Select Via Proxy: Efficient Data Selection For Training Deep Networks | Sample Selection | OurSlide |
| T9 | How SGD Selects the Global Minima in over-parameterized Learning | optimization | OurSlide |
| T10 | Escaping Saddles with Stochastic Gradients | optimization | OurSlide |
| T13 | To What Extent Do Different Neural Networks Learn the Same Representation | subspace | OurSlide |
| T19 | On the Information Bottleneck Theory of Deep Learning | informax | OurSlide |
| T20 | Visualizing the Loss Landscape of Neural Nets | normalization | OurSlide |
| T21 | Using Pre-Training Can Improve Model Robustness and Uncertainty | training, analysis | OurSlide |
| T24 | Norm matters: efficient and accurate normalization schemes in deep networks | normalization | OurSlide |
[134]: sampling
Table of readings
read on: - 30 Nov 2017
| Presenter | Papers | Paper URL | Our Slides |
|---|---|---|---|
| Ceyer | Reinforcement Learning with Unsupervised Auxiliary Tasks, ICLR17 1 | ||
| Beilun | Why is Posterior Sampling Better than Optimism for Reinforcement Learning? Ian Osband, Benjamin Van Roy 2 | ||
| Ji | Deeply AggreVaTeD: Differentiable Imitation Learning for Sequential Prediction, ICML17 3 | ||
| Xueying | End-to-End Differentiable Adversarial Imitation Learning, ICML17 4 | ||
| Deep Value Networks Learn to Evaluate and Iteratively Refine Structured Outputs, ICML17 | |||
| FeUdal Networks for Hierarchical Reinforcement Learning, ICML17 5 |
[135]: scalable
Table of readings
read on: - 25 Jan 2019
| Presenter | Papers | Paper URL | Our Notes |
|---|---|---|---|
| Basics | GraphSAGE: Large-scale Graph Representation Learning by Jure Leskovec Stanford University | URL + PDF | |
| Basics | Convolutional Neural Networks on Graphs with Fast Localized Spectral Filtering by Xavier Bresson | URL + PDF | Ryan Pdf |
| Basics | Gated Graph Sequence Neural Networks by Microsoft Research | URL + PDF | Faizan Pdf |
| Basics | DeepWalk - Turning Graphs into Features via Network Embeddings | URL + PDF | |
| Basics | Spectral Networks and Locally Connected Networks on Graphs 1 | GaoJi slides + Bill Pdf | |
| Basics | A Comprehensive Survey on Graph Neural Networks/ Graph Neural Networks: A Review of Methods and Applications | Jack Pdf | |
| GCN | Semi-Supervised Classification with Graph Convolutional Networks | Jack Pdf |
read on: - 22 Apr 2017
| Presenter | Papers | Paper URL | Our Slides |
|---|---|---|---|
| Muthu | Optimization Methods for Large-Scale Machine Learning, Léon Bottou, Frank E. Curtis, Jorge Nocedal 1 | ||
| Muthu | Fast Training of Recurrent Networks Based on EM Algorithm (1998) 2 | ||
| Muthu | FitNets: Hints for Thin Deep Nets, ICLR15 3 | ||
| Muthu | Two NIPS 2015 Deep Learning Optimization Papers | ||
| Muthu | Difference Target Propagation (2015) 4 |
read on: - 20 Jan 2017
| Presenter | Papers | Paper URL | Our Slides |
|---|---|---|---|
| scalable | Sanjiv Kumar (Columbia EECS 6898), Lecture: Introduction to large-scale machine learning 2010 [^1] | ||
| data scalable | Alex Smola - Berkeley SML: Scalable Machine Learning: Syllabus 2012 [^2] | PDF 2014 + PDF | |
| Binary | Binarized Neural Networks: Training Deep Neural Networks with Weights and Activations Constrained to +1 or -1 | ||
| Model | Binary embeddings with structured hashed projections 1 | ||
| Model | Deep Compression: Compressing Deep Neural Networks (ICLR 2016) 2 |
[136]: secure
Table of readings
read on: - 22 Feb 2017
| Presenter | Papers | Paper URL | Our Slides |
|---|---|---|---|
| Tobin | Summary of A few Papers on: Machine Learning and Cryptography, (e.g., learning to Protect Communications with Adversarial Neural Cryptography) 1 | ||
| Tobin | Privacy Aware Learning (NIPS12) 2 | ||
| Tobin | Can Machine Learning be Secure?(2006) |
[137]: semi-supervised
Table of readings
read on: - 01 Feb 2019
| Presenter | Papers | Paper URL | Our Slides |
|---|---|---|---|
| Matching | Deep Learning of Graph Matching, | PDF+ PDF | Jack Pdf |
| Matching | Graph Edit Distance Computation via Graph Neural Networks | Jack Pdf | |
| Basics | Link Prediction Based on Graph Neural Networks | Jack Pdf | |
| Basics | Supervised Community Detection with Line Graph Neural Networks | Jack Pdf | |
| Basics | Graph mining: Laws, generators, and algorithms | Arshdeep PDF | |
| pooling | Hierarchical graph representation learning with differentiable pooling | Eamon PDF |
read on: - 12 Oct 2017
| Presenter | Papers | Paper URL | Our Slides |
|---|---|---|---|
| Xueying | Semi-supervised Knowledge Transfer for Deep Learning from Private Training Data, ICLR17 1 | ||
| Bargav | Deep Learning with Differential Privacy, CCS16 2 | PDF + video | |
| Bargav | Privacy-Preserving Deep Learning, CCS15 3 | ||
| Xueying | Domain Separation Networks, NIPS16 4 |
[138]: seq2seq
Table of readings
read on: - 05 Apr 2019
| Presenter | Papers | Paper URL | Our Slides |
|---|---|---|---|
| Understand | Faithful and Customizable Explanations of Black Box Models | Derrick PDF | |
| Understand | A causal framework for explaining the predictions of black-box sequence-to-sequence models, EMNLP17 | GaoJi PDF + Bill Pdf | |
| Understand | How Powerful are Graph Neural Networks? / Deeper Insights into Graph Convolutional Networks for Semi-Supervised Learning | Pdf + Pdf | GaoJi PDF |
| Understand | Interpretable Graph Convolutional Neural Networks for Inference on Noisy Knowledge Graphs + GNN Explainer: A Tool for Post-hoc Explanation of Graph Neural Networks | Pdf + PDF | GaoJi PDF |
