CS224W | Home

Logistics

Lectures: are on Tuesday/Thursday 3:00-4:20pm in person in the NVIDIA Auditorium.
Lecture Videos: are available on Canvas for all the enrolled Stanford students.
Public resources: The lecture slides and assignments will be posted online as the course progresses. We are happy for anyone to use these resources, but we cannot grade the work of any students who are not officially enrolled in the class.
Contact: Students should ask all course-related questions on Ed (accessible from Canvas), where you will also find announcements. For external inquiries, personal matters, or in emergencies, you can email us at cs224w-aut2627-staff@lists.stanford.edu.
Academic accommodations: If you need an academic accommodation based on a disability, you should initiate the request with the Office of Accessible Education (OAE). The OAE will evaluate the request, recommend accommodations, and prepare a letter for the teaching staff. Once you receive the letter, send it to our staff email address. Students should contact the OAE as soon as possible since timely notice is needed to coordinate accommodations.
Audit requests: For students applying to audit the course, please submit the request through the online form here.

Instructor

Jure Leskovec

Guest Instructor

Charilaos Kanatsoulis

Course Manager

John Cho

Course Assistants

Hermann Kumbong (Head CA)

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 2025 / CS224W: Fall 2024 / CS224W: Fall 2023 / CS224W: Winter 2023 / CS224W: Fall 2021 / CS224W: Winter 2021 / 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.

Notes are available [here].

This schedule is subject to change. All assignment deadlines are at 11:59pm PT.

Date	Description	Optional Readings	Events	Deadlines
Tue, 9/22	1. Introduction [slides]
Thu, 9/24	2. Node embeddings	DeepWalk: Online Learning of Social Representations node2vec: Scalable Feature Learning for Networks Network Embedding as Matrix Factorization	Colab 0, Colab 1 out
Tue, 9/29	3. Graph neural networks	Geometric Deep Learning: the Erlangen Programme of ML Semi-Supervised Classification with Graph Convolutional Networks
Thu, 10/1	4. A general perspective on GNNs	Design Space of Graph Neural Networks Inductive Representation Learning on Large Graphs Graph Attention Networks	Homework 1 out
Tue, 10/6	5. GNN augmentation and training	Hierarchical Graph Representation Learning with Differentiable Pooling
Thu, 10/8	6. Theory of GNNs	How Powerful Are Graph Neural Networks?	Colab 2 out	Colab 1 due
Tue, 10/13	7. Designing Powerful Graph Encoders	Identity-aware Graph Neural Networks Graph Neural Networks are More Powerful than We Think Counting Graph Substructures with Graph Neural Networks Position-aware Graph Neural Networks
Thu, 10/15	8. Graph Transformers	Learning Efficient Positional Encodings with Graph Neural Networks Do Transformers Really Perform Bad for Graph Representation? Sign and Basis Invariant Networks for Spectral Graph Representation Learning Attending to Graph Transformers	Homework 2 out	Homework 1 due
Tue, 10/20	9. Heterogenous graphs	Modeling Relational Data with Graph Convolutional Networks Heterogeneous Graph Transformer		Project Proposal due
Thu, 10/22	10. Knowledge graphs	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, 10/27	11. GNNs for recommender systems	Neural Graph Collaborative Filtering LightGCN: Simplifying and Powering Graph Convolution Network for Recommendation Graph Convolutional Neural Networks for Web-Scale Recommender Systems
Thu, 10/29	12. Relational Deep Learning	Relational Deep Learning - Graph Representation Learning on Relational Databases RelBench: A Benchmark for Deep Learning on Relational Databases	Homework 3 out	Homework 2 due
Tue, 11/3	DEMOCRACY DAY - NO CLASS
Thu, 11/5	13. Advanced architectures in RDL	RelGNN: Composite Message Passing for Relational Deep Learning Relational Graph Transformer	Colab 4 out	Colab 3 due
Tue, 11/10	14. Advanced topics in GNNs	Relational Transformer: Toward Zero-Shot Foundation Models for Relational Data PRODIGY: Enabling In-context Learning Over Graphs Uncertainty Quantification over Graph with Conformalized Graph Neural Networks		Project Milestone due
Thu, 11/12	15. Towards Foundation Models for Knowledge Graphs	Double Equivariance for Inductive Link Prediction for Both New Nodes and New Relation Types Towards Foundation Models for Knowledge Graph Reasoning InGram: Inductive Knowledge Graph Embedding via Relation Graphs	Colab 5 out	Homework 3 due
Tue, 11/17	16. Frontiers in Graph AI
Wed, 11/18	Exam in-person
Thu, 11/19	17. Frontiers in Graph AI II
Tue, 11/24	BREAK
Thu, 11/26	BREAK
Tue, 12/1	18. Deep generative models for graphs	GraphRNN: Generating Realistic Graphs with Deep Auto-regressive Models Graph Convolutional Policy Network for Goal-Directed Molecular Graph Generation		Colab 4 due
Thu, 12/3	19. Conclusion	Design Space for Graph Neural Networks		Colab 5 due
Thu, 12/10				Project Report due

CS224W: Machine Learning with Graphs

Stanford / Fall 2026