发表机构
National Key Laboratory of Parallel and Distributed Computing; National University of Defense Technology; Intelligent Game and Decision Lab (IGDL); Singapore Management University（并行与分布式计算国家重点实验室; 国防科技大学; 智能博弈与决策实验室; 新加坡管理大学）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
针对时间序列基础模型在异常检测中可能过度建模异常模式的问题，提出轻量即插即用的正态性约束学习框架，通过构建紧凑正态性子空间并自适应引导特征，增强异常评分差异，在多种基准上持续提升检测性能。
AI 中文摘要
时间序列基础模型（TSFMs）通过在大规模时间序列预训练中学习重建或预测广泛的时序模式，实现了强大的泛化能力。然而，这种优势在异常检测中可能变成弱点：TSFMs可能将罕见的异常模式与正常模式一样有效地建模，使得异常能够被准确重建或预测，从而削弱了基于重建/预测误差的异常评分。本文提出了正态性约束学习（NCL），一个轻量级即插即用框架，在不修改预训练参数的情况下，使预训练的TSFMs适应准确的异常检测。我们的关键见解是将TSFMs的广泛模式空间约束到目标时间序列的正常结构上，防止其广泛的建模能力掩盖异常偏差。具体而言，NCL从少量正常patch特征中构建一个紧凑的正态性子空间，并在该子空间内自适应地将每个patch特征导向正态性，由形成紧凑且可区分的正态性流形的对比约束引导。校准后的特征被聚合以增强正常成分，并与原始TSFM输出融合，放大正常与异常观测之间的差异，用于基于重建/预测误差的异常评分。在多种TSFM家族和基准上的广泛实验表明，NCL持续提升异常检测性能，为将TSFMs适应异常检测提供了一个通用框架。
英文摘要
Time Series Foundation Models (TSFMs) achieve strong generalization by learning to reconstruct or forecast broad temporal patterns from large-scale time series during pre-training. Yet this strength can become a weakness for anomaly detection: TSFMs may model rare anomalous patterns as effectively as normal ones, allowing anomalies to be accurately reconstructed or forecasted and thus diminishing their reconstruction/forecasting error-based anomaly scores. This paper proposes $\underline{\textbf{N}}$$\textbf{ormality}$ $\underline{\textbf{C}}$$\textbf{onstraint}$ $\underline{\textbf{L}}$$\textbf{earning}$ ($\textbf{NCL}$), a lightweight plug-and-play framework that adapts pre-trained TSFMs for accurate anomaly detection without modifying their pre-trained parameters. Our key insight is to constrain the broad pattern space of TSFMs to the normal structure of a target time series, preventing their broad modeling capability from obscuring abnormal deviations. Specifically, NCL constructs a compact normality subspace from a few normal patch features and adaptively steers each patch feature toward normality within this subspace, guided by contrastive constraints that form compact and discriminative normality manifolds. The calibrated features are aggregated to reinforce normal components and fused with the original TSFM output, amplifying the discrepancy between normal and abnormal observations for the reconstruction/forecasting error-based anomaly scoring. Extensive experiments across diverse TSFM families and benchmarks show that NCL consistently improves anomaly detection performance, providing a generalizable framework for adapting TSFMs to anomaly detection.
Comments43 pages, 15 figures