| Understand | Attention is not Explanation, 2019 | ||
| Understand | Understanding attention in graph neural networks, 2019 |
read on: - 20 Dec 2018
| Presenter | Papers | Paper URL | Our Slides |
|---|---|---|---|
| Bill | Seq2SQL: Generating Structured Queries from Natural Language using Reinforcement Learning | ||
| Chao | Deep EHR: A Survey of Recent Advances in Deep Learning Techniques for Electronic Health Record (EHR) Analysis (I) | ||
| Chao | Deep EHR: A Survey of Recent Advances in Deep Learning Techniques for Electronic Health Record (EHR) Analysis (II) | ||
| Derrick | Deep EHR: A Survey of Recent Advances in Deep Learning Techniques for Electronic Health Record (EHR) Analysis (III) | ||
| Chao | Reading Wikipedia to Answer Open-Domain Questions | ||
| Jennifer | Open Domain Question Answering Using Early Fusion of Knowledge Bases and Text |
read on: - 20 May 2018
| Presenter | Papers | Paper URL | Our Slides |
|---|---|---|---|
| Bill | Seq2Sick: Evaluating the Robustness of Sequence-to-Sequence Models with Adversarial Examples | ||
| Bill | Adversarial Examples for Evaluating Reading Comprehension Systems, Robin Jia, Percy Liang | ||
| Bill | Certified Defenses against Adversarial Examples, Aditi Raghunathan, Jacob Steinhardt, Percy Liang | ||
| Bill | Provably Minimally-Distorted Adversarial Examples, Nicholas Carlini, Guy Katz, Clark Barrett, David L. Dill |
read on: - 18 Jan 2017
| Presenter | Papers | Paper URL | Our Slides |
|---|---|---|---|
| seq2seq | Sequence to Sequence Learning with Neural Networks | ||
| Set | Pointer Networks | ||
| Set | Order Matters: Sequence to Sequence for Sets | ||
| Point Attention | Multiple Object Recognition with Visual Attention | ||
| Memory | End-To-End Memory Networks | Jack Survey | |
| Memory | Neural Turing Machines | ||
| Memory | Hybrid computing using a neural network with dynamic external memory | ||
| Muthu | Matching Networks for One Shot Learning (NIPS16) 1 | ||
| Jack | Meta-Learning with Memory-Augmented Neural Networks (ICML16) 2 | ||
| Metric | ICML07 Best Paper - Information-Theoretic Metric Learning |
read on: - 12 Jan 2017
| Presenter | Papers | Paper URL | Our Slides |
|---|---|---|---|
| NLP | A Neural Probabilistic Language Model | ||
| Text | Bag of Tricks for Efficient Text Classification | ||
| Text | Character-level Convolutional Networks for Text Classification | ||
| NLP | BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding | ||
| seq2seq | Neural Machine Translation by Jointly Learning to Align and Translate | ||
| NLP | Natural Language Processing (almost) from Scratch | ||
| Train | Curriculum learning | ||
| Muthu | NeuroIPS Embedding Papers survey 2012 to 2015 | NIPS | |
| Basics | Efficient BackProp |
[139]: set
Table of readings
read on: - 18 Jan 2017
| Presenter | Papers | Paper URL | Our Slides |
|---|---|---|---|
| seq2seq | Sequence to Sequence Learning with Neural Networks | ||
| Set | Pointer Networks | ||
| Set | Order Matters: Sequence to Sequence for Sets | ||
| Point Attention | Multiple Object Recognition with Visual Attention | ||
| Memory | End-To-End Memory Networks | Jack Survey | |
| Memory | Neural Turing Machines | ||
| Memory | Hybrid computing using a neural network with dynamic external memory | ||
| Muthu | Matching Networks for One Shot Learning (NIPS16) 1 | ||
| Jack | Meta-Learning with Memory-Augmented Neural Networks (ICML16) 2 | ||
| Metric | ICML07 Best Paper - Information-Theoretic Metric Learning |
[140]: shapley
Table of readings
read on: - 05 Aug 2020
| Index | Papers | Our Slides |
|---|---|---|
| 0 | A survey on Interpreting Deep Learning Models | Eli Survey |
| Interpretable Machine Learning: Definitions,Methods, Applications | Arsh Survey | |
| 1 | Explaining Explanations: Axiomatic Feature Interactions for Deep Networks | Arsh Survey |
| 2 | Shapley Value review | Arsh Survey |
| L-Shapley and C-Shapley: Efficient Model Interpretation for Structured Data | Bill Survey | |
| Consistent Individualized Feature Attribution for Tree Ensembles | bill Survey | |
| Summary for A value for n-person games | Pan Survey | |
| L-Shapley and C-Shapley: Efficient Model Interpretation for Structured Data | Rishab Survey | |
| 3 | Hierarchical Interpretations of Neural Network Predictions | Arsh Survey |
| Hierarchical Interpretations of Neural Network Predictions | Rishab Survey | |
| 4 | Beyond Word Importance: Contextual Decomposition to Extract Interactions from LSTMs | Arsh Survey |
| Beyond Word Importance: Contextual Decomposition to Extract Interactions from LSTMs | Rishab Survey | |
| 5 | Towards Hierarchical Importance Attribution: Explaining Compositional Semantics for Neural Sequence Models | Rishab Survey |
| Sanchit Survey | ||
| Generating Hierarchical Explanations on Text Classification via Feature Interaction Detection | Sanchit Survey | |
| 6 | This Looks Like That: Deep Learning for Interpretable Image Recognition | Pan Survey |
| 7 | AllenNLP Interpret | Rishab Survey |
| 8 | DISCOVERY OF NATURAL LANGUAGE CONCEPTS IN INDIVIDUAL UNITS OF CNNs | Rishab Survey |
| 9 | How Does BERT Answer Questions? A Layer-Wise Analysis of Transformer Representations | Rishab Survey |
| 10 | Attention is not Explanation | Sanchit Survey |
| Pan Survey | ||
| 11 | Axiomatic Attribution for Deep Networks | Sanchit Survey |
| 12 | Grad-CAM: Visual Explanations from Deep Networks via Gradient-based Localization | Sanchit Survey |
| 13 | Learning Variational Word Masks to Improve the Interpretability of Neural Text Classifier | Sanchit Survey |
