发表机构
LMU Munich; Munich Center for Machine Learning (MCML); TU Graz; BOKU University Vienna; TECNALIA; University of the Basque Country (EHU)（慕尼黑大学; 慕尼黑机器学习中心; 格拉茨工业大学; 维也纳农业大学; 泰克纳利亚; 巴斯克大学）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
针对时间序列反事实分析易破坏时序结构的问题，提出模型无关框架IMFACT，通过替换本征模态函数生成可信反事实解释，在UCR基准数据集上的实验表明其性能优于主流基线。
AI 中文摘要
振动等振荡信号在特定频带中携带类别判别信息；在原始特征空间中对其进行扰动以开展反事实分析，易破坏其时序结构并产生物理上不可信的结果。本研究提出IMFACT（基于本征模态函数的反事实解释），这是一种模型无关框架，用于为时间序列分类器生成可信的反事实解释，该框架在经验模态分解的分解空间中运行。输入信号被拆分为本征模态函数（IMFs），并将选定的IMFs与最近异类邻域（NUN）的IMFs逐步替换，直至分类器翻转至目标类别。我们在两个UCR基准数据集（FaultDetectionA、FruitFlies）上评估了六种IMF选择策略及多NUN循环扩展方法。基于方差的策略搭配三个NUN，在可靠性和可信度指标上优于两种主流基线技术；而跨三个NUN循环的策略在两个数据集上均实现了最佳的邻近度。
英文摘要
Oscillatory signals, such as vibration, carry class-discriminative information in specific frequency bands; perturbing them in raw feature space for counterfactual analysis easily destroys their temporal structure and produces physically implausible results. In this work, we introduce IMFACT (IMF-based counterfACTuals), a model-agnostic framework for generating plausible counterfactual explanations for time series classifiers that operates in the decomposition space of Empirical Mode Decomposition. An input signal is split into Intrinsic Mode Functions (IMFs), and selected IMFs are progressively substituted with those of a Nearest Unlike Neighbour (NUN) until the classifier flips to the target class. We evaluate six IMF-selection strategies and a multi-NUN cycling extension on two UCR benchmarks (FaultDetectionA, FruitFlies). The variance-based strategy with three NUNs outperforms two prominent baseline techniques on reliability and plausibility metrics, while cycling across three NUNs yields the best proximity across both datasets.
Comments16 pages, 2 figure, 2 tables, accepted at XKDD Workshop at ECML-PKDD
