Repository files navigation

Documentation |Paper [JMLR] |Tutorials |Benchmarks |Examples |Colab Demo |slack community:fire:

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

🔥Update (2022/07): We have upgraded our DIG library based on PyG 2.0.0. We recommend installing our latest version.

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, 3D graphs, and graph out-of-distribution.

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 effort.

It includes unified implementations ofdata interfaces,common algorithms, andevaluation 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
• Graph OOD:dig.oodgraph
• Graph Augmentation:dig.auggraph
• Fair Graph Learning:dig.fairgraph

Example: a few lines of code to runSphereNet onQM9 to incorporate 3D information of molecules.

fromdig.threedgraph.datasetimportQM93Dfromdig.threedgraph.methodimportSphereNetfromdig.threedgraph.evaluationimportThreeDEvaluatorfromdig.threedgraph.methodimportrun# Load the dataset and splitdataset=QM93D(root='dataset/')target='U0'dataset.data.y=dataset.data[target]split_idx=dataset.get_idx_split(len(dataset.data.y),train_size=110000,valid_size=10000,seed=42)train_dataset,valid_dataset,test_dataset=dataset[split_idx['train']],dataset[split_idx['valid']],dataset[split_idx['test']]# Define model, loss, and evaluationmodel=SphereNet(energy_and_force=False,cutoff=5.0,num_layers=4,hidden_channels=128,out_channels=1,int_emb_size=64,basis_emb_size_dist=8,basis_emb_size_angle=8,basis_emb_size_torsion=8,out_emb_channels=256,num_spherical=3,num_radial=6,envelope_exponent=5,num_before_skip=1,num_after_skip=2,num_output_layers=3)loss_func=torch.nn.L1Loss()evaluation=ThreeDEvaluator()# Train and evaluaterun3d=run()run3d.run(device,train_dataset,valid_dataset,test_dataset,model,loss_func,evaluation,epochs=20,batch_size=32,vt_batch_size=32,lr=0.0005,lr_decay_factor=0.5,lr_decay_step_size=15)

1. For details of all included APIs, please refer to thedocumentation.
2. We provide a hands-on tutorial for each direction to help you to get started withDIG:Graph Generation,Self-supervised Learning on Graphs,Explainability of Graph Neural Networks,Deep Learning on 3D Graphs,Graph OOD (GOOD) datasets.
3. We also provideexamples to use APIs provided inDIG. You can get started with your interested directions by clicking the following links.

• Graph Generation:JT-VAE,GraphAF,GraphDF,GraphEBM.
• Self-supervised Learning on Graphs:InfoGraph,GRACE,MVGRL,GraphCL,LaGraph (v1 supported).
• Explainability of Graph Neural Networks:DeepLIFT,GNN-LRP,FlowX,GNNExplainer,GradCAM,PGExplainer,SubgraphX.
• Deep Learning on 3D Graphs:SchNet,DimeNet++,SphereNet.
• Graph OOD (GOOD) datasets:GOODHIV,GOODPCBA,GOODZINC,GOODCMNIST,GOODMotif,GOODCora,GOODArxiv,GOODCBAS.

The key dependencies of DIG: Dive into Graphs are PyTorch (>=1.10.0), PyTorch Geometric (>=2.0.0), and RDKit.

1. InstallPyTorch (>=1.10.0)

$ python -c"import torch; print(torch.__version__)">>> 1.10.0

2. InstallPyG (>=2.0.0)

$ python -c"import torch_geometric; print(torch_geometric.__version__)">>> 2.0.0

3. 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__)

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.gitcd DIGpip install.

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

Please cite ourpaper if you findDIG useful in your work:

@article{JMLR:v22:21-0343,  author  = {Meng Liu and Youzhi Luo and Limei Wang and Yaochen Xie and Hao Yuan and Shurui Gui and Haiyang Yu and Zhao Xu and Jingtun Zhang and Yi Liu and Keqiang Yan and Haoran Liu and Cong Fu and Bora M Oztekin and Xuan Zhang and Shuiwang Ji},  title   = {{DIG}: A Turnkey Library for Diving into Graph Deep Learning Research},  journal = {Journal of Machine Learning Research},  year    = {2021},  volume  = {22},  number  = {240},  pages   = {1-9},  url     = {http://jmlr.org/papers/v22/21-0343.html}}

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

This work was supported in part by National Science Foundation grants IIS-2006861, IIS-1955189, IIS-1908220, IIS-1908198, DBI-2028361, and DBI-1922969.

If you have any technical questions, please submit new issues or raise it in ourDIG slack community:fire:.

If you have any other questions, please contact us: Meng Liu [mengliu@tamu.edu] and Shuiwang Ji [sji@tamu.edu].