%0 Generic %1 liu2021turnkey %A Liu, Meng %A Luo, Youzhi %A Wang, Limei %A Xie, Yaochen %A Yuan, Hao %A Gui, Shurui %A Xu, Zhao %A Yu, Haiyang %A Zhang, Jingtun %A Liu, Yi %A Yan, Keqiang %A Oztekin, Bora %A Liu, Haoran %A Zhang, Xuan %A Fu, Cong %A Ji, Shuiwang %D 2021 %K 2021 deep-learning graph library %T DIG: A Turnkey Library for Diving into Graph Deep Learning Research %U http://arxiv.org/abs/2103.12608 %X 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 research-oriented library that integrates unified and extensible implementations of common graph deep learning algorithms for several advanced 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 and documentations are available at https://github.com/divelab/DIG/.

@misc{liu2021turnkey, abstract = {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 research-oriented library that integrates unified and extensible implementations of common graph deep learning algorithms for several advanced 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 and documentations are available at https://github.com/divelab/DIG/.}, added-at = {2021-04-01T20:49:49.000+0200}, author = {Liu, Meng and Luo, Youzhi and Wang, Limei and Xie, Yaochen and Yuan, Hao and Gui, Shurui and Xu, Zhao and Yu, Haiyang and Zhang, Jingtun and Liu, Yi and Yan, Keqiang and Oztekin, Bora and Liu, Haoran and Zhang, Xuan and Fu, Cong and Ji, Shuiwang}, biburl = {https://www.bibsonomy.org/bibtex/2b0827e6addbfb389e2add9959f02cdfb/analyst}, description = {[2103.12608] DIG: A Turnkey Library for Diving into Graph Deep Learning Research}, interhash = {07a346b47be84ab874ccfe6cd331398e}, intrahash = {b0827e6addbfb389e2add9959f02cdfb}, keywords = {2021 deep-learning graph library}, note = {cite arxiv:2103.12608}, timestamp = {2021-04-01T20:49:49.000+0200}, title = {DIG: A Turnkey Library for Diving into Graph Deep Learning Research}, url = {http://arxiv.org/abs/2103.12608}, year = 2021 }