| 14 | “Why Should I Trust You?”Explaining the Predictions of Any Classifier | Yu Survey |
| 15 | INTERPRETATIONS ARE USEFUL: PENALIZING EXPLANATIONS TO ALIGN NEURAL NETWORKS WITH PRIOR KNOWLEDGE | Pan Survey |
[141]: sketch
Table of readings
read on: - 20 Jan 2017
| Presenter | Papers | Paper URL | Our Slides |
|---|---|---|---|
| scalable | Sanjiv Kumar (Columbia EECS 6898), Lecture: Introduction to large-scale machine learning 2010 [^1] | ||
| data scalable | Alex Smola - Berkeley SML: Scalable Machine Learning: Syllabus 2012 [^2] | PDF 2014 + PDF | |
| Binary | Binarized Neural Networks: Training Deep Neural Networks with Weights and Activations Constrained to +1 or -1 | ||
| Model | Binary embeddings with structured hashed projections 1 | ||
| Model | Deep Compression: Compressing Deep Neural Networks (ICLR 2016) 2 |
[142]: small-data
Table of readings
read on: - 06 Dec 2019
| Team INDEX | Title & Link | Tags | Our Slide |
|---|---|---|---|
| T33 | The High-Dimensional Geometry of Binary Neural Networks | Quantization, binarization, scalable | OurSlide |
| T34 | Modern Neural Networks Generalize on Small Data Sets | small-data, analysis, ensemble | OurSlide |
| T4 | Cognitive Scheduler for Heterogeneous High Performance Computing System | system-application | OurSlide |
[143]: software-testing
Table of readings
read on: - 20 Nov 2018
| Presenter | Papers | Paper URL | Our Slides |
|---|---|---|---|
| Bill | Adversarial Examples that Fool both Computer Vision and Time-Limited Humans | ||
| Bill | Adversarial Attacks Against Medical Deep Learning Systems | ||
| Bill | TensorFuzz: Debugging Neural Networks with Coverage-Guided Fuzzing | ||
| Bill | Distilling the Knowledge in a Neural Network | ||
| Bill | Defensive Distillation is Not Robust to Adversarial Examples | ||
| Bill | Adversarial Logit Pairing , Harini Kannan, Alexey Kurakin, Ian Goodfellow |
read on: - 03 Aug 2018
| Presenter | Papers | Paper URL | Our Slides |
|---|---|---|---|
| GaoJi | Deep Reinforcement Fuzzing, Konstantin Böttinger, Patrice Godefroid, Rishabh Singh | ||
| GaoJi | Reluplex: An Efficient SMT Solver for Verifying Deep Neural Networks, Guy Katz, Clark Barrett, David Dill, Kyle Julian, Mykel Kochenderfer | ||
| GaoJi | DeepTest: Automated Testing of Deep-Neural-Network-driven Autonomous Cars, Yuchi Tian, Kexin Pei, Suman Jana, Baishakhi Ray | ||
| GaoJi | A few Recent (2018) papers on Black-box Adversarial Attacks, like Prior Convictions: Black-Box Adversarial Attacks with Bandits and Priors 1 | ||
| GaoJi | A few Recent papers of Adversarial Attacks on reinforcement learning, like Adversarial Attacks on Neural Network Policies (Sandy Huang, Nicolas Papernot, Ian Goodfellow, Yan Duan, Pieter Abbeel) | ||
| Testing | DeepXplore: Automated Whitebox Testing of Deep Learning Systems |
read on: - 22 Jul 2017
| Presenter | Papers | Paper URL | Our Slides |
|---|---|---|---|
| GaoJi | A few useful things to know about machine learning | ||
| GaoJi | A few papers related to testing learning, e.g., Understanding Black-box Predictions via Influence Functions | ||
| GaoJi | Automated White-box Testing of Deep Learning Systems 1 | ||
| GaoJi | Testing and Validating Machine Learning Classifiers by Metamorphic Testing 2 | ||
| GaoJi | Software testing: a research travelogue (2000–2014) |
[144]: sparsity
Table of readings
read on: - 21 Sep 2017
| Presenter | Papers | Paper URL | Our Slides |
|---|---|---|---|
| Shijia | Outrageously Large Neural Networks: The Sparsely-Gated Mixture-of-Experts Layer, (Dean), ICLR17 1 | ||
| Ceyer | Sequence Modeling via Segmentations, ICML17 2 | ||
| Arshdeep | Input Switched Affine Networks: An RNN Architecture Designed for Interpretability, ICML17 3 |
read on: - 19 Sep 2017
| Presenter | Papers | Paper URL | Our Slides |
|---|---|---|---|
| Jack | Learning End-to-End Goal-Oriented Dialog, ICLR17 1 | ||
| Bargav | Nonparametric Neural Networks, ICLR17 2 | ||
| Bargav | Learning Structured Sparsity in Deep Neural Networks, NIPS16 3 | ||
| Arshdeep | Learning the Number of Neurons in Deep Networks, NIPS16 4 |
read on: - 20 Jan 2017
| Presenter | Papers | Paper URL | Our Slides |
|---|---|---|---|
| scalable | Sanjiv Kumar (Columbia EECS 6898), Lecture: Introduction to large-scale machine learning 2010 [^1] | ||
| data scalable | Alex Smola - Berkeley SML: Scalable Machine Learning: Syllabus 2012 [^2] | PDF 2014 + PDF | |
| Binary | Binarized Neural Networks: Training Deep Neural Networks with Weights and Activations Constrained to +1 or -1 | ||
| Model | Binary embeddings with structured hashed projections 1 | ||
| Model | Deep Compression: Compressing Deep Neural Networks (ICLR 2016) 2 |
[145]: structured
Table of readings
read on: - 11 Dec 2019
| Team INDEX | Title & Link | Tags | Our Slide | |
|---|---|---|---|---|
| T5 | Deep Structured Prediction with Nonlinear Output Transformations | structured | OurSlide | |
| T12 | Large Margin Deep Networks for Classification | OurSlide | large-margin | |
| T15 | Wide Activation for Efficient and Accurate Image Super-Resolution | CNN | OurSlide | |
| T17 | Ordered Neurons: Integrating Tree Structures into Recurrent Neural Networks | RNN | OurSlide | |
| T28 | Processing of missing data by neural networks | imputation | OurSlide | |
| T27 | Implicit Acceleration by Overparameterization | analysis | OurSlide |
read on: - 06 Mar 2019
| Presenter | Papers | Paper URL | Our Slides |
|---|---|---|---|
