A Few Good Counterfactuals: Generating Interpretable, Plausible and Diverse Counterfactual Explanations

TL;DR

This paper introduces a novel method for generating diverse, plausible, and sparse counterfactual explanations by adapting native data points, addressing limitations of previous synthetic counterfactual generation techniques.

Contribution

The paper presents a new approach that leverages native dataset features to produce more valid, sparse, and diverse counterfactual explanations for XAI.

Findings

The method improves validity of counterfactuals by using naturally occurring features.

It enhances diversity and sparsity compared to traditional perturbation methods.

Experimental results identify optimal parameter settings for different datasets.

Abstract

Counterfactual explanations provide a potentially significant solution to the Explainable AI (XAI) problem, but good, native counterfactuals have been shown to rarely occur in most datasets. Hence, the most popular methods generate synthetic counterfactuals using blind perturbation. However, such methods have several shortcomings: the resulting counterfactuals (i) may not be valid data-points (they often use features that do not naturally occur), (ii) may lack the sparsity of good counterfactuals (if they modify too many features), and (iii) may lack diversity (if the generated counterfactuals are minimal variants of one another). We describe a method designed to overcome these problems, one that adapts native counterfactuals in the original dataset, to generate sparse, diverse synthetic counterfactuals from naturally occurring features. A series of experiments are reported that systematically explore parametric variations of this novel method on common datasets to establish the conditions for optimal performance.