# weihua916/powerful-gnns

How Powerful are Graph Neural Networks?

Repository: https://github.com/weihua916/powerful-gnns
Canonical: https://ross.abutalabs.com/products/powerful-gnns
Language: Python
License: MIT
License Family: permissive
Topics: deep-learning, graph-neural-networks, graph-convolutional-neural-networks
Last push: 2021-07-01T16:45:36+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": 2807, "days_push": 1889, "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 1285, forks 227 (observed 2026-08-28T04:04:14.672091+00:00)

## What it is
Official PyTorch implementation of the experiments from the ICLR 2019 paper 'How Powerful are Graph Neural Networks?', introducing the Graph Isomorphism Network (GIN). It provides training and evaluation code for GIN on graph classification benchmarks using the paper's cross-validation protocol.

## Use cases
- implement a graph isomorphism network in pytorch
- reproduce the GIN paper experiments
- run graph neural network graph classification on benchmark datasets
- study the reference code behind a foundational GNN theory paper
- get GIN baseline code for GNN research

## When to choose
- You need the exact reference implementation of GIN to cite or reproduce the ICLR 2019 results
- You want to understand the algorithm from 'How Powerful are Graph Neural Networks?' by reading its official code
- You need a GIN baseline for graph classification experiments

## When to avoid
- You need a maintained, general-purpose GNN framework with many models and active support
- You require compatibility with recent PyTorch versions, since the code was tested on PyTorch 0.4.1 and 1.0.0
- You want a plug-and-play library rather than research experiment code with manual hyperparameter tuning

## Facets
- artifact type: library
- maturity: maintenance
- function: deep-learning, machine-learning
- domain: deep-learning, machine-learning, graph-processing
- platform: python
- tags: graph-neural-networks, gin, graph-isomorphism-network, pytorch, graph-classification, paper-implementation, iclr-2019, research-code

## Member repositories
- weihua916/powerful-gnns (main) score 32

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:04:14.672091+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 2026-08-30T04:56:41.725300+00:00, confidence not recorded.
  - readme: https://github.com/weihua916/powerful-gnns (fetched 2026-08-28T04:04:14.672091+00:00, sha f146538129c1)
- Data as of 2026-08-30T08:39:29.467469+00:00.