Replication Data for: TimeX

Interpreting time series models is uniquely challenging because it requires identifying both the location of time series signals that drive model predictions and their matching to an interpretable temporal pattern. While explainers from other modalities can be applied to time series, their inductive biases do not transfer well to the inherently uninterpretable nature of time series. We present TIMEX, a time series consistency model for training explainers. TIMEX trains an interpretable surrogate to mimic the behavior of a pretrained time series model. It addresses the issue of model faithfulness by introducing model behavior consistency, a novel formulation that preserves relations in the latent space induced by the pretrained model with relations in the latent space induced by TIMEX. TIMEX provides discrete attribution maps and, unlike existing interpretability methods, it learns a latent space of explanations that can be used in various ways, such as to provide landmarks to visually aggregate similar explanations and easily recognize temporal patterns. We evaluate TIMEX on 8 synthetic and real-world datasets and compare its performance against state-of-the-art interpretability methods. We also conduct case studies using physiological time series. Quantitative evaluations demonstrate that TIMEX achieves the highest or second-highest performance in every metric compared to baselines across all datasets. Through case studies, we show that the novel components of TIMEX show potential for training faithful, interpretable models that capture the behavior of pretrained time series models.时间序列模型的可解释性分析具有独特的挑战性：该任务需要同时定位驱动模型预测的时间序列信号（time series signals），并将这些信号匹配至可解释的时序模式（temporal pattern）。尽管其他模态的可解释性方法可应用于时间序列任务，但其归纳偏置（inductive biases）无法很好地适配时间序列固有的不可解释特性。本文提出TIMEX——一种用于训练可解释器（explainers）的时序一致性模型。TIMEX通过训练可解释代理模型（interpretable surrogate），复刻预训练时间序列模型（pretrained time series model）的行为逻辑。该方法通过引入模型行为一致性（model behavior consistency）这一全新的公式化定义，解决了模型保真度（model faithfulness）问题：该定义保留了预训练模型诱导生成的隐空间（latent space）与TIMEX诱导生成的隐空间中的关联关系。TIMEX可输出离散归因图（discrete attribution maps）；与现有可解释性方法不同，它能够学习可解释性结果的隐空间，该空间可通过多种方式加以利用：例如为可视化聚合相似可解释性结果提供锚点，以及便捷识别时序模式。本文在8个合成数据集与真实世界数据集上对TIMEX进行了评估，并将其性能与当前最优的可解释性方法进行了对比。此外，本文还利用生理时序信号（physiological time series）开展了案例研究。定量评估结果显示，在所有数据集上，与基线模型（baselines）相比，TIMEX在各项评估指标中均取得了最优或次优的性能表现。通过案例研究，本文验证了TIMEX的全新组件具备训练保真且可解释模型的潜力，此类模型能够复刻预训练时间序列模型的行为逻辑。

搜集汇总

背景与挑战

背景概述

该数据集用于复现TimeX模型，TimeX是一个专门设计用于解释时间序列模型的一致性模型，通过训练可解释的代理来模仿预训练模型行为，并引入模型行为一致性以提升忠实度。它提供离散归因图和解释的潜在空间，在8个合成和真实世界数据集（包括生理时间序列）的评估中表现优异，在所有指标上均达到最佳或次佳性能。