发表机构
School of Computer Science, University of Bristol; School of Engineering Mathematics and Technology, University of Bristol（布里斯托大学计算机科学学院; 布里斯托大学工程数学与技术学院）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
研究时间序列分类器解释问题，提出必要性感知框架TimePNS，受Pearl反事实必要性概念启发，采用两阶段设计，通过实验证明其能更准确识别决策关键子序列，改进充分性-必要性权衡。
AI 中文摘要
时间序列分类器的可靠解释应识别出不仅足以维持黑箱模型预测，而且对维持预测必不可少的子序列。然而，现有的面向充分性的方法可能会将高重要性赋予支持预测但对模型决策并非必不可少的虚假子序列。我们引入了TimePNS，这是一个用于时间序列解释的必要性感知框架。受Pearl反事实必要性概念的启发，TimePNS通过对时间因素进行干预并测量原始预测是否被破坏来评估其是否必要。该框架采用两阶段设计。第一阶段学习一个可识别的因果生成过程以及一个面向充分性的解释掩码。第二阶段对时间因素进行反事实干预以得出必要性信号，该信号监督一个时间门，通过抑制非必要成分并强调反事实必要成分来完善初始解释。在合成和真实世界时间序列基准上的实验表明，TimePNS能更准确地识别决策关键子序列，并始终优于强大基线改进充分性-必要性权衡。
英文摘要
Faithful explanations of time-series classifiers should identify subsequences that are not only sufficient to preserve a black-box model's prediction, but also necessary for maintaining it. However, existing sufficiency-oriented methods can assign high importance to spurious subsequences that support the prediction without being essential to the model's decision. We introduce \textbf{TimePNS}, a necessity-aware framework for time-series explanation. Inspired by Pearl's counterfactual notion of necessity, TimePNS assesses whether a temporal factor is necessary by intervening on it and measuring whether the original prediction is disrupted. The framework adopts a two-stage design. Stage I learns an identifiable causal generative process together with a sufficiency-oriented explanation mask. Stage II performs counterfactual interventions on temporal factors to derive necessity signals, which supervise a temporal gate that refines the initial explanation by suppressing non-essential components and emphasizing counterfactually necessary ones. Experiments on synthetic and real-world time-series benchmarks show that TimePNS more accurately identifies decision-critical subsequences and consistently improves sufficiency-necessity trade-offs over strong baselines.
