Introduction

AutoGL (i.e. Auto Graph Learning) is an automatic machine learning (AutoML) toolkit specified for graph datasets & tasks.

It will automatically handle all the stages involved in graph learning problems, including dataset download & management, data preprocessing and feature engineering, neural architecture search, model selection and training, hyper-parameter tuning and ensemble, which will reduce human labors and biases in the machine learning loop by a large scale. This toolkit also serves as a platform for users to implement and test their own auto or graph learning methods. The workflow below gives the overall framework of AutoGL.

Actively under development by THUMNLab
Feel free to open issues or contact us at autogl@tsinghua.edu.cn if you have any comments or suggestions!

from autogl.datasets import build_dataset_from_name from autogl.solver import AutoNodeClassifier dataset = build_dataset_from_name('cora') autoClassifier = AutoNodeClassifier() autoClassifier.fit(dataset) acc = autoClassifier.evaluate(metric="acc") print("test acc: {:.4f}".format(acc))

Installation

Please first install the requirements of AutoGL and then install with the following command.


Install from pip

pip install autogl

Install from source

git clone https://github.com/THUMNLab/AutoGL
python setup.py install

Requirements
Python >= 3.6.0
PyTorch >= 1.6.0
# Follow PyTorch to install
PyTorch-Geometric >= 1.7.0 or Deep Graph Library (>=0.7.0)
# Follow PyTorch-Geometric to install
# Follow Deep Graph Library to install

Incoming Features

  • Solutions for large-scale graphs
  • More supported algorithms for graph tasks, graph models, and AutoML algorithms
  • Applications of AutoGL in real-world tasks
  • Citations

    Please cite our paper 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},
    }
    You may also find our survey 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}
    }

    Related Links

    Here is our KDD 21 tutorial on Automated Machine Learning on Graph.

    Slides >

    Contact Us

    Please contact us through autogl@tsinghua.edu.cn or xin_wang@tsinghua.edu.cn

    Send E-mail >

    Github

    Visit our github to get access to codes and ask questions.

    View Github >