GCExplainer

This repository contains the code for the paper: "GCExplainer: Human-in-the-Loop Concept-based Explanations for Graph Neural Networks" (https://arxiv.org/pdf/2107.11889.pdf)

Citing

If you find this code useful in your research, please consider citing:

@article{magister2021gcexplainer,
  title={GCExplainer: Human-in-the-Loop Concept-based Explanations for Graph Neural Networks},
  author={Magister, Lucie Charlotte and Kazhdan, Dmitry and Singh, Vikash and Li{\`o}, Pietro},
  journal={arXiv preprint arXiv:2107.11889},
  year={2021}
}

Requirements

A requirements file is located in the k_clustering folder. Simply create a virtual envrionment and run pip install -r k_clustering/requirements.txt

Running Instructions

The repository provides a set of Jupyter Notebooks to make replication of the experiments as easy as possible.