提出窗口化时序显著性重标方法，精准解析时间序列模型的动态特征重要性。
WinTSR: A Windowed Temporal Saliency Rescaling Method for Interpreting Time Series Deep Learning Models
- 基于时间窗口捕捉历史步长间依赖关系，动态重标特征重要性
- 在5种先进模型上对比测试，性能超越10种现有解释方法
- 开源支持最新时序变换器与基础模型解释，适合研究者部署使用
解释复杂的时间序列预测模型面临挑战，源于时间步之间的时序依赖以及输入特征随时间动态变化的重要性。现有解释方法受限于多聚焦分类任务、使用自定义基线模型而非最新时序模型、依赖简单合成数据集，且需额外训练模型。本文提出一种新解释方法——窗口化时序显著性重标（WinTSR），有效捕捉过去时间步间的时序依赖，并据此高效调整特征重要性。我们在5种不同架构的前沿深度学习模型（含一个时序基础模型）上，与10种近期解释技术进行对比，使用3个真实世界数据集完成分类与回归任务。全面分析表明，WinTSR在整体表现上显著优于其他局部解释方法。最后，我们提供一个新颖的开源框架，支持对最新时序变换器和基础模型进行解释。
原文摘要 · Abstract (English)
Interpreting complex time series forecasting models is challenging due to the temporal dependencies between time steps and the dynamic relevance of input features over time. Existing interpretation methods are limited by focusing mostly on classification tasks, evaluating using custom baseline models instead of the latest time series models, using simple synthetic datasets, and requiring training another model. We introduce a novel interpretation method, \textit{Windowed Temporal Saliency Rescaling (WinTSR)} addressing these limitations. WinTSR explicitly captures temporal dependencies among the past time steps and efficiently scales the feature importance with this time importance. We benchmark WinTSR against 10 recent interpretation techniques with 5 state-of-the-art deep-learning models of different architectures, including a time series foundation model. We use 3 real-world datasets for both time-series classification and regression. Our comprehensive analysis shows that WinTSR significantly outperforms other local interpretation methods in overall performance. Finally, we provide a novel, open-source framework to interpret the latest time series transformers and foundation models.
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。