A Two-Stage Algorithm for Cost-Efficient Multi-instance Counterfactual Explanations

TL;DR

This paper introduces a two-stage algorithm that efficiently generates counterfactual explanations applicable to multiple instances simultaneously, addressing a key limitation of existing methods that focus on single instances.

Contribution

The paper proposes a novel two-stage algorithm for cost-efficient multi-instance counterfactual explanations, expanding the applicability of counterfactual methods to group-based scenarios.

Findings

The algorithm outperforms popular alternatives in efficiency and cost-effectiveness.

It effectively identifies groups of instances with shared counterfactual explanations.

Experimental results demonstrate improved performance over existing methods.

Abstract

Counterfactual explanations constitute among the most popular methods for analyzing black-box systems since they can recommend cost-efficient and actionable changes to the input of a system to obtain the desired system output. While most of the existing counterfactual methods explain a single instance, several real-world problems, such as customer satisfaction, require the identification of a single counterfactual that can satisfy multiple instances (e.g. customers) simultaneously. To address this limitation, in this work, we propose a flexible two-stage algorithm for finding groups of instances and computing cost-efficient multi-instance counterfactual explanations. The paper presents the algorithm and its performance against popular alternatives through a comparative evaluation.