Subgraph-Based Networks for Expressive, Efficient, and Domain-Independent Graph Learning

Subgraph-Based Networks for Expressive, Efficient, and Domain-Independent Graph Learning

Centre International de Rencontres Mathématiques via YouTube Direct link

Intro

1 of 19

1 of 19

Intro

Class Central Classrooms beta

YouTube videos curated by Class Central.

Classroom Contents

Subgraph-Based Networks for Expressive, Efficient, and Domain-Independent Graph Learning

Automatically move to the next video in the Classroom when playback concludes

  1. 1 Intro
  2. 2 Learning on graphs
  3. 3 Setup
  4. 4 Message passing Neural Networks
  5. 5 Color refinement (CR)
  6. 6 MPNNs have limited expressivity
  7. 7 Why expressivity matters?
  8. 8 Sets of subgraphs: example
  9. 9 Equivariant Subgraph Aggregation Networks (ESAN)
  10. 10 Equivariance as a design principle
  11. 11 Symmetry for sets of subgraphs
  12. 12 Detour: Deep Sets for Symmetric Elements
  13. 13 Equivariant layer
  14. 14 Subpraph selection policies
  15. 15 Stochastic subgraph sampling
  16. 16 Design choices and expressivity
  17. 17 Experiments
  18. 18 Detour: Invariant Graph Networks (IGNs)
  19. 19 Symmetries of node-based policies

Never Stop Learning.

Get personalized course recommendations, track subjects and courses with reminders, and more.

Someone learning on their laptop while sitting on the floor.