Counterfactual explanations constitute among the most popular methods for analyzing the predictions of black-box systems since they can recommend cost-efficient and actionable changes to the input to turn an undesired system's output into a desired output. While most of the existing counterfactual methods explain a single instance, several real-world use cases, such as customer satisfaction, require the identification of a single counterfactual that can satisfy multiple instances (e.g. customers) simultaneously. In this work, we propose a flexible two-stage algorithm for finding groups of instances along with cost-efficient multi-instance counterfactual explanations. This is motivated by the fact that in most previous works the aspect of finding such groups is not addressed.

翻译：反事实解释是分析黑箱系统预测结果最流行的方法之一，因为它能推荐成本高效且可操作的输入变更，将系统的非期望输出转化为期望输出。现有的大多数反事实方法仅解释单个实例，但实际应用场景（如客户满意度）需要能够同时满足多个实例（例如，多个客户）的单一反事实解释。本文提出了一种灵活的两阶段算法，用于查找实例组及其对应的成本高效的多实例反事实解释。这一研究的动机在于，以往大多数工作并未涉及如何发现此类实例组的问题。