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

TL;DR

TimeRadar introduces a novel time series foundation model that employs a fractional time-frequency domain rotation to effectively detect anomalies across diverse datasets, addressing limitations of existing models focused on regular pattern learning.

Contribution

The paper proposes TimeRadar, a new TSFM with fractional time-frequency rotation and adaptive data reconstruction, enhancing unsupervised anomaly detection across unseen datasets.

Findings

Effective differentiation of normal and abnormal patterns across datasets.

Improved anomaly detection accuracy in diverse and unseen datasets.

Novel fractional time-frequency rotation mechanism enhances model adaptability.

Abstract

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.