dive-into-graphs 0.0.1

DIG: Dive into Graphs is a turnkey library for graph deep learning research.

Documentation | Paper | Benchmarks/Examples

DIG: Dive into Graphs is a turnkey library for graph deep learning research.

Why DIG?

The key difference with current graph deep learning libraries, such as PyTorch Geometric (PyG) and Deep Graph Library (DGL), is that, while PyG and DGL support basic graph deep learning operations, DIG provides a unified testbed for higher level, research-oriented graph deep learning tasks, such as graph generation, self-supervised learning, explainability, and 3D graphs.

If you are working or plan to work on research in graph deep learning, DIG enables you to develop your own methods within our extensible framework, and compare with current baseline methods using common datasets and evaluation metrics without extra efforts.

Overview

It includes unified implementations of data interfaces, common algorithms, and evaluation metrics for several advanced tasks. Our goal is to enable researchers to easily implement and benchmark algorithms. Currently, we consider the following research directions.

• Graph Generation: dig.ggraph
• Self-supervised Learning on Graphs: dig.sslgraph
• Explainability of Graph Neural Networks: dig.xgraph
• Deep Learning on 3D Graphs: dig.threedgraph

Installation

Install from pip (available soon)

The key dependencies of DIG: Dive into Graphs are PyTorch (>=1.6.0), PyTorch Geometric (>=1.6.0), and RDKit.

1. Install PyTorch (>=1.6.0)

$ python -c "import torch; print(torch.__version__)"
>>> 1.6.0

2. Install PyTorch Geometric (>=1.6.0)

$ python -c "import torch_geometric; print(torch_geometric.__version__)"
>>> 1.6.0

3. Install RDKit.

conda install -y -c conda-forge rdkit

4. Install DIG: Dive into Graphs.

pip install dive-into-graphs

After installation, you can check the version. You have successfully installed DIG: Dive into Graphs if no error occurs.

$ python
>>> from dig.version import __version__
>>> print(__version__)

Install from source

If you want to try the latest features that have not been released yet, you can install dig from source.

git clone https://github.com/divelab/DIG.git
cd DIG
pip install .

Usage

For details of all included APIs, please refer to the documentation. We also provide benchmark implementations as examples to use APIs provided in DIG. You can get started with your interested directions by clicking the following links.

• Graph Generation: JT-VAE (coming soon), GraphAF, GraphDF, GraphEBM.
• Self-supervised Learning on Graphs: InfoGraph, GRACE, MVGRL, GraphCL.
• Explainability of Graph Neural Networks: DeepLIFT, GNN-LRP, GNNExplainer, GradCAM, PGExplainer, SubgraphX.
• Deep Learning on 3D Graphs: SchNet, DimeNet++, SphereNet.

Contributing

We welcome any forms of contributions, such as reporting bugs and adding new features. Please refer to our contributing guidelines for details.

Citing DIG

Please cite our paper if you find DIG useful in your work:

@article{liu2021dig,
      title={{DIG}: A Turnkey Library for Diving into Graph Deep Learning Research}, 
      author={Meng Liu and Youzhi Luo and Limei Wang and Yaochen Xie and Hao Yuan and Shurui Gui and Zhao Xu and Haiyang Yu and Jingtun Zhang and Yi Liu and Keqiang Yan and Bora Oztekin and Haoran Liu and Xuan Zhang and Cong Fu and Shuiwang Ji},
      journal={arXiv preprint arXiv:2103.12608},
      year={2021},
}

The Team

DIG: Dive into Graphs is developed by DIVE@TAMU. Contributors are Meng Liu*, Youzhi Luo*, Limei Wang*, Yaochen Xie*, Hao Yuan*, Shurui Gui, Zhao Xu, Haiyang Yu, Jingtun Zhang, Yi Liu, Keqiang Yan, Bora Oztekin, Haoran Liu, Xuan Zhang, Cong Fu, and Shuiwang Ji.

Contact

If you have any technical questions, please submit new issues.

If you have any other questions, please contact us: Meng Liu [[e-mail]] and Shuiwang Ji [[e-mail]].