# FighterLYL/GraphNeuralNetwork

《深入浅出图神经网络：GNN原理解析》配套代码

Repository: https://github.com/FighterLYL/GraphNeuralNetwork
Canonical: https://ross.abutalabs.com/products/graphneuralnetwork
Language: Jupyter Notebook
License Family: other
Topics: gnn, gcn, graph-neural-network
Last push: 2021-02-24T01:55:46+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": 2508, "days_push": 2017, "days_rel": null, "gap_med": null, "n_releases_24m": 0}
- flags: no_releases, no_license
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 1928, forks 472 (observed 2026-08-28T04:05:55.839501+00:00)

## What it is
Companion code repository for the Chinese book '深入浅出图神经网络：GNN原理解析' (Graph Neural Networks: Principles Explained). It contains Jupyter Notebook examples covering GCN node classification, GraphSAGE, graph classification, and graph autoencoders using PyTorch.

## Use cases
- learn graph neural networks from worked examples
- implement GCN node classification on the Cora dataset
- understand GraphSAGE with code
- study graph classification and graph autoencoders
- find companion code for the GNN book

## When to choose
- you are reading the book and want runnable code for each chapter
- you want simple PyTorch-based GNN examples to learn from

## When to avoid
- you need a production GNN framework - use PyTorch Geometric or DGL instead
- you need actively maintained code or official support

## Facets
- artifact type: learning-resource
- maturity: maintenance
- function: machine-learning, deep-learning
- domain: deep-learning, machine-learning, tutorials
- platform: python
- tags: graph-neural-networks, gnn, gcn, graphsage, pytorch, jupyter-notebook, book-companion-code, chinese

## Member repositories
- FighterLYL/GraphNeuralNetwork (main) score 32

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:05:55.839501+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 2026-08-30T03:09:06.245716+00:00, confidence not recorded.
  - readme: https://github.com/FighterLYL/GraphNeuralNetwork (fetched 2026-08-28T04:05:55.839501+00:00, sha 4ef62bbdcc64)
- Data as of 2026-08-30T08:39:29.467469+00:00.