Introduction to Graph Neural Networks
Chapter 1: Foundations of Graph-Based Learning
What is Graph Data?
Limitations of Standard Neural Networks on Graphs
Common Graph Machine Learning Tasks
Representing Graphs: Adjacency and Feature Matrices
Graph Properties and Measurements
Introduction to the NetworkX Library
Hands-on: Loading and Inspecting a Graph Dataset
Chapter 2: The Message Passing Mechanism
The Neighborhood Aggregation Idea
A General GNN Layer: Aggregate and Update
Common Aggregation Functions
Update Functions and Non-Linearities
Permutation Invariance and Equivariance
Stacking Layers to Form a Deep GNN
Practice: A Simple GNN Layer with NumPy
Chapter 3: Foundational GNN Architectures
Graph Convolutional Networks (GCN)
A Spatial Interpretation of Graph Convolutions
GraphSAGE: Sampling and Aggregating Neighborhoods
Inductive Learning with GraphSAGE
Graph Attention Networks (GAT)
The Attention Mechanism in GATs
Comparing GCN, GraphSAGE, and GAT
Hands-on: Implementing a GCN from Scratch
Chapter 4: Training GNN Models
Setting up a GNN for Node Classification
Loss Functions for Graph Tasks
The Training Loop for GNNs
Data Splitting in Graphs: Transductive vs. Inductive
Evaluation Metrics for Node Classification
Overfitting and Regularization in GNNs
Practice: Training and Evaluating your GCN
Chapter 5: GNN Implementation with PyTorch Geometric
Introduction to PyTorch Geometric (PyG)
The PyG Data Object
Working with PyG Datasets
Building Models with PyG GNN Layers
Mini-Batching for Large Graphs
A Complete Training Script in PyG
Hands-on: Node Classification on the Cora Dataset with PyG
A General GNN Layer: Aggregate and Update
Was this section helpful?
- Neural Message Passing for Quantum Chemistry, Justin Gilmer, Samuel S. Schoenholz, Patrick F. Riley, Oriol Vinyals, George E. Dahl, 2017 Proceedings of the 34th International Conference on Machine Learning (ICML), Vol. 70 (PMLR (Proceedings of Machine Learning Research)) DOI: 10.5555/3305890.3306020 - Introduces the general "Message Passing Neural Network" (MPNN) framework, which formalizes the aggregate-update mechanism for various graph neural network variants.
- Semi-Supervised Classification with Graph Convolutional Networks, Thomas N. Kipf, Max Welling, 2017 International Conference on Learning Representations (ICLR) DOI: 10.48550/arXiv.1609.02907 - A foundational paper introducing Graph Convolutional Networks (GCNs), which exemplify the aggregate-update mechanism in a widely adopted GNN model.
- Inductive Representation Learning on Large Graphs, William L. Hamilton, Rex Ying, Jure Leskovec, 2017 Advances in Neural Information Processing Systems, Vol. 30 (NeurIPS) DOI: 10.5555/3295222.3295267 - Introduces GraphSAGE, explicitly exploring different neighborhood aggregation functions (mean, LSTM, pooling) and demonstrating the inductive capabilities of the message passing framework.
- Relational inductive biases, deep learning, and graph networks, Peter W. Battaglia, Jessica B. Hamrick, Victor Bapst, Alvaro Sanchez-Gonzalez, Vinicius Zambaldi, Mateusz Malinowski, Andrea Tacchetti, David Raposo, Adam Santoro, Ryan Faulkner, Caglar Gulcehre, Francis Song, Andrew Ballard, Justin Gilmer, George Dahl, Ashish Vaswani, Kelsey Allen, Charles Nash, Victoria Langston, Chris Dyer, Nicolas Heess, Daan Wierstra, Pushmeet Kohli, Matt Botvinick, Oriol Vinyals, Yujia Li, Razvan Pascanu, 2018 arXiv preprint arXiv:1806.01261 DOI: 10.48550/arXiv.1806.01261 - Presents a unified conceptual framework for "Graph Networks" that generalizes many graph neural network approaches, including the message passing mechanism, by focusing on object, relation, and global attributes.