A curated repository of all learning resources from stanfords CS224W course about machine learning with graphs, includes all reading materials from lectures and jupyter notebooks for assigned homeworks. Have fun learning!
- http://web.stanford.edu/class/cs224w/ - contains all files for slides, reading materials, and jupyter notebooks used
- https://github.com/hdvvip/CS224W_Winter2021 - contains all notebooks used in the course exclusively
Syllabus: Date Description Optional Readings Events Deadlines Tue 1/10 1. Introduction lectures 1.1 to 1.3 [slides] finished 1.1, 1.2, 1.3 Thu 1/12 2. Feature Engineering for ML in Graphs lectures 2.1 to 2.3 [slides] finished 2.1, 2.2 pending 2.3 Efficient Graphlet Kernels for Large Graph Comparison Weisfeiler-lehman Graph Kernels Colab 0, Colab 1 out
Tue 1/17 3. Node Embeddings lectures 3.1 to 5.3 [slides] finished 3.2 pending 3.3 to 5.3 DeepWalk: Online Learning of Social Representations node2vec: Scalable Feature Learning for Networks Network Embedding as Matrix Factorization Thu 1/19 4. Graph Neural Networks lectures 6.1 to 6.3 [slides] finished 6.1, 6.2, 6.3 Geometric Deep Learning: the Erlangen Programme of ML Semi-Supervised Classification with Graph Convolutional Networks Homework 1 out
Tue 1/24 5. A General Perspective on GNNs lectures 7.1 to 7.3 [slides] finished 7.1, 7.2 pending 7.3 Design Space of Graph Neural Networks Inductive Representation Learning on Large Graphs Graph Attention Networks Thu 1/26 6. GNN Augmentation and Training *lectures 8.1 to [slides] **finished Hierarchical Graph Representation Learning with Differentiable Pooling Colab 2 out Colab 1 due
Tue 1/31 7. Theory of Graph Neural Networks [slides] How Powerful Are Graph Neural Networks? Thu 2/2 8. Label Propagation on Graphs [slides] Combining Label Propagation and Simple Models Out-performs Graph Neural Networks Masked Label Prediction: Unified Message Passing Model for Semi-Supervised Classification Homework 2 out LaTeX template Homework 1 due
Tue 2/7 9. Machine Learning with Heterogeneous Graphs [slides] Modeling Relational Data with Graph Convolutional Networks Heterogeneous Graph Transformer Project Proposal due
Thu 2/9 10. Knowledge Graph Embeddings [slides] Translating Embeddings for Modeling Multi-relational Data Learning Entity and Relation Embeddings for Knowledge Graph Completion Embedding Entities and Relations for Learning and Inference in Knowledge Bases Complex Embeddings for Simple Link Prediction RotatE: Knowledge Graph Embedding by Relational Rotation in Complex Space Colab 3 out Colab 2 due
Tue 2/14 11. Reasoning over Knowledge Graphs [slides] Embedding Logical Queries on Knowledge Graphs Query2box: Reasoning over Knowledge Graphs in Vector Space Using Box Embeddings Traversing Knowledge Graphs in Vector Space
Thu 2/16 12. Fast Neural Subgraph Matching and Counting [slides] Network Motifs: Simple Building Blocks of Complex Networks Neural Subgraph Matching SPMiner: Frequent Subgraph Mining by Walking in Order Embedding Space Homework 3 out LaTeX template
Tue 2/21 13. GNNs for Recommender Systems [slides] Neural Graph Collaborative Filtering LightGCN: Simplifying and Powering Graph Convolution Network for Recommendation Graph Convolutional Neural Networks for Web-Scale Recommender Systems
Thu 2/23 14. Deep Generative Models for Graphs [slides] GraphRNN: Generating Realistic Graphs with Deep Auto-regressive Models Graph Convolutional Policy Network for Goal-Directed Molecular Graph Generation Colab 4 out Colab 3 due
Tue 2/28 15. Advanced Topics in GNNs [slides] Position-aware Graph Neural Networks Identity-aware Graph Neural Networks Adversarial Attacks on Neural Networks for Graph Data
Thu 3/2 16. Scaling Up GNNs to Large Graphs Guest Lecture: Weihua Hu [slides] Cluster-GCN: An Efficient Algorithm for Training Deep and Large Graph Convolutional Networks Simplifying Graph Convolutional Networks Colab 5 out Homework 3 due
Thu 3/9 17. Geometric Graph Learning Guest Lecture: Minkai Xu [slides] SchNet: A continuous-filter convolutional neural network for modeling quantum interactions Equivariant message passing for the prediction of tensorial properties and molecular spectra Tensor field networks: Rotation- and translation-equivariant neural networks for 3D point clouds GeoDiff: A Geometric Diffusion Model for Molecular Conformation Generation Colab 4 due
Tue 3/14 18. Trustworthy Graph AI Guest Lecture: Rex Ying [slides] LIME: Local Interpretable Model-Agnostic Explanations A Unified Approach to Interpreting Model Predictions GNNExplainer Explainability in Graph Neural Networks: A Taxonomic Survey Trustworthy Graph Neural Networks GraphFramEx Colab 5 due
Thu 3/16 19. Conclusion [slides]