CS224W | Home (original) (raw)
This class will be offered next in Fall 2021.
The first meeting of the class will be on Tuesday September 21 2021.
Content
What is this course about?
Complex data can be represented as a graph of relationships between objects. Such networks are a fundamental tool for modeling social, technological, and biological systems. This course focuses on the computational, algorithmic, and modeling challenges specific to the analysis of massive graphs. By means of studying the underlying graph structure and its features, students are introduced to machine learning techniques and data mining tools apt to reveal insights on a variety of networks.
Topics include: representation learning and Graph Neural Networks; algorithms for the World Wide Web; reasoning over Knowledge Graphs; influence maximization; disease outbreak detection, social network analysis.
Previous Offerings
You can access slides and project reports of previous versions of the course on our archived websites:CS224W: Fall 2019 /CS224W: Fall 2018 /CS224W: Fall 2017 /CS224W: Fall 2016 /CS224W: Fall 2015 /CS224W: Fall 2014 /CS224W: Fall 2013 /CS224W: Fall 2012 /CS224W: Fall 2011 /CS224W: Fall 2010
Prerequisites
Students are expected to have the following background:
- Knowledge of basic computer science principles, sufficient to write a reasonably non-trivial computer program (e.g., CS107 or CS145 or equivalent are recommended)
- Familiarity with the basic probability theory (CS109 or Stat116 are sufficient but not necessary)
- Familiarity with the basic linear algebra (any one of Math 51, Math 103, Math 113, or CS 205 would be much more than necessary)
The recitation sessions in the first weeks of the class will give an overview of the expected background.
Course Materials
Notes and reading assignments will be posted periodically on the course Web site. The following books are recommended as optional reading:
- Graph Representation Learning by William L. Hamilton
- Networks, Crowds, and Markets: Reasoning About a Highly Connected World by David Easley and Jon Kleinberg
- Network Science by Albert-László Barabási
Schedule
Lecture slides will be posted here shortly before each lecture.
This schedule is subject to change. All deadlines are at 11:59pm PT except for project proposal and report (which will be at 12:00pm PT).
| Date | Description | Suggested Readings / Important Notes | Events | Deadlines |
|---|---|---|---|---|
| Tue Jan 12 | 1. Introduction; Machine Learning for Graphs [slides] | |||
| Thu Jan 14 | 2. Traditional Methods for ML on Graphs [slides] | Colab 0, Colab 1 out | ||
| Tue Jan 19 | 3. Node Embeddings [slides] | |||
| Thu Jan 21 | 4. Link Analysis: PageRank [slides] | Homework 1 out | ||
| Tue Jan 26 | 5. Label Propagation for Node Classification [slides] | |||
| Thu Jan 28 | 6. Graph Neural Networks 1: GNN Model [slides] | Colab 2 out | Colab 1 due | |
| Tue Feb 2 | 7. Graph Neural Networks 2: Design Space [slides] | |||
| Thu Feb 4 | 8. Applications of Graph Neural Networks [slides] | Homework 2 out | Homework 1 due | |
| Tue Feb 9 | 9. Theory of Graph Neural Networks [slides] | |||
| Thu Feb 11 | 10. Knowledge Graph Embeddings [slides] | Colab 3 out | Colab 2 due | |
| Tue Feb 16 | 11. Reasoning over Knowledge Graphs [slides] | Project Proposaldue | ||
| Thu Feb 18 | 12. Frequent Subgraph Mining with GNNs [slides] | |||
| Mon Feb 22 | Homework 3 out | Homework 2 due | ||
| Tue Feb 23 | 13. Community Structure in Networks [slides] | |||
| Thu Feb 25 | 14. Traditional Generative Models for Graphs [slides] | Colab 4 out | Colab 3 due | |
| Tue Mar 2 | 15. Deep Generative Models for Graphs [slides] | |||
| Thu Mar 4 | 16. Advanced Topics on GNNs [slides] | Colab 5 out | ||
| Mon Mar 8 | Homework 3 due | |||
| Tue Mar 9 | 17. Scaling Up GNNs [slides] | |||
| Thu Mar 11 | 18. Guest Lecture: GNNs for Computational Biology [slides] | Colab 4 due | ||
| Tue Mar 16 | Bonus Guest Lecture: Industrial Applications of GNNs [slides] | |||
| Thu Mar 18 | 19. GNNs for Science [slides] | |||
| Sun Mar 21 | Project Report due |