# stellargraph/stellargraph

StellarGraph - Machine Learning on Graphs

Repository: https://github.com/stellargraph/stellargraph
Canonical: https://ross.abutalabs.com/products/stellargraph
Homepage: https://stellargraph.readthedocs.io/
Language: Python
License: Apache-2.0
License Family: permissive
Topics: graphs, machine-learning, machine-learning-algorithms, graph-convolutional-networks, networkx, geometric-deep-learning, saliency-map, interpretability, heterogeneous-networks, graph-neural-networks, graph-analysis, graph-machine-learning, gcn, link-prediction, stellargraph-library, graph-data, python, deep-learning, data-science
Last push: 2024-04-10T12:25:23+00:00

## Health v2 (maintenance only)
Score: 23/100 (v2, computed 2026-09-02T17:46:02.011165+00:00)
- activity 0, release rhythm 8, longevity 100
- inputs: {"age_days": 3064, "days_push": 875, "days_rel": null, "gap_med": null, "n_releases_24m": 0}
- flags: none
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 3060, forks 443 (observed 2026-08-28T04:07:41.124309+00:00)

## What it is
StellarGraph is a Python library for machine learning on graphs and networks, offering state-of-the-art graph neural network algorithms such as GCN, GraphSAGE, and heterogeneous graph models. It supports node classification, link prediction, graph classification, and representation learning on graph-structured data.

## Use cases
- classify nodes in a graph with graph neural networks
- predict missing links in a network
- learn node embeddings for downstream machine learning
- run machine learning on heterogeneous graphs
- train a GCN on graph-structured data
- visualize graph embeddings
- graph classification with deep learning

## When to choose
- you need graph machine learning algorithms in Python with a Keras/TensorFlow backend
- you work with heterogeneous graphs or attributed networks
- you want node classification, link prediction, or graph embeddings out of the box
- your data is already in NetworkX or pandas graph form

## When to avoid
- you need a PyTorch-based GNN library (consider PyTorch Geometric or DGL instead)
- you need actively developed features - the project is in maintenance mode
- your data is not graph-structured
- you need very large-scale distributed graph training

## Facets
- artifact type: library
- maturity: maintenance
- function: machine-learning, deep-learning, data-science
- domain: machine-learning, deep-learning, data-science, graph-processing
- platform: python
- tags: graph-neural-networks, gcn, link-prediction, node-classification, heterogeneous-graphs, graph-embeddings, networkx, tensorflow

## Member repositories
- stellargraph/stellargraph (main) score 23

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:07:41.124309+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 2026-08-30T07:28:26.427091+00:00, confidence not recorded.
  - readme: https://github.com/stellargraph/stellargraph (fetched 2026-08-28T04:07:41.124309+00:00, sha 7bee0917c51f)
  - registry_pypi: https://pypi.org/pypi/stellargraph/json (fetched 2026-08-29T09:44:11.807290+00:00, sha a3af2d643bdd)
- Data as of 2026-08-30T08:39:29.467469+00:00.