Graph-structured data, network analysis, and learning on relational data.
- Stanford CS224W: Machine Learning with Graphs - The comprehensive course on graph ML from Stanford with videos and assignments.
Intermediate - Petar Velickovic: Theoretical Foundations of GNNs - Deep dive into GNN theory by a leading Cambridge/DeepMind researcher.
Advanced - DeepFindr: GNN Tutorials (YouTube) - Practical GNN video tutorials with code walkthroughs.
Beginner
- Graph Representation Learning Book (Hamilton) - Free comprehensive textbook on graph neural networks.
Intermediate - Geometric Deep Learning: Grids, Groups, Graphs (Bronstein et al.) - Free book and course on the geometric foundations of deep learning.
Advanced - A Gentle Introduction to GNNs (Distill) - Beautiful, interactive explanation of how GNNs work.
Beginner
- PyTorch Geometric (PyG) - Leading GNN library with extensive tutorials and examples.
Intermediate - Deep Graph Library (DGL) - Flexible GNN framework with great getting-started tutorials.
Intermediate - NetworkX Documentation - Python library for graph analysis — good foundation before GNNs.
Beginner - OGB: Open Graph Benchmark - Standardized benchmarks for evaluating graph ML methods.
Intermediate - GraphGym - Platform for designing and evaluating GNN architectures.
Advanced