因果可解释人工智能（XAI）方法用于基于深度学习的多变量时间序列分类
Counterfactual Explainable AI (XAI) Method for Deep Learning-Based Multivariate Time Series Classification
AI总结：
CONFETTI是一种针对多变量时间序列分类的新型因果解释方法，通过平衡预测置信度、接近性和稀疏性，提升模型可解释性和决策支持能力。
摘要：
近年来，深度学习的进步提高了多变量时间序列（MTS）分类和回归的能力，通过捕捉复杂的模式，但其缺乏透明性阻碍了决策。可解释人工智能（XAI）方法提供部分见解，但往往无法传达完整的决策空间。因果解释（CE）提供了一种有前途的替代方案，但当前方法通常优先考虑准确性、接近性或稀疏性——很少同时兼顾，限制了其实际价值。为此，我们提出了CONFETTI，一种新的多目标CE方法用于MTS。CONFETTI识别关键MTS子序列，定位一个因果目标，并优化时间序列以平衡预测置信度、接近性和稀疏性。该方法通过最小的修改提供可操作的见解，提高可解释性并支持决策。CONFETTI在七个来自UEA档案的MTS数据集上进行了评估，证明了其在不同领域中的有效性。CONFETTI在优化目标上始终优于最先进CE方法，并在其他六项指标上取得更高置信度（≥10%）并提高稀疏性（≥40%）。
英文摘要：
Recent advances in deep learning have improved multivariate time series (MTS) classification and regression by capturing complex patterns, but their lack of transparency hinders decision-making. Explainable AI (XAI) methods offer partial insights, yet often fall short of conveying the full decision space. Counterfactual Explanations (CE) provide a promising alternative, but current approaches typically prioritize either accuracy, proximity or sparsity -- rarely all -- limiting their practical value. To address this, we propose CONFETTI, a novel multi-objective CE method for MTS. CONFETTI identifies key MTS subsequences, locates a counterfactual target, and optimally modifies the time series to balance prediction confidence, proximity and sparsity. This method provides actionable insights with minimal changes, improving interpretability, and decision support. CONFETTI is evaluated on seven MTS datasets from the UEA archive, demonstrating its effectiveness in various domains. CONFETTI consistently outperforms state-of-the-art CE methods in its optimization objectives, and in six other metrics from the literature, achieving $\geq10\%$ higher confidence while improving sparsity in $\geq40\%$.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
