poipoipoi233 / ProtGNN

Official implementation of AAAI'22 paper "ProtGNN: Towards Self-Explaining Graph Neural Networks"

ProtGNN

Official implementation of AAAI'22 paper "ProtGNN: Towards Self-Explaining Graph Neural Networks" (https://arxiv.org/abs/2112.00911)

The code is based on the Pytorch implementation of [[DIG]](https://github.com/divelab/DIG)

Requirements

pytorch                   1.8.0             
torch-geometric           2.0.2

Usage

• Download the required dataset to ./datasets The hyper-parameters can be set in ./Configures.py

You can run ProtGNN by

python -m models.train_gnns

Cite

If you find this repo to be useful, please cite our paper. Thank you.

@article{zhang2021protgnn,
  title={ProtGNN: Towards Self-Explaining Graph Neural Networks},
  author={Zhang, Zaixi and Liu, Qi and Wang, Hao and Lu, Chengqiang and Lee, Cheekong},
  journal={arXiv preprint arXiv:2112.00911},
  year={2021}
}