DIG: A Turnkey Library for Diving into Graph Deep Learning Research

Although there exist several libraries for deep learning on graphs, they are aiming at implementing basic operations for graph deep learning. In the research community, implementing and benchmarking various advanced tasks are still painful and time-consuming with existing libraries. To facilitate graph deep learning research, we introduce DIG: Dive into Graphs, a turnkey library that provides a unified testbed for higher level, research-oriented graph deep learning tasks. Currently, we consider graph generation, self-supervised learning on graphs, explainability of graph neural networks, and deep learning on 3D graphs. For each direction, we provide unified implementations of data interfaces, common algorithms, and evaluation metrics. Altogether, DIG is an extensible, open-source, and turnkey library for researchers to develop new methods and effortlessly compare with common baselines using widely used datasets and evaluation metrics. Source code is available at https://github.com/divelab/DIG.

[1]  Stephan Günnemann,et al.  Directional Message Passing for Molecular Graphs , 2020, ICLR.

[2]  Luca Antiga,et al.  Automatic differentiation in PyTorch , 2017 .

[3]  Lingfan Yu,et al.  Deep Graph Library: A Graph-Centric, Highly-Performant Package for Graph Neural Networks. , 2019 .

[4]  Johannes Klicpera,et al.  Fast and Uncertainty-Aware Directional Message Passing for Non-Equilibrium Molecules , 2020, ArXiv.

[5]  Avanti Shrikumar,et al.  Learning Important Features Through Propagating Activation Differences , 2017, ICML.

[6]  Alán Aspuru-Guzik,et al.  Molecular Sets (MOSES): A Benchmarking Platform for Molecular Generation Models , 2018, Frontiers in Pharmacology.

[7]  Weinan Zhang,et al.  GraphAF: a Flow-based Autoregressive Model for Molecular Graph Generation , 2020, ICLR.

[8]  Kaveh Hassani,et al.  Contrastive Multi-View Representation Learning on Graphs , 2020, ICML.

[9]  William L. Hamilton.  Graph Representation Learning , 2020, Synthesis Lectures on Artificial Intelligence and Machine Learning.

[10]  Jian Tang,et al.  InfoGraph: Unsupervised and Semi-supervised Graph-Level Representation Learning via Mutual Information Maximization , 2019, ICLR.

[11]  Pierre Vandergheynst,et al.  Geometric Deep Learning: Going beyond Euclidean data , 2016, IEEE Signal Process. Mag..

[12]  Max Welling,et al.  Semi-Supervised Classification with Graph Convolutional Networks , 2016, ICLR.

[13]  Pavlo O. Dral,et al.  Quantum chemistry structures and properties of 134 kilo molecules , 2014, Scientific Data.

[14]  Heiko Hoffmann,et al.  Explainability Methods for Graph Convolutional Neural Networks , 2019, 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR).

[15]  J. Leskovec,et al.  Open Graph Benchmark: Datasets for Machine Learning on Graphs , 2020, NeurIPS.

[16]  Ruslan Salakhutdinov,et al.  Revisiting Semi-Supervised Learning with Graph Embeddings , 2016, ICML.

[17]  Klaus-Robert Müller,et al.  Machine learning of accurate energy-conserving molecular force fields , 2016, Science Advances.

[18]  Klaus-Robert Müller,et al.  SchNet: A continuous-filter convolutional neural network for modeling quantum interactions , 2017, NIPS.

[19]  Razvan Pascanu,et al.  Interaction Networks for Learning about Objects, Relations and Physics , 2016, NIPS.

[20]  Qiang Liu,et al.  Deep Graph Contrastive Representation Learning , 2020, ArXiv.

[21]  Philip S. Yu,et al.  A Comprehensive Survey on Graph Neural Networks , 2019, IEEE Transactions on Neural Networks and Learning Systems.

[22]  Shuiwang Ji,et al.  GraphDF: A Discrete Flow Model for Molecular Graph Generation , 2021, ICML.

[23]  Zhangyang Wang,et al.  Graph Contrastive Learning with Augmentations , 2020, NeurIPS.

[24]  Suhang Wang,et al.  Self-supervised Learning on Graphs: Deep Insights and New Direction , 2020, ArXiv.

