This repository is an attempt to convert the slides from Stanford's "CS224W: Machine Learning with Graphs" course into code. The notebooks presented here include code to implement techniques hinted at in the lectures but not shown in the official labs.

My initial plan was to cover all the lessons but already by the eighth the computation becomes challenging for Colab and I think these first eight are already a great introduction to the subject, I'll stop here.

Disclaimer: I am not a Stanford student and this material has not been reviewed by the course instructors, it is possible that it contains errors, if you find any please open an issue.

A few useful links:

• CS224W | Home
• CS224W | YouTube

1. Introduction; Machine Learning for Graphs
2. Traditional Methods for ML on Graphs
3. Node Embeddings
4. Link Analysis: PageRank
5. Label Propagation for Node Classification
6. Graph Neural Networks 1: GNN Model
7. Graph Neural Networks 2: Design Space
8. Applications of Graph Neural Networks

• Add the link to the Medium article related to the 6th lesson "Graph Neural Networks 1: GNN Model"

• Complete the notebook related to the 8th lesson "Applications of Graph Neural Networks"

• Complete the notebook related to the 7th lesson "Graph Neural Networks 2: Design Space"

• Complete the notebook related to the 6th lesson "Graph Neural Networks 1: GNN Model"
• Add Anaconda env. file

• Complete the notebook related to the 5th lesson "Label Propagation for Node Classification"

• Complete the notebook related to the 4th lesson "Link Analysis: PageRank"

• Complete the notebook related to the 3rd lesson "Node Embeddings"

• Complete the notebook related to the 2nd lesson "Traditional Methods for ML on Graphs"

• Complete the notebook related to the 1st lesson "Introduction; Machine Learning for Graphs"