Share your thoughts, 1 month free Claude Pro on usSee more
WorkDL logo mark

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

About

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.

Tri Dung Duong, Qian Li, Guandong Xu• 2023

Related benchmarks

TaskDatasetResultRank
Counterfactual ExplanationsCOMPAS
Validity38.5
21
Counterfactual Explanationsmoons
Validity99.1
19
Counterfactual ExplanationsHELOC
Validity54.2
19
Counterfactual Explanation PlausibilitySpirals
LOF Score1.25
5
Counterfactual Explanationschessboard
Cost0.804
5
Counterfactual ExplanationsSpirals
Cost0.895
5
Counterfactual Explanationsblood
Cost1.556
5
Counterfactual ExplanationAdult
Cost3.959
5
Counterfactual Explanationscircles
Cost1.195
5
Showing 9 of 9 rows

Other info

Follow for update