| Robust | Adversarial Attacks on Graph Structured Data | Faizan [PDF + GaoJi Pdf | |
| Robust | KDD’18 Adversarial Attacks on Neural Networks for Graph Data | Faizan PDF + GaoJi Pdf | |
| Robust | Attacking Binarized Neural Networks | Faizan PDF |
read on: - 11 May 2018
| Presenter | Papers | Paper URL | Our Slides |
|---|---|---|---|
| Chao | Maximizing Subset Accuracy with Recurrent Neural Networks in Multi-label Classification | ||
| Jack | FastXML: A Fast, Accurate and Stable Tree-classifier for eXtreme Multi-label Learning | ||
| BasicMLC | Multi-Label Classification: An Overview | ||
| SPEN | Structured Prediction Energy Networks | ||
| InfNet | Learning Approximate Inference Networks for Structured Prediction | ||
| SPENMLC | Deep Value Networks | ||
| Adversarial | Semantic Segmentation using Adversarial Networks | ||
| EmbedMLC | StarSpace: Embed All The Things! | ||
| deepMLC | CNN-RNN: A Unified Framework for Multi-label Image Classification/ CVPR 2016 | ||
| deepMLC | Order-Free RNN with Visual Attention for Multi-Label Classification / AAAI 2018 |
read on: - 30 Nov 2017
| Presenter | Papers | Paper URL | Our Slides |
|---|---|---|---|
| Ceyer | Reinforcement Learning with Unsupervised Auxiliary Tasks, ICLR17 1 | ||
| Beilun | Why is Posterior Sampling Better than Optimism for Reinforcement Learning? Ian Osband, Benjamin Van Roy 2 | ||
| Ji | Deeply AggreVaTeD: Differentiable Imitation Learning for Sequential Prediction, ICML17 3 | ||
| Xueying | End-to-End Differentiable Adversarial Imitation Learning, ICML17 4 | ||
| Deep Value Networks Learn to Evaluate and Iteratively Refine Structured Outputs, ICML17 | |||
| FeUdal Networks for Hierarchical Reinforcement Learning, ICML17 5 |
read on: - 14 Nov 2017
| Presenter | Papers | Paper URL | Our Slides |
|---|---|---|---|
| ChaoJiang | Courville - Generative Models II | DLSS17Slide + video | |
| GaoJi | Attend, Infer, Repeat: Fast Scene Understanding with Generative Models, NIPS16 1 | PDF + talk | |
| Arshdeep | Composing graphical models with neural networks for structured representations and fast inference, NIPS16 2 | ||
| Johnson - Graphical Models and Deep Learning | DLSSSlide + video | ||
| Parallel Multiscale Autoregressive Density Estimation, ICML17 3 | |||
| Beilun | Conditional Image Generation with Pixel CNN Decoders, NIPS16 4 | ||
| Shijia | Marrying Graphical Models & Deep Learning | DLSS17 + Video |
read on: - 05 Oct 2017
| Presenter | Papers | Paper URL | Our Slides |
|---|---|---|---|
| Anant | AdaNet: Adaptive Structural Learning of Artificial Neural Networks, ICML17 1 | ||
| Shijia | SplitNet: Learning to Semantically Split Deep Networks for Parameter Reduction and Model Parallelization, ICML17 2 | ||
| Jack | Proximal Deep Structured Models, NIPS16 3 | ||
| Optimal Architectures in a Solvable Model of Deep Networks, NIPS16 4 | |||
| Tianlu | Large-Scale Evolution of Image Classifiers, ICML17 5 |
read on: - 26 Sep 2017
| Presenter | Papers | Paper URL | Our Slides |
|---|---|---|---|
| Rita | Paying More Attention to Attention: Improving the Performance of Convolutional Neural Networks via Attention Transfer, ICLR17 1 | ||
| Tianlu | Dynamic Coattention Networks For Question Answering, ICLR17 2 | PDF + code | |
| ChaoJiang | Structured Attention Networks, ICLR17 3 | PDF + code |
read on: - 21 Sep 2017
| Presenter | Papers | Paper URL | Our Slides |
|---|---|---|---|
| Shijia | Outrageously Large Neural Networks: The Sparsely-Gated Mixture-of-Experts Layer, (Dean), ICLR17 1 | ||
| Ceyer | Sequence Modeling via Segmentations, ICML17 2 | ||
| Arshdeep | Input Switched Affine Networks: An RNN Architecture Designed for Interpretability, ICML17 3 |
read on: - 19 Sep 2017
| Presenter | Papers | Paper URL | Our Slides |
|---|---|---|---|
| Jack | Learning End-to-End Goal-Oriented Dialog, ICLR17 1 | ||
| Bargav | Nonparametric Neural Networks, ICLR17 2 | ||
| Bargav | Learning Structured Sparsity in Deep Neural Networks, NIPS16 3 | ||
| Arshdeep | Learning the Number of Neurons in Deep Networks, NIPS16 4 |
[146]: stylometric
Table of readings
read on: - 29 Mar 2019
| Presenter | Papers | Paper URL | Our Slides |
|---|---|---|---|
| QA | A Comparison of Current Graph Database Models | Pdf + PDF2 | Bill PDF |
| QA | Open Domain Question Answering Using Early Fusion of Knowledge Bases and Text | Bill [PDF + GaoJi Pdf | |
| QA | Generative Question Answering: Learning to Answer the Whole Question, Mike Lewis, Angela Fan | Bill PDF + GaoJi Pdf | |
| QA | Learning to Reason Science Exam Questions with Contextual Knowledge Graph Embeddings / Knowledge Graph Embedding via Dynamic Mapping Matrix | PDF + Pdf | Bill PDF + GaoJi Pdf |
| Text | Adversarial Text Generation via Feature-Mover’s Distance | URL | Faizan PDF |
| Text | Content preserving text generation with attribute controls | URL | Faizan PDF |
| Text | Multiple-Attribute Text Rewriting, ICLR, 2019, | URL | Faizan PDF |
| Text | Writeprints: a stylometric approach to identity level identification and similarity detection in cyberSpace | URL | Faizan PDF |
[147]: submodular
Table of readings
read on: - 10 Dec 2019
| Team INDEX | Title & Link | Tags | Our Slide |
|---|---|---|---|
| T3 | Deletion-Robust Submodular Maximization: Data Summarization with Privacy and Fairness Constraints | submodular, coreset, safety | OurSlide |
| T6 | Decision Boundary Analysis of Adversarial Examples | adversarial-examples | OurSlide |
| T8 | Robustness may be at odds with accuracy | robustness | OurSlide |
