English

CeFlow: A Robust and Efficient Counterfactual Explanation Framework for Tabular Data using Normalizing Flows

Machine Learning 2023-03-28 v1 Artificial Intelligence

Abstract

Counterfactual explanation is a form of interpretable machine learning that generates perturbations on a sample to achieve the desired outcome. The generated samples can act as instructions to guide end users on how to observe the desired results by altering samples. Although state-of-the-art counterfactual explanation methods are proposed to use variational autoencoder (VAE) to achieve promising improvements, they suffer from two major limitations: 1) the counterfactuals generation is prohibitively slow, which prevents algorithms from being deployed in interactive environments; 2) the counterfactual explanation algorithms produce unstable results due to the randomness in the sampling procedure of variational autoencoder. In this work, to address the above limitations, we design a robust and efficient counterfactual explanation framework, namely CeFlow, which utilizes normalizing flows for the mixed-type of continuous and categorical features. Numerical experiments demonstrate that our technique compares favorably to state-of-the-art methods. We release our source at https://github.com/tridungduong16/fairCE.git for reproducing the results.

Keywords

Cite

@article{arxiv.2303.14668,
  title  = {CeFlow: A Robust and Efficient Counterfactual Explanation Framework for Tabular Data using Normalizing Flows},
  author = {Tri Dung Duong and Qian Li and Guandong Xu},
  journal= {arXiv preprint arXiv:2303.14668},
  year   = {2023}
}
R2 v1 2026-06-28T09:34:02.472Z