# RexYing/gnn-model-explainer

gnn explainer

Repository: https://github.com/RexYing/gnn-model-explainer
Canonical: https://ross.abutalabs.com/products/gnn-model-explainer
Language: Python
License: Apache-2.0
License Family: permissive
Last push: 2024-08-30T23:54:01+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": 2811, "days_push": 733, "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 1055, forks 193 (observed 2026-08-28T04:03:24.392543+00:00)

## What it is
Official implementation of GNNExplainer, a NeurIPS 2019 method for explaining predictions of graph neural networks by learning soft masks over edges and node features. It includes training scripts for GCN models, the explainer optimization, and visualization via Tensorboard, Jupyter notebooks, and D3.js export.

## Use cases
- explain predictions of a graph neural network
- identify important edges and node features for a GNN prediction
- replicate GNNExplainer paper experiments
- visualize GNN explanations interactively
- interpret node classification results on graphs
- generate subgraph explanations for GCN models

## When to choose
- you need model-agnostic explanations for PyTorch Geometric-style GCN predictions
- you want to reproduce the original GNNExplainer paper results
- you are researching explainability methods for graph neural networks

## When to avoid
- you need explanations for non-graph models like transformers or CNNs
- you want a maintained production library with broad model support (use PyTorch Geometric's Explainer instead)
- you need GNN explanation for frameworks other than PyTorch

## Facets
- artifact type: library
- maturity: maintenance
- function: machine-learning, deep-learning, data-visualization, interpreter
- domain: machine-learning, deep-learning, graph-processing, data-visualization
- platform: python, cross-platform
- tags: gnn, explainability, graph-neural-networks, interpretability, xai, neurips-2019, research-code, research

## Member repositories
- RexYing/gnn-model-explainer (main) score 32

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:03:24.392543+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 2026-08-30T06:58:28.204816+00:00, confidence not recorded.
  - readme: https://github.com/RexYing/gnn-model-explainer (fetched 2026-08-28T04:03:24.392543+00:00, sha 3d3bfea2951e)
- Data as of 2026-08-30T08:39:29.467469+00:00.