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