Stanford AI Course Map 中文 GitHub ↗
← Back to the course map
Stanford · 2026—27 CS 224W Foundations ★★★☆☆

Core course · Foundations

Machine Learning with Graphs

中文:图机器学习

Graph machine learning: GNNs, knowledge graphs, and influence maximization — turning relational data into learnable representations.

Draft translation: official facts are checked; wording may change after native review.

3–4 units Autumn 2026 Letter or Credit/No Credit ★★★☆☆
GraphsGNNRepresentation learning

Course positioning

Taught by Jure Leskovec, CS 224W is one of the most popular courses on graph neural networks. It covers graph structure analysis, node/graph representation learning, GNNs, knowledge-graph reasoning, propagation and influence, with applications in social networks, recommendation, biological networks, and fraud detection.

What it covers

  1. Graph basics: centrality, community detection, power laws, graph generation
  2. Node embeddings: DeepWalk, node2vec, matrix factorization
  3. GNNs: GCN, GraphSAGE, GAT, message passing
  4. Knowledge graphs: TransE, RotatE, querying and reasoning
  5. Propagation and influence: independent cascade, linear threshold, influence maximization
  6. Graph generation and self-supervision: graph contrastive learning, diffusion
  7. Project: usually prediction/analysis on real graph data

Prerequisites

CS 109; one introductory machine learning course.

Assessment & workload

Assignments plus a project; programming is mainly PyTorch/PyG. Check the current syllabus for details.

Who it's for

Social networks, recommendation, risk control, biological networks, and knowledge graphs; anyone who wants to model non-Euclidean data.

Study advice

Understand the message-passing paradigm before learning GNN variants. The project can build on CS 246's large-scale data methods.

Related courses

Official course description

Many complex data can be represented as a graph of relationships between objects. Such networks are a fundamental tool for modeling complex 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. Prerequisites: CS109, any introductory course in Machine Learning.