Ecosyste.ms: Awesome

An open API service indexing awesome lists of open source software.

https://github.com/THUMNLab/AutoGL

An autoML framework & toolkit for machine learning on graphs.
https://github.com/THUMNLab/AutoGL

automl deep-learning graph-neural-networks hyper-parameter-optimization machine-learning neural-architecture-search pytorch pytorch-geometric

Last synced: about 2 months ago
JSON representation

An autoML framework & toolkit for machine learning on graphs.

Lists

README 

        
# Auto Graph Learning



[Chinese Introduction](README_cn.md)



An autoML framework & toolkit for machine learning on graphs.



*Actively under development by @THUMNLab*



Feel free to open issues or contact us at [email protected] if you have any comments or suggestions!



## News!

- 2023.10.29 New version! v0.4.1 is here!

    - We have simplified the dataset module so that users can build their own datasets more easily! 

    - We have developed an extended library: [AutoGL-light](https://github.com/THUMNLab/AutoGL-light), which is a lightweight version of AutoGL. Users can customize their own AutoML pipeline for graphs more easily!

    - Minor bugs fixed.

- 2022.12.30 New version! v0.4.0-pre is here!

    - We have proposed __NAS-Bench-Graph__ ([paper](https://openreview.net/pdf?id=bBff294gqLp), [code](https://github.com/THUMNLab/NAS-Bench-Graph), [tutorial](http://mn.cs.tsinghua.edu.cn/autogl/documentation/docfile/tutorial/t_nas_bench_graph.html)), the first NAS-benchmark for graphs published in NeurIPS'22. By using AutoGL together with NAS-Bench-Graph, the performance estimation process of GraphNAS algorithms can be greatly speeded up. 

    - We have supported the graph __robustness__ algorithms in AutoGL, including graph structure engineering, robust GNNs and robust GraphNAS. See [robustness tutorial](http://mn.cs.tsinghua.edu.cn/autogl/documentation/docfile/tutorial/t_robust.html) for more details.

    - We have supported graph __self-supervised learning__! See [self-supervised learning tutorial](http://mn.cs.tsinghua.edu.cn/autogl/documentation/docfile/tutorial/t_ssl_trainer.html) for more details.

- 2021.12.31 Version v0.3.0-pre is released

    - Support [__Deep Graph Library (DGL)__](https://www.dgl.ai/) backend including homogeneous node classification, link prediction, and graph classification tasks. AutoGL is also compatible with PyG 2.0 now.

    - Support __heterogeneous__ node classification! See [hetero tutorial](http://mn.cs.tsinghua.edu.cn/autogl/documentation/docfile/tutorial/t_hetero_node_clf.html) .

    - The module `model` now supports __decoupled__ to two additional sub-modules named `encoder` and `decoder`. Under the __decoupled__ design, one `encoder` can be used to solve all kinds of tasks.

    - Enrich [NAS algorithms](http://mn.cs.tsinghua.edu.cn/autogl/documentation/docfile/tutorial/t_nas.html) such as [AutoAttend](https://proceedings.mlr.press/v139/guan21a.html), [GASSO](https://proceedings.neurips.cc/paper/2021/hash/8c9f32e03aeb2e3000825c8c875c4edd-Abstract.html), [hardware-aware algorithm](http://mn.cs.tsinghua.edu.cn/autogl/documentation/docfile/documentation/nas.html#autogl.module.nas.estimator.OneShotEstimator_HardwareAware), etc. 

- 2021.07.11 Version 0.2.0-pre is released, which supports [neural architecture search (NAS)](http://mn.cs.tsinghua.edu.cn/autogl/documentation/docfile/tutorial/t_nas.html) to customize architectures, [sampling](http://mn.cs.tsinghua.edu.cn/autogl/documentation/docfile/tutorial/t_trainer.html#node-classification-with-sampling) to perform tasks on large datasets, and link prediction. 

- 2021.04.16 Our survey paper about automated machine learning on graphs is accepted by IJCAI! See more [here](http://arxiv.org/abs/2103.00742).

- 2021.04.10 Our paper [__AutoGL: A Library for Automated Graph Learning__](https://arxiv.org/abs/2104.04987) is accepted by _ICLR 2021 Workshop on Geometrical and Topological Representation Learning_! You can cite our paper following methods [here](#Cite).