| T18 | Towards Reverse-Engineering Black-Box Neural Networks | meta, model-as-sample, safety, privacy | OurSlide |
| T23 | The Odds are Odd: A Statistical Test for Detecting Adversarial Examples | adversarial-examples | OurSlide |
| T25 | Learning how to explain neural networks: PatternNet and PatternAttribution | Attribution, Interpretable | OurSlide |
| T31 | Detecting Statistical Interactions from Neural Network Weights | Interpretable, Relational | OurSlide |
[148]: subspace
Table of readings
read on: - 12 Dec 2019
| Team INDEX | Title & Link | Tags | Our Slide |
|---|---|---|---|
| T2 | Empirical Study of Example Forgetting During Deep Neural Network Learning | Sample Selection, forgetting | OurSlide |
| T29 | Select Via Proxy: Efficient Data Selection For Training Deep Networks | Sample Selection | OurSlide |
| T9 | How SGD Selects the Global Minima in over-parameterized Learning | optimization | OurSlide |
| T10 | Escaping Saddles with Stochastic Gradients | optimization | OurSlide |
| T13 | To What Extent Do Different Neural Networks Learn the Same Representation | subspace | OurSlide |
| T19 | On the Information Bottleneck Theory of Deep Learning | informax | OurSlide |
| T20 | Visualizing the Loss Landscape of Neural Nets | normalization | OurSlide |
| T21 | Using Pre-Training Can Improve Model Robustness and Uncertainty | training, analysis | OurSlide |
| T24 | Norm matters: efficient and accurate normalization schemes in deep networks | normalization | OurSlide |
[149]: temporal-difference
Table of readings
read on: - 28 Nov 2017
| Presenter | Papers | Paper URL | Our Slides |
|---|---|---|---|
| Anant | The Predictron: End-to-End Learning and Planning, ICLR17 1 | ||
| ChaoJiang | Szepesvari - Theory of RL 2 | RLSS.pdf + Video | |
| GaoJi | Mastering the game of Go without human knowledge / Nature 2017 3 | ||
| Thomas - Safe Reinforcement Learning | RLSS17.pdf + video | ||
| Sutton - Temporal-Difference Learning | RLSS17.pdf + Video |
[150]: text
Table of readings
read on: - 12 Jan 2017
| Presenter | Papers | Paper URL | Our Slides |
|---|---|---|---|
| NLP | A Neural Probabilistic Language Model | ||
| Text | Bag of Tricks for Efficient Text Classification | ||
| Text | Character-level Convolutional Networks for Text Classification | ||
| NLP | BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding | ||
| seq2seq | Neural Machine Translation by Jointly Learning to Align and Translate | ||
| NLP | Natural Language Processing (almost) from Scratch | ||
| Train | Curriculum learning | ||
| Muthu | NeuroIPS Embedding Papers survey 2012 to 2015 | NIPS | |
| Basics | Efficient BackProp |
[151]: training
Table of readings
read on: - 12 Dec 2019
| Team INDEX | Title & Link | Tags | Our Slide |
|---|---|---|---|
| T2 | Empirical Study of Example Forgetting During Deep Neural Network Learning | Sample Selection, forgetting | OurSlide |
| T29 | Select Via Proxy: Efficient Data Selection For Training Deep Networks | Sample Selection | OurSlide |
| T9 | How SGD Selects the Global Minima in over-parameterized Learning | optimization | OurSlide |
| T10 | Escaping Saddles with Stochastic Gradients | optimization | OurSlide |
| T13 | To What Extent Do Different Neural Networks Learn the Same Representation | subspace | OurSlide |
| T19 | On the Information Bottleneck Theory of Deep Learning | informax | OurSlide |
| T20 | Visualizing the Loss Landscape of Neural Nets | normalization | OurSlide |
| T21 | Using Pre-Training Can Improve Model Robustness and Uncertainty | training, analysis | OurSlide |
| T24 | Norm matters: efficient and accurate normalization schemes in deep networks | normalization | OurSlide |
[152]: transfer
Table of readings
read on: - 07 Dec 2019
| Team INDEX | Title & Link | Tags | Our Slide |
|---|---|---|---|
| T11 | Parameter-Efficient Transfer Learning for NLP | meta, BERT, text, Transfer | OurSlide |
| T22 | Deep Asymmetric Multi-task Feature Learning | meta, regularization, Multi-task | OurSlide |
[153]: transfer-learning
Table of readings
read on: - 05 Apr 2020
| Index | Papers | Our Slides |
|---|---|---|
| 1 | Invariant Risk Minimization | Zhe Survey |
| 2 | Causal Machine Learning | Zhe Survey |
| 3 | A Meta-Transfer Objective for Learning to Disentangle Causal Mechanisms | Zhe Survey |
| 3 | Review on Optimization-Based Meta Learning | Zhe Survey |
| 4 | Domain adaptation and counterfactual prediction | Zhe Survey |
| 5 | Gaussian Processes | Zhe Survey |
| 6 | A Framework for Learning Predictive Structures from Multiple Tasks and Unlabeled Data | Zhe Survey |
| 7 | Few-shot domain adaptation by causal mechanism transfer | Zhe Survey |
read on: - 28 Sep 2017
| Presenter | Papers | Paper URL | Our Slides |
|---|---|---|---|
| Jack | Attend, Adapt and Transfer: Attentive Deep Architecture for Adaptive Transfer from multiple sources in the same domain, ICLR17 1 | ||
| Arshdeep | Bidirectional Attention Flow for Machine Comprehension, ICLR17 2 | PDF + code | |
| Ceyer | Image-to-Markup Generation with Coarse-to-Fine Attention, ICML17 | PDF + code | |
| ChaoJiang | Can Active Memory Replace Attention? ; Samy Bengio, NIPS16 3 | ||
| An Information-Theoretic Framework for Fast and Robust Unsupervised Learning via Neural Population Infomax, ICLR17 |
read on: - 26 Sep 2017
| Presenter | Papers | Paper URL | Our Slides |
|---|---|---|---|
| Rita | Paying More Attention to Attention: Improving the Performance of Convolutional Neural Networks via Attention Transfer, ICLR17 1 | ||
