GNN Basics I - Deep Learning Advances on Graphs
| Presenter | Papers | Paper URL | Our Notes |
|---|---|---|---|
| Basics | GraphSAGE: Large-scale Graph Representation Learning by Jure Leskovec Stanford University | URL + PDF | ย |
| 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 | ย |
| 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 |
-
Some Relevant Notes from URL. On periodic domain, people always use Fourier basis, which eigenvectors of Laplace operator. On sphere, people use spherical harmonics, which also are eigenvectors of Laplace operator. In applied science, people decompose functions on a graph using eigenvectors of graph laplacian. Why are these basis preferred? The exponentials used in Fourier series are eigenvalues of shifts, and thus of any operator commuting with shifts, not just Laplacian. Similarly, spherical harmonics carry irreducible representations of ๐๐(3) and so they are eigenfunctions of any rotationally invariant operator. If the underlying space has symmetries, itโs no wonder that a basis respecting those symmetries has some nice properties. ย ↩