Finding Regions of Counterfactual Explanations via Robust Optimization

TL;DR

This paper introduces an iterative robust optimization method to find regions of counterfactual explanations that remain valid under feature perturbations, enhancing the reliability and usability of model recourse options.

Contribution

It develops a novel iterative approach to compute entire regions of robust counterfactual explanations, extending beyond single solutions and applicable to various classifiers.

Findings

Efficiently generates globally optimal robust CEs.

Proves convergence for multiple machine learning models.

Applicable to logistic regression, decision trees, random forests, neural networks.

Abstract

Counterfactual explanations play an important role in detecting bias and improving the explainability of data-driven classification models. A counterfactual explanation (CE) is a minimal perturbed data point for which the decision of the model changes. Most of the existing methods can only provide one CE, which may not be achievable for the user. In this work we derive an iterative method to calculate robust CEs, i.e. CEs that remain valid even after the features are slightly perturbed. To this end, our method provides a whole region of CEs allowing the user to choose a suitable recourse to obtain a desired outcome. We use algorithmic ideas from robust optimization and prove convergence results for the most common machine learning methods including logistic regression, decision trees, random forests, and neural networks. Our experiments show that our method can efficiently generate globally optimal robust CEs for a variety of common data sets and classification models.