| Tianlu | Dynamic Coattention Networks For Question Answering, ICLR17 2 | PDF + code | |
| ChaoJiang | Structured Attention Networks, ICLR17 3 | PDF + code |
[154]: trees
Table of readings
read on: - 27 Aug 2018
| Presenter | Papers | Paper URL | Our Slides |
|---|---|---|---|
| Derrick | GloVe: Global Vectors for Word Representation | ||
| Derrick | PARL.AI: A unified platform for sharing, training and evaluating dialog models across many tasks. | URL | |
| Derrick | scalable nearest neighbor algorithms for high dimensional data (PAMI14) 1 | ||
| Derrick | StarSpace: Embed All The Things! | ||
| Derrick | Weaver: Deep Co-Encoding of Questions and Documents for Machine Reading, Martin Raison, Pierre-Emmanuel Mazaré, Rajarshi Das, Antoine Bordes |
[155]: tutorial
Table of readings
read on: - 03 Jan 2021
| Type | Papers | Paper URL | Our Slides |
|---|---|---|---|
| Dr Qi | Survey of 10 DeepLearning (DL) trends different from classic machine learning | OurSlide | |
| Youtube | Generative DL Basics | Youtube1 + Youtube2 | NA |
| Youtube | Computation Graph for DL (pytorch vs. tensorflow | Youtube URL + Youtube2 | NA |
| Youtube | Auto Differentiation for DL | Youtube1+ Youtube2 | NA |
| Youtube | RL basics and DL-RL basics | Youtube1 + Youtube2 | NA |
| Youtube | Probabilistic programming and in DL Pyro | Youtube1 + Youtube2 | NA |
| Youtube | Basics of Software Testing for DL | Youtube URL | NA |
| Course | Bill_CNN_Ng_Lecture_Notes | Bill’s Notes | |
| Course | Bill_caltechMLnotes_ALL | Bill’s Notes | |
| classic Paper | The Lottery Ticket Hypothesis | Morris’ Notes | |
| classic Paper | NLP From Scratch | Morris’ Notes | |
| classic Paper | Statistical Modeling The Two Cultures | Morris’ Notes | |
| classic Paper | Attention_is_All_You_Need | Eli’ Notes | |
| classic Paper | YOLO | Eli’ Notes | |
| classic Paper | Neural Turing Machine | Jake Survey | |
| classic Paper | BERT (Bidirectional Encoder Representation for Transformers): Pretraining of Deep Bidirectional Transformers for Language Understanding | Rishab Survey |
read on: - 03 Nov 2019
| Presenter | Papers | Paper URL | Our Slides |
|---|---|---|---|
| Dr Qi | Survey of Recent DeepLearning to 12 Groups / PDF |
read on: - 29 Aug 2018
| Presenter | Papers | Paper URL | Our Slides |
|---|---|---|---|
| Dr. Qi | Making Deep Learning Understandable for Analyzing Sequential Data about Gene Regulation |
Attend and Predict: Understanding Gene Regulation by Selective Attention on Chromatin, NIPS2017 / Ritambhara Singh, Jack Lanchantin, Arshdeep Sekhon, Yanjun Qi
The past decade has seen a revolution in genomic technologies that enable a flood of genome-wide profiling of chromatin marks. Recent literature tried to understand gene regulation by predicting gene expression from large-scale chromatin measurements. Two fundamental challenges exist for such learning tasks: (1) genome-wide chromatin signals are spatially structured, high-dimensional and highly modular; and (2) the core aim is to understand what are the relevant factors and how they work together? Previous studies either failed to model complex dependencies among input signals or relied on separate feature analysis to explain the decisions. This paper presents an attention-based deep learning approach; we call AttentiveChrome, that uses a unified architecture to model and to interpret dependencies among chromatin factors for controlling gene regulation. AttentiveChrome uses a hierarchy of multiple Long short-term memory (LSTM) modules to encode the input signals and to model how various chromatin marks cooperate automatically. AttentiveChrome trains two levels of attention jointly with the target prediction, enabling it to attend differentially to relevant marks and to locate important positions per mark. We evaluate the model across 56 different cell types (tasks) in human. Not only is the proposed architecture more accurate, but its attention scores also provide a better interpretation than state-of-the-art feature visualization methods such as saliency map. Code and data are shared atwww.deepchrome.org
[156]: understanding
Table of readings
read on: - 12 Oct 2018
| Presenter | Papers | Paper URL | Our Slides |
|---|---|---|---|
| Jack | A Unified Approach to Interpreting Model Predictions | ||
| Jack | “Why Should I Trust You?”: Explaining the Predictions of Any Classifier | ||
| Jack | Visual Feature Attribution using Wasserstein GANs | ||
| Jack | GAN Dissection: Visualizing and Understanding Generative Adversarial Networks | ||
| GaoJi | Recent Interpretable machine learning papers | ||
| Jennifer | The Building Blocks of Interpretability |
read on: - 14 Sep 2017
| Presenter | Papers | Paper URL | Our Slides |
|---|---|---|---|
| SE | Equivariance Through Parameter-Sharing, ICML17 1 | ||
| SE | Why Deep Neural Networks for Function Approximation?, ICLR17 2 | ||
| SE | Geometry of Neural Network Loss Surfaces via Random Matrix Theory, 3ICML17 | ||
| Sharp Minima Can Generalize For Deep Nets, ICML17 4 |
read on: - 12 Sep 2017
| Presenter | Papers | Paper URL | Our Slides |
|---|---|---|---|
| Ceyer | A Closer Look at Memorization in Deep Networks, ICML17 1 | ||
| On the Expressive Efficiency of Overlapping Architectures of Deep Learning 2 | DLSSpdf + video | ||
| Mutual Information | Opening the Black Box of Deep Neural Networks via Information 3 | URL + video | |
| ChaoJiang | Toward Deeper Understanding of Neural Networks: The Power of Initialization and a Dual View on Expressivity, NIPS16 |
read on: - 07 Sep 2017
