MASCOTS：时间序列的模型无关符号反事实解释
MASCOTS: Model-Agnostic Symbolic COunterfactual explanations for Time Series
AI总结：
针对时间序列反事实解释的挑战，提出模型无关的MASCOTS方法，利用符号特征空间生成可解释且多样的反事实，在保持效度的同时显著提升可解释性与稀疏性。
摘要：
反事实解释通过识别改变结果所需的最小变化，为理解模型决策提供了一种直观的方式。然而，由于时间依赖性、高维性以及缺乏直观的人类可解释表示，将反事实方法应用于时间序列模型仍然具有挑战性。我们提出了MASCOTS，一种利用词袋感受野表示以及受符号聚合近似启发的符号变换的方法。通过在符号特征空间中操作，它增强了可解释性，同时保持了对原始数据和模型的保真度。与依赖模型结构或基于自编码器采样的现有方法不同，MASCOTS以模型无关的方式直接生成有意义且多样的反事实观测，适用于单变量和多变量数据。我们在单变量和多变量基准数据集上评估了MASCOTS，展示了与最先进方法相当的效度、邻近性和合理性，同时显著提高了可解释性和稀疏性。其符号特性使得解释可以以视觉、自然语言或语义表示的形式表达，使反事实推理更易于访问和操作。
英文摘要：
Counterfactual explanations provide an intuitive way to understand model decisions by identifying minimal changes required to alter an outcome. However, applying counterfactual methods to time series models remains challenging due to temporal dependencies, high dimensionality, and the lack of an intuitive human-interpretable representation. We introduce MASCOTS, a method that leverages the Bag-of-Receptive-Fields representation alongside symbolic transformations inspired by Symbolic Aggregate Approximation. By operating in a symbolic feature space, it enhances interpretability while preserving fidelity to the original data and model. Unlike existing approaches that either depend on model structure or autoencoder-based sampling, MASCOTS directly generates meaningful and diverse counterfactual observations in a model-agnostic manner, operating on both univariate and multivariate data. We evaluate MASCOTS on univariate and multivariate benchmark datasets, demonstrating comparable validity, proximity, and plausibility to state-of-the-art methods, while significantly improving interpretability and sparsity. Its symbolic nature allows for explanations that can be expressed visually, in natural language, or through semantic representations, making counterfactual reasoning more accessible and actionable.
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。
