A Framework for Differentiable Discovery of Graph Algorithms

A Framework for Differentiable Discovery of Graph Algorithms

Institute for Pure & Applied Mathematics (IPAM) via YouTube Direct link

Intro

1 of 19

1 of 19

Intro

Class Central Classrooms beta

YouTube videos curated by Class Central.

Classroom Contents

A Framework for Differentiable Discovery of Graph Algorithms

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

  1. 1 Intro
  2. 2 Graphs are everywhere
  3. 3 Combinatorial optimization over graph
  4. 4 Graph neural networks (GNN/MPN/Structure2vec)
  5. 5 Sequential vs distributed local algorithms
  6. 6 Leaming algorithms with reinforcement leaming
  7. 7 Example of leamed sequential algorithms
  8. 8 Example of distributed local algorithms: PageRank
  9. 9 GNN - Parametrized distributed local graph algorithm
  10. 10 Challenges for leaming new algorithms
  11. 11 Motivating example
  12. 12 Spanning tree solution as cheap global feature
  13. 13 Multiple spanning trees to multiple features
  14. 14 Better learned algorithms with global information
  15. 15 Unsupervised
  16. 16 Better time-solution trade-off
  17. 17 Anchor nodes of explanation
  18. 18 Comparing feature quality
  19. 19 Differentiable Algorithm Discovery (DAD)

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.