# dair-ai/GNNs-Recipe

🟠 A study guide to learn about Graph Neural Networks (GNNs)

Repository: https://github.com/dair-ai/GNNs-Recipe
Canonical: https://ross.abutalabs.com/products/gnns-recipe
License: CC0-1.0
License Family: permissive
Topics: graph-neural-networks, deep-learning, machine-learning, graph, graph-convolutional-networks
Last push: 2023-01-06T20:15:03+00:00

## Health v2 (maintenance only)
Score: 32/100 (v2, computed 2026-09-03T02:20:16.233290+00:00)
- activity 0, release rhythm 35, longevity 100
- inputs: {"age_days": 1660, "days_push": 1335, "days_rel": null, "gap_med": null, "n_releases_24m": 0}
- flags: no_releases
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 1330, forks 135 (observed 2026-08-28T04:04:24.235868+00:00)

## What it is
A curated study guide (recipe/studysheet) for learning Graph Neural Networks, collecting introductory articles, videos, survey papers, courses, benchmarks, and tools. It is a documentation-style resource rather than executable software.

## Use cases
- learn graph neural networks from scratch
- find survey papers on GNNs
- get a curated list of GNN tutorials and videos
- find graph datasets and benchmarks for GNNs
- keep up to date with GNN research and implementations
- prepare for studying ML with graphs

## When to choose
- you want a concise, curated starting point for learning GNNs
- you need links to courses, books, and survey papers on graph deep learning
- you are a student looking for a structured self-study path

## When to avoid
- you need runnable GNN code or a library - use PyTorch Geometric or DGL instead
- you need an exhaustive or continuously updated reference
- you need production tooling for graph models

## Facets
- artifact type: learning-resource
- maturity: maintenance
- function: machine-learning, deep-learning
- domain: machine-learning, deep-learning, tutorials
- platform: cross-platform
- tags: graph-neural-networks, study-guide, gnn, graph-convolutional-networks, curated-links

## Member repositories
- dair-ai/GNNs-Recipe (main) score 32

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:04:24.235868+00:00.
- Health v2: computed from the inputs above; adoption is never an input.
- Inferred fields (summary, facets, guidance): AI-extracted, prompt v1, taxonomy v1, on 2026-08-30T04:45:30.719843+00:00, confidence not recorded.
  - readme: https://github.com/dair-ai/GNNs-Recipe (fetched 2026-08-28T04:04:24.235868+00:00, sha 8fb7914bf044)
- Data as of 2026-08-30T08:39:29.467469+00:00.