提出新方法CONFETTI，让深度学习时序分类更可解释且改动小。
Counterfactual Explainable AI (XAI) Method for Deep Learning-Based Multivariate Time Series Classification
- 多目标优化：同时提升预测置信度、修改距离和变化稀疏性
- 在7个数据集上实现≥10%置信度提升，40%以上场景更稀疏
- 适合需要可行动解释的医疗、金融等高风险决策场景
深度学习提升了多变量时间序列（MTS）分类与回归性能，但其缺乏透明性阻碍了决策。现有可解释AI方法难以全面揭示决策空间。反事实解释（CE）具潜力，但当前方法常仅关注准确性、接近性或稀疏性中的单一目标，实用性受限。为此，我们提出CONFETTI，一种新型多目标反事实解释方法。该方法识别关键时间序列子段，定位反事实目标，并最优调整时序数据，在预测置信度、接近性和稀疏性之间取得平衡。该方法以最小改动提供可行动洞察，增强可解释性与决策支持。在来自UEA数据集的7个多变量时间序列数据集上评估，CONFETTI在各项优化目标上均优于现有先进方法，且在文献中6项指标上表现更优，实现≥10%的置信度提升，同时在≥40%的案例中改善稀疏性。
原文摘要 · Abstract (English)
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 $\geq40\%$.
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。