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 2602.19068cs.LG
收藏

TimeRadar: 一个用于时间序列异常检测的领域可旋转基础模型

TimeRadar: A Domain-Rotatable Foundation Model for Time Series Anomaly Detection

School of Computing and Information Systems(计算与信息系);Singapore Management University(新加坡管理大学);Chongqing Institute of Green and Intelligent Technology(绿色与智能技术研究所);University of Chinese Academy of Sciences(中国科学院大学);State Information Center(信息中心)

Hui He, Hezhe Qiao, Yutong Chen, Kun Yi, Guansong Pang

AI总结:

TimeRadar通过分数时间-频率域旋转和FTFRecon组件实现跨不同数据集的通用时间序列异常检测。

摘要:

当前的时间序列基础模型(TSFMs)主要专注于在预定义的时间或频率域内学习普遍且规律的模式,以实现监督的下游任务(例如预测)。因此,它们往往在本质上无监督的下游任务中表现不佳,例如时间序列异常检测(TSAD),其目标是识别罕见且不规则的模式。这种限制源于异常模式在相同的时间/频率域中可能与常规模式相似。为了解决这个问题,我们引入了TimeRadar,一种创新的TSFM,其构建在分数时间-频率域中,以支持在多样化的未见数据集上进行通用的TSAD。我们的关键见解是将时间序列旋转到数据依赖的分数时间-频率表示中,可以自适应地区分不同数据集中的正常和异常信号。为此,在TimeRadar中提出了一种新的组件,即分数调制时间-频率重建(FTFRecon),利用可学习的分数阶次将时间序列旋转到连续时间-频率域中最具显著角度的位置,以实现准确的数据重建。这为每个数据输入提供了在最优时间-频率域中的自适应数据重建,使在不同数据集上(包括未见数据集)能够有效地区分无界异常模式与常规模式。为了使TimeRadar能够建模未被全局数据重建捕捉到的局部异常性,我们进一步引入了上下文偏差学习(CDL)组件,以建模输入相对于其在可旋转域中的上下文时间序列数据的局部偏差。

英文摘要:

Current time series foundation models (TSFMs) primarily focus on learning prevalent and regular patterns within a predefined time or frequency domain to enable supervised downstream tasks (e.g., forecasting). Consequently, they are often ineffective for inherently unsupervised downstream tasks-such as time series anomaly detection (TSAD), which aims to identify rare, irregular patterns. This limitation arises because such abnormal patterns can closely resemble the regular patterns when presented in the same time/frequency domain. To address this issue, we introduce TimeRadar, an innovative TSFM built in a fractional time-frequency domain to support generalist TSAD across diverse unseen datasets. Our key insight is that rotating a time series into a data-dependent fractional time-frequency representation can adaptively differentiate the normal and abnormal signals across different datasets. To this end, a novel component, namely Fractionally modulated Time-Frequency Reconstruction (FTFRecon), is proposed in TimeRadar to leverage a learnable fractional order to rotate the time series to the most pronounced angle between a continuous time and frequency domain for accurate data reconstruction. This provides adaptive data reconstruction in an optimal time-frequency domain for each data input, enabling effective differentiation of the unbounded abnormal patterns from the regular ones across datasets, including unseen datasets. To allow TimeRadar to model local abnormality that is not captured by the global data reconstruction, we further introduce a Contextual Deviation Learning (CDL) component to model the local deviation of the input relative to its contextual time series data in the rotatable domain.

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。

↑