标题： 多目标子序列稀疏反事实解释的多变量时间序列分类：Multi-SpaCE 显示英文标题

标题： Multi-SpaCE: Multi-Objective Subsequence-based Sparse Counterfactual Explanations for Multivariate Time Series Classification

摘要： 深度学习系统在复杂任务中表现出色，但往往缺乏透明性，这限制了它们在关键应用中的使用。 反事实解释是可解释人工智能（XAI）的核心工具之一，通过识别输入的最小变化以改变其预测结果，提供模型决策的见解。 然而，现有的时间序列数据方法受限于单变量假设、修改上的刚性约束或缺乏有效性保证。 本文介绍了一种名为Multi-SpaCE的多目标反事实解释方法，用于多元时间序列。 利用非支配排序遗传算法II（NSGA-II），Multi-SpaCE平衡了接近性、稀疏性、合理性以及连续性。 与大多数方法不同，它确保了完全的有效性，支持多元数据，并提供了解决方案的帕累托前沿，从而能够满足不同的终端用户需求。 在各种数据集中的综合实验表明，Multi-SpaCE能够在保持完全有效性的同时，相较于现有方法展现出更优越的性能。 显示英文摘要

摘要： Deep Learning systems excel in complex tasks but often lack transparency, limiting their use in critical applications. Counterfactual explanations, a core tool within eXplainable Artificial Intelligence (XAI), offer insights into model decisions by identifying minimal changes to an input to alter its predicted outcome. However, existing methods for time series data are limited by univariate assumptions, rigid constraints on modifications, or lack of validity guarantees. This paper introduces Multi-SpaCE, a multi-objective counterfactual explanation method for multivariate time series. Using non-dominated ranking genetic algorithm II (NSGA-II), Multi-SpaCE balances proximity, sparsity, plausibility, and contiguity. Unlike most methods, it ensures perfect validity, supports multivariate data and provides a Pareto front of solutions, enabling flexibility to different end-user needs. Comprehensive experiments in diverse datasets demonstrate the ability of Multi-SpaCE to consistently achieve perfect validity and deliver superior performance compared to existing methods.