Counterfactual explanation is the meaningful and minimum perturbation for an input that can alter the original prediction by a machine learning model, usually from an undesirable prediction to a desirable one. In this repo, I plan to reproduce the implementation of C-CHVAE WWW2020 on PyTorch platform. The official implementation works on Tensorflow. Thanks for Martin providing the test file to me which help me understand the algorithms.
@inproceedings{pawelczyk_learning2019,
author = {Pawelczyk, Martin and Broelemann, Klaus and Kasneci, Gjergji},
title = {Learning Model-Agnostic Counterfactual Explanations for Tabular Data},
year = {2020},
publisher = {Association for Computing Machinery},
address = {New York, NY, USA},
booktitle = {Proceedings of The Web Conference 2020},
pages = {3126–3132},
numpages = {7},
keywords = {Transparency, Counterfactual explanations, Interpretability},
location = {Taipei, Taiwan},
series = {WWW '20}
}