Completed
GNNs and graph convolutions
Class Central Classrooms beta
YouTube videos curated by Class Central.
Classroom Contents
Graph Mining Hamilton
Automatically move to the next video in the Classroom when playback concludes
- 1 Intro
- 2 Learning on graph-structured data
- 3 Node classification in the real world
- 4 Link prediction in the real world
- 5 Graph classification in the real world
- 6 The rise of deep learning on graphs
- 7 Outline for today
- 8 What is graph representation learning Goal: Learning useful node and graph representations without hand-crafted features.
- 9 Key challenges of graph data . Two key challenges with graph-structured data
- 10 Limitations of traditional node embeddings
- 11 Node embeddings to graph neural networks
- 12 What about graph classification?
- 13 The impact of GNNs: drug repurposing
- 14 The impact of GNNs: recommender systems
- 15 GNNs and graph convolutions
- 16 Graph Fourier analysis
- 17 What does this have to do with GNNS
- 18 Weisfeiler-Lehman algorithm
- 19 Practical GNNs beyond the WL hierarchy
- 20 Breaking the bottleneck of message passing
- 21 Three challenges or one?
