A Syllabus for Graph Neural Networks, Served as a README

What it does This repository is a curated study guide — essentially a syllabus rendered as a README — that collects and organizes external resources for learning graph neural networks. It sorts material into progressive stages: gentle introductions, survey papers, deep-dive courses and books, popular implementations, benchmarks, and software tools. The author also promises a tutorial series, though only one PyTorch Geometric notebook is currently linked.

The interesting bit The value is not in any original code but in the sequencing. Most ML subfields suffer from an embarrassment of riches; this repo tries to turn that firehose into a drinkable curriculum by grouping resources by cognitive load rather than by date or citation count.

Key highlights

• Progression from Distill articles and introductory videos up to Stanford’s CS224W and the Graph Representation Learning textbook
• Links to major survey papers and Papers with Code collections for models, datasets, and leaderboards
• Pointers to four active GNN frameworks: PyTorch Geometric, DGL, jraph, and Spektral
• A single runnable Colab tutorial introducing PyTorch Geometric, with more advertised

Caveats

• The guide is explicitly non-exhaustive and currently hosts only one original tutorial
• It is purely a link aggregator; no code, implementations, or hosted content live in the repository itself

Verdict Worth bookmarking if you are a student or practitioner trying to self-study GNNs systematically. Skip it if you are looking for a library, original research, or hands-on code examples beyond a single notebook.