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. [abs] [ pdf ][ bib ] [ code ] &copy JMLR 2021. ( edit, beta )

Authors

• Meng Liu School of Computer, National University of Defense Technology
• Youzhi Luo Texas A&M University
• Limei Wang
• Yaochen Xie
• Hao Yuan Shenzhen Transsion Holdings CO.,LTD.
• Shurui Gui
• Haiyang Yu Fudan University
• Zhao Xu Fraunhofer IAIS
• Jingtun Zhang
• Yi Liu City University of Hong Kong
• Keqiang Yan
• Haoran Liu Texas A&M University
• Cong Fu
• Bora M Oztekin
• Xuan Zhang Harvest Fund Management Co., Ltd.
• Shuiwang Ji

Keywords

No keywords are indexed for this paper.