提出多目标时序反事实解释方法，让复杂模型决策更透明可信。
Multi-SpaCE: Multi-Objective Subsequence-based Sparse Counterfactual Explanations for Multivariate Time Series Classification
- 用遗传算法平衡修改量、稀疏性、合理性与连续性
- 在多个数据集上实现100%解释有效性，优于现有方法
- 适合医疗、金融等对解释可靠性要求高的场景
深度学习在复杂任务中表现优异，但缺乏透明性，限制了其在关键领域的应用。反事实解释作为可解释人工智能的核心工具，通过识别使预测结果改变的最小输入修改来揭示模型决策逻辑。然而，现有时序数据方法受限于单变量假设、修改约束僵硬或缺乏有效性保证。本文提出Multi-SpaCE，一种面向多变量时间序列分类的多目标反事实解释方法。采用非支配排序遗传算法II（NSGA-II），在逼近性、稀疏性、合理性与连续性之间进行权衡。与多数方法不同，它确保完全有效性，支持多变量数据，并提供帕累托前沿解集，满足不同用户需求。在多个数据集上的全面实验表明，Multi-SpaCE能持续实现100%的有效性，性能显著优于现有方法。
原文摘要 · Abstract (English)
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.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。