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.

翻译：反事实解释是分析黑箱系统最流行的方法之一，因为它能推荐对系统输入进行成本高效且可操作的更改，以获得期望的系统输出。尽管现有的大多数反事实方法仅解释单个实例，但若干实际问题（如客户满意度）要求识别能同时满足多个实例（例如客户）的单一反事实。为应对这一局限，本研究提出了一种灵活的两阶段算法，用于寻找实例组并计算成本高效的多实例反事实解释。本文介绍了该算法，并通过对比评估展示了其相对于常用替代方法的性能表现。