Completed
Improving discriminative power
Class Central Classrooms beta
YouTube videos curated by Class Central.
Classroom Contents
Theory of Graph Neural Networks: Representation and Learning
Automatically move to the next video in the Classroom when playback concludes
- 1 Intro
- 2 Machine Learning in one picture
- 3 Machine Learning with Graph Data: Applicat
- 4 Outline
- 5 GNNS: Origins and Relations
- 6 Message Passing Graph Neural Networks
- 7 Message Passing for Node Embedding
- 8 Fully connected Neural Network (FNN)
- 9 Message Passing Tree
- 10 Function Approximation and Graph Distincti
- 11 Color refinement/Weisfeiler-Leman algorith
- 12 Improving discriminative power
- 13 Node IDs and Local Algorithms
- 14 The challenge with generalization
- 15 Bounding the generalization gap
- 16 Neural Tangent Kernel
- 17 Computational structure
- 18 Algorithmic Alignment
- 19 Big picture: when may extrapolation "work"?
- 20 Extrapolation in fully connected ReLU netwo
- 21 Implications for the full GNN
- 22 Open Questions...