[25]  Shinichi Nakajima,et al.  Higher-Order Explanations of Graph Neural Networks via Relevant Walks , 2020, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[26]  Vijay S. Pande,et al.  MoleculeNet: a benchmark for molecular machine learning , 2017, Chemical science.

[27]  Jure Leskovec,et al.  Learning to Simulate Complex Physics with Graph Networks , 2020, ICML.

[28]  Jure Leskovec,et al.  Representation Learning on Graphs: Methods and Applications , 2017, IEEE Data Eng. Bull..

[29]  Xiaojie Guo,et al.  A Systematic Survey on Deep Generative Models for Graph Generation , 2020, ArXiv.

[30]  Hamid R. Rabiee,et al.  Deep Graph Generators: A Survey , 2020, IEEE Access.

[31]  Regina Barzilay,et al.  Junction Tree Variational Autoencoder for Molecular Graph Generation , 2018, ICML.

[32]  Defferrard Michaël,et al.  Deep Learning on Graphs , 2016 .

[33]  Jure Leskovec,et al.  GNNExplainer: Generating Explanations for Graph Neural Networks , 2019, NeurIPS.

[34]  Shuiwang Ji,et al.  Self-Supervised Learning of Graph Neural Networks: A Unified Review , 2021, ArXiv.

[35]  Razvan Pascanu,et al.  Relational inductive biases, deep learning, and graph networks , 2018, ArXiv.

[36]  Zibin Zheng,et al.  GraphGallery: A Platform for Fast Benchmarking and Easy Development of Graph Neural Networks Based Intelligent Software , 2021, 2021 IEEE/ACM 43rd International Conference on Software Engineering: Companion Proceedings (ICSE-Companion).

[37]  Shuiwang Ji,et al.  Explainability in Graph Neural Networks: A Taxonomic Survey , 2020, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[38]  Chang Zhou,et al.  CogDL: An Extensive Toolkit for Deep Learning on Graphs , 2021, ArXiv.

[39]  Shuiwang Ji,et al.  Advanced Graph and Sequence Neural Networks for Molecular Property Prediction and Drug Discovery. , 2020, Bioinformatics.

[40]  Bo Zong,et al.  Parameterized Explainer for Graph Neural Network , 2020, NeurIPS.

[41]  Kang Li,et al.  On Explainability of Graph Neural Networks via Subgraph Explorations , 2021, International Conference on Machine Learning.

[42]  Meng Liu,et al.  GraphEBM: Molecular Graph Generation with Energy-Based Models , 2021, ArXiv.

[43]  Ryan G. Coleman,et al.  ZINC: A Free Tool to Discover Chemistry for Biology , 2012, J. Chem. Inf. Model..

[44]  Emma J. Chory,et al.  A Deep Learning Approach to Antibiotic Discovery , 2020, Cell.

[45]  Kristian Kersting,et al.  TUDataset: A collection of benchmark datasets for learning with graphs , 2020, ArXiv.

[46]  Jure Leskovec,et al.  Inductive Representation Learning on Large Graphs , 2017, NIPS.

[47]  Pietro Liò,et al.  Graph Attention Networks , 2017, ICLR.

[48]  Shuiwang Ji,et al.  XGNN: Towards Model-Level Explanations of Graph Neural Networks , 2020, KDD.

[49]  Jan Eric Lenssen,et al.  Fast Graph Representation Learning with PyTorch Geometric , 2019, ArXiv.

[50]  Jun Hu,et al.  Efficient Graph Deep Learning in TensorFlow with tf_geometric , 2021, ACM Multimedia.

[51]  Cesare Alippi,et al.  Graph Neural Networks in TensorFlow and Keras with Spektral , 2020, IEEE Comput. Intell. Mag..

[52]  Shuiwang Ji,et al.  Spherical Message Passing for 3D Graph Networks , 2021, ArXiv.

[53]  Zhiyuan Liu,et al.  Graph Neural Networks: A Review of Methods and Applications , 2018, AI Open.

[54]  Samuel S. Schoenholz,et al.  Neural Message Passing for Quantum Chemistry , 2017, ICML.