Skip to content

Latest commit

 

History

History
38 lines (22 loc) · 2.17 KB

GNN-Resources.md

File metadata and controls

38 lines (22 loc) · 2.17 KB

Useful resources about Graph Neural Networks

  1. Message Passing All The Way Up, link

  2. A video on oversmoothing, link

  3. Graph-In-Graph: Learning interpretable latent graphs in non-Euclidean domain for biological and healthcare applications, link

  4. About the role of graph pooling, link

  5. Cooperative GNNs, link

  6. Graph benchmark, link

  7. Oversquashing, bottlenecks, Graph Ricci curvature, link

  8. Message passing simplicial networks, link

  9. Enhancing topological message passing, link

  10. Improving Graph Neural Network Expressivity via Subgraph Isomorphism Counting, link

  11. Weisfeiler and lehman go topological: Message passing simplicial networks, link

  12. Geometric deep learning: going beyond euclidean data, link

  13. Dynamic Graph CNN for learning on point clouds, link

  14. Geometric deep learning on graphs and manifolds using mixture model cnns, link

  15. Graph Attention Networks, link

Video resources:

  • Theoretical foundations of GNNs, by Petar Veličković link
  • A brief history of geometric deep learning, Michael Bronstein link
  • Topological message passing, Cristian Bodnar link
  • Sheaf Neural Networks, Cristian Bodnar link