PGExplainer

This is a Tensorflow implementation of the paper: Parameterized Explainer for Graph Neural Network

https://arxiv.org/abs/2011.04573

NeurIPS 2020

Requirements

• Python 3.6.8
• tensorflow 2.0
• networkx

References

@article{luo2020parameterized,
  title={Parameterized Explainer for Graph Neural Network},
  author={Luo, Dongsheng and Cheng, Wei and Xu, Dongkuan and Yu, Wenchao and Zong, Bo and Chen, Haifeng and Zhang, Xiang},
  journal={Advances in Neural Information Processing Systems},
  volume={33},
  year={2020}
}

Pytorch Implementation

Here are several re-implementations and reproduction reports from other groups. Thanks very much these researchers for re-implementing PGExplainer to make it more easy to use!

1. [Re] Parameterized Explainer for Graph Neural Network

https://zenodo.org/record/4834242/files/article.pdf

Code:

https://github.com/LarsHoldijk/RE-ParameterizedExplainerForGraphNeuralNetworks

Note that in this report, they adopt different GCN models with our implementation.

2. Reproducing: Parameterized Explainer for Graph NeuralNetwork

https://openreview.net/forum?id=tt04glo-VrT

Code:

https://openreview.net/attachment?id=tt04glo-VrT&name=supplementary_material

3. DIG

https://github.com/divelab/DIG/tree/main/dig/xgraph/PGExplainer