arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2610.32189cs.LG
收藏

EVOLVE:基于自适应原型记忆的不确定性感知多变量时间序列异常预测

EVOLVE: Uncertainty-Aware Multivariate Time Series Anomaly Prediction with Adaptive Prototype Memories

East China Normal University(华东师范大学);Aalborg University(奥尔堡大学);Huawei(华为);Huawei Technologies Co., Ltd(华为技术有限公司);Huawei Cloud(华为云)

Jianxin Jin, Kai Zhao, Shiyan Hu, Yang Shu, Peng Chen, Meng Wang, Zhongwen Rao, Yijie Li, Jing Wang, Bin Yang, Chenjuan Guo

AI总结:

本文提出EVOLVE框架,针对现有无监督多变量时间序列异常预测方法未考虑异常演化的变量与上下文依赖性及不确定性的问题,通过自适应原型记忆与不确定性感知推理实现更优的异常预测性能。

摘要:

无监督多变量时间序列异常预测(AP)旨在从当前观测值估计未来异常风险,为复杂系统的主动干预与维护提供预警信号。现有无监督AP方法遵循基于扰动的范式,将预定义或随机扰动注入历史窗口以模拟未来异常演化。然而,这些方法在不同变量和上下文间共享扰动,且学习确定性的历史到未来演化。实际中,异常演化具有变量和上下文依赖性:同一扰动在某一变量或上下文中可能被放大为未来异常动态,而在另一变量或上下文中则被吸收为正常波动。此外,未来演化并非由单一历史窗口唯一确定,相似历史可能导致多种合理轨迹,如渐进退化或突变。为解决这些问题,本文提出EVOLVE,这一统一框架通过变量和上下文条件扰动及不确定性感知未来推理来建模无监督AP。EVOLVE通过自适应异常原型记忆构建上下文特定的异常扰动,该记忆可在变量层面动态更新和检索相关扰动。EVOLVE通过采样多个潜在历史状态并通过互补的平滑演化假设与偏差放大演化假设进行解码来建模不确定性,解码的未来轨迹间的分歧被用于估计未来异常风险。在六个真实世界基准数据集上的大量实验表明,EVOLVE始终优于最先进的异常预测基线。

英文摘要:

Unsupervised multivariate time series anomaly prediction (AP) aims to estimate future anomaly risks from current observations, providing early-warning signals for proactive intervention and maintenance in complex systems. Existing unsupervised AP methods follow a perturbation-based paradigm, where predefined or random perturbations are injected into historical windows to simulate abnormal future evolution. However, these methods share perturbations across different variables and contexts, and learn deterministic history-to-future evolution. In reality, anomaly evolution is variable- and context-dependent: the same perturbation may be amplified into abnormal future dynamics in one variable or context, while being absorbed as normal fluctuation in another. In addition, future evolution is not uniquely determined by a historical window, since similar histories may lead to multiple plausible trajectories, such as gradual degradation or abrupt changes. To address these problems, we propose EVOLVE, a unified framework that models unsupervised AP via variable- and context-conditioned perturbations and uncertainty-aware future reasoning. EVOLVE constructs context-specific anomaly perturbations through an adaptive anomaly prototype memory, which can dynamically update and retrieve relevant perturbations at the variable level. EVOLVE models uncertainty by sampling multiple latent historical states and decoding through complementary smooth and deviation-amplifying evolution hypotheses, and the disagreement among decoded future trajectories is used to estimate future anomaly risk. Extensive experiments on six real-world benchmark datasets demonstrate that EVOLVE consistently outperforms state-of-the-art anomaly prediction baselines.

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。

↑