发表机构
Zhejiang University; Aalborg University; School of Computing Technologies, RMIT University（浙江大学; 奥尔堡大学; 皇家墨尔本理工大学计算技术学院）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
JAPE是首个联合异常预测与解释的多变量时间序列框架，通过解耦时空建模等技术提升预测性能与可解释性，在五个真实基准上实现F1、AUC-PR及MRR的显著提升。
AI 中文摘要
多变量时间序列异常预测旨在从历史观测中识别未来一段时间内是否会发生异常以及发生的时间。现有方法主要将异常表征为未来数值的偏差，这可能会忽略由微弱异常前兆引发的细微依赖变化，且无法在发出警报的同时提供原生变量级别的解释。为弥合这些差距，我们提出JAPE，一个联合异常预测与解释框架，将异常预测从数值偏差建模提升至依赖结构建模。JAPE是首个明确建模演化依赖结构以实现逐点警报和原生变量级解释的异常预测框架。具体而言，JAPE（i）提出解耦时空表示（Decoupled Spatio-Temporal Representation，DSTR）骨干网络，该网络解耦时间与空间建模，并通过可学习的滞后聚合捕捉滞后感知依赖关系，从而在数值偏差出现前感知结构前兆；（ii）设计双视图警报机制，将数值预测与演化依赖图融合以实现逐点异常预测，即使在细微数值偏差下也能捕捉结构证据；（iii）提出原生预测解释（Native Predictive Explanation，NPE），其直接复用预测得到的依赖图，无需额外模型或训练即可按结构偏差对变量进行排序。在三个预测时间跨度的五个真实基准上开展的大量实验表明，JAPE的平均F1值提升了19.7%，AUC-PR提升了41.3%，同时可解释性的MRR提升了26.6%。
英文摘要
Multivariate time-series anomaly prediction aims to identify whether and when anomalies will occur over a future horizon from historical observations. Existing methods primarily characterize anomalies as deviations in future numerical values, which may overlook subtle dependency changes induced by weak anomaly precursors and provide no native variable-level explanation together with the alert. To bridge these gaps, we propose JAPE, a Joint Anomaly Prediction and Explanation framework that lifts anomaly prediction from numerical-deviation modeling to dependency-structure modeling. JAPE is the first anomaly prediction framework to explicitly model evolving dependency structures for both point-wise alerting and native variable-level explanation. Specifically, JAPE (i) proposes a Decoupled Spatio-Temporal Representation (DSTR) backbone that decouples temporal and spatial modeling and captures lag-aware dependencies via learnable lag aggregation, thereby perceiving structural precursors before numerical deviations emerge; (ii) designs a dual-view alerting mechanism that fuses numerical forecasts with evolving dependency graphs for point-wise anomaly prediction, capturing structural evidence even under subtle numerical deviations; and (iii) presents Native Predictive Explanation (NPE), which directly reuses the predicted dependency graphs to rank variables by structural deviations without additional models or training. Extensive experiments on five real-world benchmarks across three prediction horizons demonstrate that JAPE improves average F1 and AUC-PR by 19.7% and 41.3%, respectively, while improving explainability with 26.6% gain in MRR.