## Introduction



AutoGL is developed for researchers and developers to conduct autoML on graph datasets and tasks easily and quickly. See our documentation for detailed information!



The workflow below shows the overall framework of AutoGL.






AutoGL uses `datasets` to maintain datasets for graph-based machine learning, which is based on Dataset in PyTorch Geometric or Deep Graph Library with some functions added to support the auto solver framework.



Different graph-based machine learning tasks are handled by different `AutoGL solvers`, which make use of five main modules to automatically solve given tasks, namely `auto feature engineer`, `neural architecture search`, `auto model`, `hyperparameter optimization`, and `auto ensemble`. 



Currently, the following algorithms are supported in AutoGL:



    

    

        Feature Engineer

        Model

        NAS

        HPO

        Ensemble

    

    

        

        Generators
Graphlets 
 EigenGNN 
 more ...

Selectors
 SeFilterConstant
 gbdt 
 
Graph
 netlsd
 NxAverageClustering
 more ...

        Homo Encoders
 GCNEncoder 
 GATEncoder 
 SAGEEncoder 
 GINEncoder 
 
Decoders
LogSoftmaxDecoder 
 DotProductDecoder 
 SumPoolMLPDecoder 
 JKSumPoolDecoder 

        

        Algorithms


        Random


        RL


        Evolution


        GASSO


        more ...



        Spaces


        SinglePath


        GraphNas


        AutoAttend


        more ...



        Estimators


        Oneshot


        Scratch


        

         Grid 
 Random 
 Anneal 
 Bayes 
 CAMES 
 MOCAMES 
 Quasi random 
 TPE 
 AutoNE 

         Voting 
 Stacking 

    

    



This toolkit also serves as a framework for users to implement and test their own autoML or graph-based machine learning models.



## Installation



### Requirements



Please make sure you meet the following requirements before installing AutoGL.



1. Python >= 3.6.0



2. PyTorch (>=1.6.0)



    see  for installation.



3. Graph Library Backend



    You will need either PyTorch Geometric (PyG) or Deep Graph Library (DGL) as the backend. You can select a backend following [here](http://mn.cs.tsinghua.edu.cn/autogl/documentation/docfile/tutorial/t_backend.html) if you install both.



    3.1 PyTorch Geometric (>=1.7.0)



    See  for installation.



    3.2 Deep Graph Library (>=0.7.0)



    See  for installation.



### Installation



#### Install from pip



Run the following command to install this package through `pip`.



```

pip install autogl

```



#### Install from source



Run the following command to install this package from the source.



```

git clone https://github.com/THUMNLab/AutoGL.git

cd AutoGL

python setup.py install

```



#### Install for development



If you are a developer of the AutoGL project, please use the following command to create a soft link, then you can modify the local package without install them again.



```

pip install -e .

```



## Documentation



Please refer to our documentation to see the detailed documentation.



You can also make the documentation locally. First, please install sphinx and sphinx-rtd-theme:

```

pip install -U Sphinx

pip install sphinx-rtd-theme

```

Then, make an html documentation by:

```

cd docs

make clean && make html

```



The documentation will be automatically generated under `docs/_build/html`



## Cite



Please cite [our paper](https://openreview.net/forum?id=0yHwpLeInDn) as follows if you find our code useful:

```

@inproceedings{guan2021autogl,

  title={Auto{GL}: A Library for Automated Graph Learning},

  author={Chaoyu Guan and Ziwei Zhang and Haoyang Li and Heng Chang and Zeyang Zhang and Yijian Qin and Jiyan Jiang and Xin Wang and Wenwu Zhu},

  booktitle={ICLR 2021 Workshop on Geometrical and Topological Representation Learning},

  year={2021},

  url={https://openreview.net/forum?id=0yHwpLeInDn}

}

```



You may also find our [survey paper](http://arxiv.org/abs/2103.00742) helpful:

```

@article{zhang2021automated,

  title={Automated Machine Learning on Graphs: A Survey},

  author={Zhang, Ziwei and Wang, Xin and Zhu, Wenwu},

  booktitle = {Proceedings of the Thirtieth International Joint Conference on Artificial Intelligence, {IJCAI-21}},

  year={2021},

  note={Survey track}

}

```



## License

We follow [Apache license](LICENSE) across the entire codebase from v0.2.