| Presenter | Papers | Paper URL | Our Slides |
|---|---|---|---|
| Beilun | Learning Deep Parsimonious Representations, NIPS16 1 | ||
| Jack | Dense Associative Memory for Pattern Recognition, NIPS16 2 | PDF + video |
read on: - 05 Sep 2017
| Presenter | Papers | Paper URL | Our Slides |
|---|---|---|---|
| Rita | On the Expressive Power of Deep Neural Networks 1 | ||
| Arshdeep | Understanding deep learning requires rethinking generalization, ICLR17 2 | ||
| Tianlu | On Large-Batch Training for Deep Learning: Generalization Gap and Sharp Minima, ICLR17 3 |
[157]: vae
Table of readings
read on: - 05 Feb 2020
| Index | Papers | Our Slides |
|---|---|---|
| 1 | Beta VAE, Ladder VAE, Causal VAE | Arsh Survey |
| 2 | Learnt Prior VAE | Arsh Survey |
| 3 | Multitask Graph Autoencoder | Arsh Survey |
| 4 | Introduction to component analysi | Zhe Survey |
| 5 | Normalizing flow | Zhe Survey |
| 6 | Nonlinear ICA | Zhe Survey |
| 7 | Deep Convolutional Inverse Graphics Network | Zhe Survey |
read on: - 09 Dec 2019
| Team INDEX | Title & Link | Tags | Our Slide |
|---|---|---|---|
| T14 | CAN: Creative Adversarial Networks Generating “Art” | GAN | OurSlide |
| T26 | Unsupervised Discrete Sentence Representation Learning for Interpretable Neural Dialog Generation | encoder-decoder, dialog, VAE, Interpretable | OurSlide |
| T32 | Which Training Methods for GANs do actually Converge | convergence, optimization, GAN | OurSlide |
[158]: value-networks
Table of readings
read on: - 30 Nov 2017
| Presenter | Papers | Paper URL | Our Slides |
|---|---|---|---|
| Ceyer | Reinforcement Learning with Unsupervised Auxiliary Tasks, ICLR17 1 | ||
| Beilun | Why is Posterior Sampling Better than Optimism for Reinforcement Learning? Ian Osband, Benjamin Van Roy 2 | ||
| Ji | Deeply AggreVaTeD: Differentiable Imitation Learning for Sequential Prediction, ICML17 3 | ||
| Xueying | End-to-End Differentiable Adversarial Imitation Learning, ICML17 4 | ||
| Deep Value Networks Learn to Evaluate and Iteratively Refine Structured Outputs, ICML17 | |||
| FeUdal Networks for Hierarchical Reinforcement Learning, ICML17 5 |
[159]: variational
Table of readings
read on: - 15 Mar 2019
| Presenter | Papers | Paper URL | Our Slides |
|---|---|---|---|
| Generate | Maximum-Likelihood Augmented Discrete Generative Adversarial Networks | Tkach PDF + GaoJi Pdf | |
| Generate | Graphical Generative Adversarial Networks | Arshdeep PDF | |
| Generate | GraphRNN: Generating Realistic Graphs with Deep Auto-regressive Models, ICML2018 | Arshdeep PDF | |
| Generate | Inference in probabilistic graphical models by Graph Neural Networks | Arshdeep PDF | |
| Generate | Encoding robust representation for graph generation | Arshdeep PDF | |
| Generate | Junction Tree Variational Autoencoder for Molecular Graph Generation | Tkach PDF + Arshdeep Pdf | |
| Generate | Graph Convolutional Policy Network for Goal-Directed Molecular Graph Generation NeurIPS18 | Tkach PDF | |
| Generate | Towards Variational Generation of Small Graphs | Tkach PDF + Arshdeep Pdf | |
| Generate | Convolutional Imputation of Matrix Networks | Tkach PDF | |
| Generate | Graph Convolutional Matrix Completion | Tkach PDF | |
| Generate | NetGAN: Generating Graphs via Random Walks ICML18 | [ULR] | Tkach PDF |
| Beam | Stochastic Beams and Where to Find Them: The Gumbel-Top-k Trick for Sampling Sequences Without Replacement | URL | Tkach PDF |
read on: - 29 Dec 2018
| Presenter | Papers | Paper URL | Our Slides |
|---|---|---|---|
| Tkach | Boundary-Seeking Generative Adversarial Networks | ||
| Tkach | Maximum-Likelihood Augmented Discrete Generative Adversarial Networks | ||
| Tkach | Generating Sentences from a Continuous Space |
read on: - 21 Dec 2018
| Presenter | Papers | Paper URL | Our Slides |
|---|---|---|---|
| Arshdeep | Constrained Graph Variational Autoencoders for Molecule Design | ||
| Arshdeep | Learning Deep Generative Models of Graphs | ||
| Arshdeep | Graph Convolutional Policy Network for Goal-Directed Molecular Graph Generation | ||
| Jack | Generating and designing DNA with deep generative models |
read on: - 23 Aug 2018
| Presenter | Papers | Paper URL | Our Slides |
|---|---|---|---|
| Arshdeep | The Concrete Distribution: A Continuous Relaxation of Discrete Random Variables, Chris J. Maddison, Andriy Mnih, Yee Whye Teh 1 | ||
| GaoJi | Summary Of Several Autoencoder models | ||
| GaoJi | Latent Constraints: Learning to Generate Conditionally from Unconditional Generative Models, Jesse Engel, Matthew Hoffman, Adam Roberts 2 | ||
| GaoJi | Summary of A Few Recent Papers about Discrete Generative models, SeqGAN, MaskGAN, BEGAN, BoundaryGAN | ||
| Arshdeep | Semi-Amortized Variational Autoencoders, Yoon Kim, Sam Wiseman, Andrew C. Miller, David Sontag, Alexander M. Rush 3 | ||
| Arshdeep | Synthesizing Programs for Images using Reinforced Adversarial Learning, Yaroslav Ganin, Tejas Kulkarni, Igor Babuschkin, S.M. Ali Eslami, Oriol Vinyals 4 |
read on: - 03 May 2018
| Presenter | Papers | Paper URL | Our Slides |
|---|---|---|---|
| Arshdeep | Show, Attend and Tell: Neural Image Caption Generation with Visual Attention 1 | ||
| Arshdeep | Latent Alignment and Variational Attention 2 | ||
| Arshdeep | Modularity Matters: Learning Invariant Relational Reasoning Tasks, Jason Jo, Vikas Verma, Yoshua Bengio 3 |
[160]: verification
Table of readings
read on: - 08 Dec 2019
| Team INDEX | Title & Link | Tags | Our Slide |
|---|---|---|---|
