chester-w-xie / PGCL

The code of “Prototypical Graph Contrastive Learning”. [TNNLS 2022]

Geek Repo:Geek Repo

Github PK Tool:Github PK Tool

Prototypical Graph Contrastive Learning

Code to be further cleaned...

This repo contains the code of the following paper:

Prototypical Graph Contrastive Learning

Shuai Lin, Pan Zhou, Zi-Yuan Hu, Shuojia Wang, Ruihui Zhao, Yefeng Zheng, Liang Lin, Eric Xing, Xiaodan Liang.
IEEE Transactions on Neural Networks and Learning Systems. (TNNLS 2022)

Experiments

  • Unsupervised representation learning
  • Transfer learning

Please refer to the README.md for the dependencies and training (evaluation) in each directory.

Acknowledgements

  1. We thank GraphCL for their released code (https://github.com/Shen-Lab/GraphCL).
  2. The code regarding clustering consistency is partially referenced from SwaV (https://github.com/facebookresearch/swav).

Cite

Please cite our paper if you use this code in your own work:

@article{lin2022prototypical,
  title={Prototypical graph contrastive learning},
  author={Lin, Shuai and Liu, Chen and Zhou, Pan and Hu, Zi-Yuan and Wang, Shuojia and Zhao, Ruihui and Zheng, Yefeng and Lin, Liang and Xing, Eric and Liang, Xiaodan},
  journal={IEEE Transactions on Neural Networks and Learning Systems},
  year={2022},
  publisher={IEEE}
}

About

The code of “Prototypical Graph Contrastive Learning”. [TNNLS 2022]

License:MIT License


Languages

Language:Python 98.6%Language:Shell 1.4%