Repository files navigation

May 10, 2022

• Project based on DGL 0.6.1 and higher. See the relevant dependencies defined in the environment yml files (CPU,GPU).
• Updated technical report of the framework onArXiv.
• AddedAQSOL dataset, which is similar to ZINC for graph regression task, but has a real-world measured chemical target.
• Added mathematical datasets -- GraphTheoryProp and CYCLES which are useful to test GNNs on specific theoretical graph properties.
• Fixedissue #57.

Oct 7, 2020

• Repo updated to DGL 0.5.2 and PyTorch 1.6.0. Please update your environment using yml files (CPU,GPU).
• AddedZINC-full dataset (249K molecular graphs) withscripts.

Jun 11, 2020

• Second release of the project. Major updates :
  • Added experimental pipeline for Weisfeiler-Lehman-GNNs operating on dense rank-2 tensors.
  • Added a leaderboard for all datasets.
  • Updated PATTERN dataset.
  • Fixed bug for PATTERN and CLUSTER accuracy.
  • Moved first release to thisbranch.
• New ArXiv's version of thepaper.

Mar 3, 2020

• First release of the project.

Follow these instructions to install the benchmark and setup the environment.

Proceed as follows to download the benchmark datasets.

Use this page to run the codes and reproduce the published results.

Instructions to add a dataset to the benchmark.

Step-by-step directions to add a MP-GCN to the benchmark.

Step-by-step directions to add a WL-GNN to the benchmark.

Full leaderboards coming soon onpaperswithcode.com.

ArXiv's paper

@article{dwivedi2020benchmarkgnns,  title={Benchmarking Graph Neural Networks},  author={Dwivedi, Vijay Prakash and Joshi, Chaitanya K and Luu, Anh Tuan and Laurent, Thomas and Bengio, Yoshua and Bresson, Xavier},  journal={arXiv preprint arXiv:2003.00982},  year={2020}}