Zhe’s PhD Defense - Toward Out-Of-Distribution Generalization Of Deep Learning Models
Ph.D. Dissertation Defense by Zhe Wang, Tues., 04/02/24, at 12:00PM (ET) Committee:
Deep Learning's Generalization, Especially on structured discrete data
This front adapts from our legacy website deeplearning4discrete.net and introduces a suite of
deep learning tools we have developed for improve deep learning generalization, especially when on discrete structured
data types like text, graph, or sets. Please feel free to email me when you find my typos.
Background on why Generalization topics of Deep Learning are interesting?
Generalization refers to how a machine model adapts properly to new, previously unseen data. We focus on OOD (out of distribution) generalization.
Why structured discrete Data is Interesting?
Deep learning constructs networks of parameterized functional modules and is trained from reference examples using gradient-based optimization [Lecun19].
Since it is hard to estimate gradients through functions of discrete random variables, researching on how to make deep learning behave well on discrete structured data and structured representation interests us. Developing such techniques are an active research area. We focus on investigating interpretable and scalable techniques for doing so.
Relevant Papers we published
- We can use a component-view to categorize the research topics in OOD generalization:
- (1) sample level
- (2) feature level
- (3) representation/encoding level
- (4) loss level
- (5) task level (e.g., meta learning, few shot generalization)
- Please check out each item in our side-bar
Contacts:
Have questions or suggestions? Feel free to ask me on Twitter or email me.
Thanks for reading!
Arsh’s PhD Defense - Relational Structure Discovery for Deep Learning
Arshdeep Sekhon’s PhD Defense June 29, 2022.
JackL’s PhD Defense - Modeling interactions with Deep Learning
Ph.D. Dissertation Defense by Jack Lanchantin Tuesday, July 20th, 2021 at 2:00 PM (ET), via Zoom. Committee: Vicente Ordóñez Román, Committee Chair, ...
ACM BCB - Transfer Learning for Predicting Virus-Host Protein Interactions for Novel Virus Sequences
CVPR - General Multi-label Image Classification with Transformers
Title: General Multi-label Image Classification with Transformers
AAAI - Curriculum Labeling- Self-paced Pseudo-Labeling for Semi-Supervised Learning
Title: Curriculum Labeling- Self-paced Pseudo-Labeling for Semi-Supervised Learning”
EMNLP - Benchmarking Search Algorithms for Generating NLP Adversarial Examples
Title: Searching for a Search Method: Benchmarking Search Algorithms for Generating NLP Adversarial Examples
EMNLP- On Quality of Generated Adversarial Examples and How to Set Attack Contraints
Title: Reevaluating Adversarial Examples in Natural Language
Beilun’s PhD Defense - Fast and Scalable Joint Estimators for Learning Sparse Gaussian Graphical Models from Heterogeneous Data with Additional Knowledge
PhD Defense Presentation by Beilun Wang Friday, July 20, 2018 at 9:00 am in Rice 242 Committee Members: Mohammad Mahmoody (Chair), Yanjun Qi (Advisor), ...
AAAI - MUST-CNN- A Multilayer Shift-and-Stitch Deep Convolutional Architecture for Sequence-based Protein Structure Prediction
Tool MUST-CNN: A Multilayer Shift-and-Stitch Deep Convolutional Architecture for Sequence-based Protein Structure Prediction
ECIR - Deep Learning for Character-based Information Extraction on Chinese and Protein Sequence
Title: Deep Learning for Character-based Information Extraction on Chinese and Protein Sequence
Plos- A unified multitask architecture for predicting local structural properties on proteins
Tool Multitask-ProteinTagging: A unified multitask architecture for predicting local protein properties
NeurIPS - Deep Metric Learning to Learn and to Use
Paper0: Learning to rank with (a lot of) word features