Repository files navigation

PyTorch implementation forWhen Does Self-Supervision Help Graph Convolutional Networks?[appendix]

Yuning You^*, Tianlong Chen^*, Zhangyang Wang, Yang Shen

In ICML 2020.

Properly designed multi-task self-supervision benefits GCNs in gaining more generalizability and robustness.In this repository we verify it through performing experiments on several GCN architectures with three designed self-supervised tasks: node clustering, graph partitioning and graph completion.

Please setup the environment following Section 3 (Setup Python environment for GPU) in thisinstruction, and then install the dependencies related to graph partitioning with the following commands:

sudo apt-get install libmetis-devpip install METIS==0.2a.4

• GCN, GAT and GIN with self-supervision
• GMNN and GraphMix with self-supervision
• GCN with self-supervision in adversarial defense

If you use this code for you research, please cite our paper.

@article{you2020does,  title={When Does Self-Supervision Help Graph Convolutional Networks?},  author={You, Yuning and Chen, Tianlong and Wang, Zhangyang and Shen, Yang},  journal={Proceedings of machine learning research},  volume={119},  pages={10871--10880},  year={2020}}