Skip to content
All tags

#cs224w

20 posts

Stanford CS224W Lecture 1: Introduction: Why Relational Data Needs Graph Machine Learning

A slide-grounded reconstruction of Fall 2025 Lecture 1, covering Course map and tools, A common language for graph data, Hand-designed features and representation learning while documenting the classroom material unavailable to self-learners.

Stanford CS224W Lecture 2: Node Embeddings: From Random Walks to node2vec

A slide-grounded reconstruction of Fall 2025 Lecture 2, covering Encoder-decoder view, Similarity and the objective, Random walks while documenting the classroom material unavailable to self-learners.

Stanford CS224W Lecture 3: Graph Neural Networks: A First Complete Message-Passing Model

A slide-grounded reconstruction of Fall 2025 Lecture 3, covering From fixed embeddings to deep encoders, The message-passing framework, Aggregation and update while documenting the classroom material unavailable to self-learners.

Stanford CS224W Lecture 4: A General Perspective on GNNs: Turning a Model into Design Components

A slide-grounded reconstruction of Fall 2025 Lecture 4, covering The GNN design space, Message, aggregation, and update, GraphSAGE while documenting the classroom material unavailable to self-learners.

Stanford CS224W Lecture 5: GNN Augmentation and Training: Co-designing Data, Tasks, and Models

A slide-grounded reconstruction of Fall 2025 Lecture 5, covering Graph-data augmentation, Feature and structural augmentation, Supervision and loss while documenting the classroom material unavailable to self-learners.

Stanford CS224W Lecture 6: Theory of GNNs: The WL Test, GIN, and Expressive Limits

A Fall 2025 slide-grounded reconstruction of Lecture 6, covering What distinguishability means, The Weisfeiler–Lehman test, An upper bound for message passing while documenting unavailable classroom material.

Stanford CS224W Lecture 7: Designing Powerful Graph Encoders: Structural and Positional Awareness

A Fall 2025 slide-grounded reconstruction of Lecture 7, covering The perfect-GNN thought experiment, Three levels of standard-GNN failure, Identity-aware encoding while documenting unavailable classroom material.

Stanford CS224W Lecture 8: Graph Transformers: Connecting Attention to Graph Structure

A Fall 2025 slide-grounded reconstruction of Lecture 8, covering Self-attention and message passing, The scope of graph attention, Positional and structural encodings while documenting unavailable classroom material.

Stanford CS224W Lecture 9: Heterogenous Graphs: Adding Node and Relation Types to Message Passing

A Fall 2025 slide-grounded reconstruction of Lecture 9, covering Heterogeneous graph schemas, Relation-specific messages, R-GCN while documenting unavailable classroom material.

Stanford CS224W Lecture 10: Knowledge Graphs: Modeling Relations with TransE, ComplEx, and RotatE

A Fall 2025 slide-grounded reconstruction of Lecture 10, covering Knowledge graphs and completion, Triple scoring, TransE and relation patterns while documenting unavailable classroom material.

Stanford CS224W Lecture 11: GNNs for Recommender Systems: From Collaborative Filtering to LightGCN

A Fall 2025 slide-grounded reconstruction of Lecture 11, covering Graph formulation of recommendation, The matrix-factorization baseline, Message passing in NGCF while documenting the public-material boundary.

Stanford CS224W Lecture 12: Relational Deep Learning: Turning Databases Directly into Prediction Graphs

A Fall 2025 slide-grounded reconstruction of Lecture 12, covering Limits of the tabular pipeline, Mapping relational databases to graphs, Temporal entity graphs while documenting the public-material boundary.

Stanford CS224W Lecture 13: Advanced Architectures in RDL: RelGNN and the Relational Graph Transformer

A Fall 2025 slide-grounded reconstruction of Lecture 13, covering The multi-relational bottleneck, RelGNN composite message passing, Relation-specific aggregation while documenting the public-material boundary.

Stanford CS224W Lecture 14: Advanced Topics in GNNs: In-Context Learning and Uncertainty on Graphs

A Fall 2025 slide-grounded reconstruction of Lecture 14, covering The goal of relational foundation models, Zero-shot relational transfer, PRODIGY's prompt graph while documenting the public-material boundary.

Stanford CS224W Lecture 15: Foundation Models for Knowledge Graphs: New Entities, New Relations, and Double Equivariance

A Fall 2025 slide-grounded reconstruction of Lecture 15, covering Limits of transductive KG embeddings, Entity-inductive link prediction, The relation graph while documenting the public-material boundary.

Stanford CS224W Lecture 16: LLM + GNN: Letting Language Models Read Graphs and Graph Models Read Text

A Fall 2025 slide-grounded reconstruction of Lecture 16, covering Complementary gaps in LLMs and GNNs, Text-attributed graphs, The LLM as predictor or encoder while documenting the public-material boundary.

Stanford CS224W Lecture 17: Agents + Graphs: Retrieval, Planning, and Action in Structured Worlds

A Fall 2025 slide-grounded reconstruction of Lecture 17, covering From graph QA to agents, Multimodal retrieval in STaRK, Tool use and traversal while documenting the public-material boundary.

Stanford CS224W Lecture 18: Deep Generative Models for Graphs: GraphRNN and Goal-Directed Molecular Generation

A Fall 2025 slide-grounded reconstruction of Lecture 18, covering The graph-generation problem and representation, Evaluating generation quality, GraphRNN's autoregressive factorization while documenting the public-material boundary.

Stanford CS224W Lecture 19: Ranking 315K GNN Designs with Anchor Models

The Fall 2025 conclusion studies roughly 315K GNN designs across 32 tasks: run a small set of anchor models, derive task similarity from rankings, and transfer the best designs from similar tasks.

Stanford CS224W: Every Assignment Runs in Colab, but the Biggest Slice of the Grade Is Closed to Self-Learners

All six CS224W Colabs download and run today, and the first one needs only NetworkX — no PyG install at all. But the exam is 35% of the grade, the largest single piece, and it's an in-person closed-book sitting. The public recordings stop at 2021 and cover none of the current syllabus's second half: graph transformers, relational deep learning, LLM+GNN.