提出KARMA方法，用马尔可夫模型解释时间序列预测的依赖关系。
Global Explanations for Multivariate Time Series Forecasting Models via $K$-Order Markov Approximations
- 构建基于最小历史长度K的马尔可夫代理模型，捕捉时间依赖性
- 在真实气象数据上成功还原模型学习到的因果结构
- 比TimeSHAP等方法更准确识别时间依赖，适合时序预测解释
尽管已有诸多可解释人工智能（XAI）方法，但多数不适用于时间序列预测模型，且常隐含时间戳特征独立的假设。这一假设忽略了时间依赖的本质，可能导致违背数据时序与因果结构的解释。本文提出KARMA方法，通过构建能捕获预测模型所学时间依赖性的马尔可夫代理模型来解释时间序列预测器。核心包括：识别模型预测充分的最小历史长度K；从离散化历史空间估计最优的K阶马尔可夫转移核；以及由转移核导出的五级全局解释层次。我们以北京PM2.5真实数据为例进行展示。此外，在具有已知真实因果边的复杂合成数据上，实验验证了KARMA（i）能通过受控实验恢复模型学习到的因果结构，（ii）在识别时间依赖方面优于现有方法如TimeSHAP。
原文摘要 · Abstract (English)
While many explainable AI (XAI) methods have been proposed, most are not designed for time-series forecasting models and often rely on the implicit assumption that timestamp features are independent. This assumption ignores the fundamental property of temporal dependence and can lead to explanations that violate the sequential and causal structure of the data. We introduce \textsc{KARMA}, a method for explaining time-series predictors by constructing a Markov surrogate model that captures the temporal dependencies learned by the predictor. Our approach revolves around three main aspects: identifying the minimal history length $K$ that is predictively sufficient for the model, estimating the best-fitting $K$-order Markov transition kernel from the discretized history space, and a five-level global explanation hierarchy that can be derived from the Markov transition kernel, which we illustrate using real-world weather data (Beijing PM 2.5). We also certify using complex synthetic data with known true causal edges that KARMA (i) recovers the data causal structure as learned by the model via a controlled experiment and (ii) identifies temporal dependencies better than established attribution methods such as TimeSHAP.
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。