# THUMNLab/AutoGL

An autoML framework & toolkit for machine learning on graphs.

Repository: https://github.com/THUMNLab/AutoGL
Canonical: https://ross.abutalabs.com/products/autogl
Homepage: http://mn.cs.tsinghua.edu.cn/AutoGL/
Language: Python
License: Apache-2.0
License Family: permissive
Topics: graph-neural-networks, automl, pytorch, pytorch-geometric, hyper-parameter-optimization, machine-learning, deep-learning, neural-architecture-search
Last push: 2025-11-20T02:46:56+00:00

## Health v2 (maintenance only)
Score: 47/100 (v2, computed 2026-09-02T17:46:02.011165+00:00)
- activity 53, release rhythm 8, longevity 100
- inputs: {"age_days": 2102, "days_push": 286, "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 1140, forks 125 (observed 2026-08-28T04:03:44.392319+00:00)

## What it is
AutoGL is an autoML framework and toolkit for machine learning on graphs, built on PyTorch with PyTorch Geometric and DGL backends. It provides automated feature engineering, model selection, neural architecture search, hyperparameter optimization, and ensembling for graph tasks like node classification, link prediction, and graph classification.

## Use cases
- automatically train GNNs on graph datasets without manual tuning
- run neural architecture search for graph neural networks
- hyperparameter optimization for node classification on Cora
- automated link prediction on graph data
- benchmark graph NAS algorithms with NAS-Bench-Graph
- apply robust or self-supervised graph learning automatically

## When to choose
- you need automated graph ML pipelines with minimal manual configuration
- you want NAS or HPO specifically for graph neural networks
- you work with PyTorch Geometric or DGL datasets and want AutoML on top

## When to avoid
- you need a lightweight, fully manual GNN training loop
- your data is not graph-structured
- you need non-PyTorch frameworks like TensorFlow

## Facets
- artifact type: framework
- maturity: active
- function: machine-learning, deep-learning, llm-training
- domain: machine-learning, graph-processing, artificial-intelligence
- platform: python
- tags: automl, graph-neural-networks, neural-architecture-search, hyperparameter-optimization, pytorch-geometric, dgl, gpu

## Member repositories
- THUMNLab/AutoGL (main) score 47

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:03:44.392319+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 2026-08-30T06:35:26.822805+00:00, confidence not recorded.
  - readme: https://github.com/THUMNLab/AutoGL (fetched 2026-08-28T04:03:44.392319+00:00, sha 92f8ad43f6e2)
  - homepage: http://mn.cs.tsinghua.edu.cn/AutoGL/ (fetched 2026-08-29T12:40:45.676129+00:00, sha 6ba62f3303cf)
  - site_page: https://mn.cs.tsinghua.edu.cn/AutoGL/docfile/tutorial/t_quickstart.html (fetched 2026-08-29T12:40:45.678715+00:00, sha 4c02138a4749)
  - site_page: https://mn.cs.tsinghua.edu.cn/AutoGL/docfile/tutorial_cn/t_quickstart.html (fetched 2026-08-29T12:40:45.681215+00:00, sha 8280ea8b5dbf)
  - site_page: https://mn.cs.tsinghua.edu.cn/AutoGL/docfile/documentation/data.html (fetched 2026-08-29T12:40:45.683578+00:00, sha 08dfe7e1d4d8)
  - site_page: https://mn.cs.tsinghua.edu.cn/AutoGL/docfile/documentation/dataset.html (fetched 2026-08-29T12:40:45.685475+00:00, sha 5ddc9eaed53e)
  - site_page: https://mn.cs.tsinghua.edu.cn/AutoGL/docfile/documentation/feature.html (fetched 2026-08-29T12:40:45.687162+00:00, sha dc74dc6fb712)
  - site_page: https://mn.cs.tsinghua.edu.cn/AutoGL/docfile/documentation/model.html (fetched 2026-08-29T12:40:45.689049+00:00, sha 6049b741c96c)
  - site_page: https://mn.cs.tsinghua.edu.cn/AutoGL/docfile/documentation/train.html (fetched 2026-08-29T12:40:45.690767+00:00, sha 1ea6eede311f)
  - site_page: https://mn.cs.tsinghua.edu.cn/AutoGL/docfile/documentation/hpo.html (fetched 2026-08-29T12:40:45.693181+00:00, sha 5c3c0bcb9b37)
- Data as of 2026-08-30T08:39:29.467469+00:00.