| T1 | Safe Reinforcement Learning via Shielding | RL, safety, verification | OurSlide |
read on: - 03 Aug 2018
| Presenter | Papers | Paper URL | Our Slides |
|---|---|---|---|
| GaoJi | Deep Reinforcement Fuzzing, Konstantin Böttinger, Patrice Godefroid, Rishabh Singh | ||
| GaoJi | Reluplex: An Efficient SMT Solver for Verifying Deep Neural Networks, Guy Katz, Clark Barrett, David Dill, Kyle Julian, Mykel Kochenderfer | ||
| GaoJi | DeepTest: Automated Testing of Deep-Neural-Network-driven Autonomous Cars, Yuchi Tian, Kexin Pei, Suman Jana, Baishakhi Ray | ||
| GaoJi | A few Recent (2018) papers on Black-box Adversarial Attacks, like Prior Convictions: Black-Box Adversarial Attacks with Bandits and Priors 1 | ||
| GaoJi | A few Recent papers of Adversarial Attacks on reinforcement learning, like Adversarial Attacks on Neural Network Policies (Sandy Huang, Nicolas Papernot, Ian Goodfellow, Yan Duan, Pieter Abbeel) | ||
| Testing | DeepXplore: Automated Whitebox Testing of Deep Learning Systems |
[161]: visualizing
Table of readings
read on: - 15 Feb 2019
| Presenter | Papers | Paper URL | Our Slides |
|---|---|---|---|
| Bio | KDEEP: Protein–Ligand Absolute Binding Affinity Prediction via 3D-Convolutional Neural Networks, 2018 1 | Eli Pdf | |
| Bio | Molecular geometry prediction using a deep generative graph neural network | Eli Pdf | |
| Bio | Visualizing convolutional neural network protein-ligand scoring | PDF() | Eli PDF |
| Bio | Deep generative models of genetic variation capture mutation effects | PDF() | Eli PDF |
| Bio | Attentive cross-modal paratope prediction | Eli PDF |
read on: - 02 Dec 2018
| Presenter | Papers | Paper URL | Our Slides |
|---|---|---|---|
| Jennifer | Adversarial Attacks Against Medical Deep Learning Systems | ||
| Jennifer | Adversarial-Playground: A Visualization Suite Showing How Adversarial Examples Fool Deep Learning | ||
| Jennifer | Black-box Generation of Adversarial Text Sequences to Evade Deep Learning Classifiers | ||
| Jennifer | CleverHans | ||
| Ji | Ji-f18-New papers about adversarial attack |
read on: - 12 Oct 2018
| Presenter | Papers | Paper URL | Our Slides |
|---|---|---|---|
| Jack | A Unified Approach to Interpreting Model Predictions | ||
| Jack | “Why Should I Trust You?”: Explaining the Predictions of Any Classifier | ||
| Jack | Visual Feature Attribution using Wasserstein GANs | ||
| Jack | GAN Dissection: Visualizing and Understanding Generative Adversarial Networks | ||
| GaoJi | Recent Interpretable machine learning papers | ||
| Jennifer | The Building Blocks of Interpretability |
read on: - 11 Oct 2017
| Presenter | Papers | Paper URL | Our Slides |
|---|---|---|---|
| Rita | Visualizing Deep Neural Network Decisions: Prediction Difference Analysis, ICLR17 1 | ||
| Arshdeep | Axiomatic Attribution for Deep Networks, ICML17 2 | ||
| The Robustness of Estimator Composition, NIPS16 |
read on: - 24 Aug 2017
Ganguli - Theoretical Neuroscience and Deep Learning
| Presenter | Papers | Paper URL | Our Slides |
|---|---|---|---|
| DLSS16 | video | ||
| DLSS17 | video + slide | ||
| DLSS17 | Deep learning in the brain | DLSS17 + Video |
read on: - 19 Jan 2017
| Presenter | Papers | Paper URL | Our Slides |
|---|---|---|---|
| AE | Intriguing properties of neural networks / | ||
| AE | Explaining and Harnessing Adversarial Examples | ||
| AE | Towards Deep Learning Models Resistant to Adversarial Attacks | ||
| AE | DeepFool: a simple and accurate method to fool deep neural networks | ||
| AE | Towards Evaluating the Robustness of Neural Networks by Carlini and Wagner | ||
| Data | Basic Survey of ImageNet - LSVRC competition | URL | |
| Understand | Understanding Black-box Predictions via Influence Functions | ||
| Understand | Deep inside convolutional networks: Visualising image classification models and saliency maps | ||
| Understand | BeenKim, Interpretable Machine Learning, ICML17 Tutorial [^1] | ||
| provable | Provable defenses against adversarial examples via the convex outer adversarial polytope, Eric Wong, J. Zico Kolter, | URL |
[162]: white-box
Table of readings
read on: - 03 Aug 2018
| Presenter | Papers | Paper URL | Our Slides |
|---|---|---|---|
| GaoJi | Deep Reinforcement Fuzzing, Konstantin Böttinger, Patrice Godefroid, Rishabh Singh | ||
| GaoJi | Reluplex: An Efficient SMT Solver for Verifying Deep Neural Networks, Guy Katz, Clark Barrett, David Dill, Kyle Julian, Mykel Kochenderfer | ||
| GaoJi | DeepTest: Automated Testing of Deep-Neural-Network-driven Autonomous Cars, Yuchi Tian, Kexin Pei, Suman Jana, Baishakhi Ray | ||
| GaoJi | A few Recent (2018) papers on Black-box Adversarial Attacks, like Prior Convictions: Black-Box Adversarial Attacks with Bandits and Priors 1 | ||
| GaoJi | A few Recent papers of Adversarial Attacks on reinforcement learning, like Adversarial Attacks on Neural Network Policies (Sandy Huang, Nicolas Papernot, Ian Goodfellow, Yan Duan, Pieter Abbeel) | ||
| Testing | DeepXplore: Automated Whitebox Testing of Deep Learning Systems |
read on: - 22 Jul 2017
| Presenter | Papers | Paper URL | Our Slides |
|---|---|---|---|
| GaoJi | A few useful things to know about machine learning | ||
| GaoJi | A few papers related to testing learning, e.g., Understanding Black-box Predictions via Influence Functions | ||
| GaoJi | Automated White-box Testing of Deep Learning Systems 1 | ||
| GaoJi | Testing and Validating Machine Learning Classifiers by Metamorphic Testing 2 | ||
| GaoJi | Software testing: a research travelogue (2000–2014) |