CeFlow: A Robust and Efficient Counterfactual Explanation Framework for Tabular Data using Normalizing Flows
This work addresses efficiency and robustness issues in counterfactual explanations for tabular data, which is important for interpretable machine learning in interactive environments, though it appears incremental as it builds on existing methods.
The authors tackled the slow and unstable counterfactual generation in tabular data by proposing CeFlow, a framework using normalizing flows, which achieved favorable performance compared to state-of-the-art methods in numerical experiments.
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.