kdha0727/cs224w

Graph Neural Networks: Stanford university CS224w

CS224w: Machine Learning with Graphs

Implementations

• GCN: Graph Convolution Network (Thomas N. Kipf, et al. arXiv:1609.02907 [cs.LG])
• GAT: Graph Attention Network (Petar Veličković, et al. arXiv:1710.10903 [stat.ML])

Lecture Notes (Video available in here)

Index	Lecture	Report	Lab
01.	Introduction; Machine Learning for Graphs	Report
02.	Traditional Methods for ML on Graphs	Report	Colab 0
03.	Node Embeddings	Report
04.	Link Analysis: PageRank	Report	Colab 1
05.	Label Propagation for Node Classification	Report
06.	Graph Neural Networks 1: GNN Model	Report	Colab 2
07.	Graph Neural Networks 2: Design Space	Report
08.	Applications of Graph Neural Networks	Report
09.	Theory of Graph Neural Networks	Report
10.	Knowledge Graph Embeddings		Colab 3
11.	Reasoning over Knowledge Graphs
12.	Frequent Subgraph Mining with GNNs
13.	GNNs for Recommender Systems		Colab 4
14.	Community Structure in Networks
15.	Deep Generative Models for Graphs		Colab 5
16.	Advanced Topics on GNNs
17.	Scaling Up GNNs
18.	Guest Lecture: Petar Veličković
19.	Design Space of Graph Neural Networks

Schedule

• 2022.01. ~ 2022.02
  • Lecture: 1 ~ 9
  • Lab: 0 ~ 3
  • Implementation: GAT & GCN