TimeRadar: A domain-rotatable foundation model for time series anomaly detection

Publication Type

Conference Proceeding Article

Version

publishedVersion

Publication Date

8-2026

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 (\eg, 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. Extensive experiments on eight popular TSAD benchmarks demonstrate that TimeRadar consistently outperforms a variety of conventional and TSFM-based competing methods, delivering average gains of 10.5% and 29.4% in AUC-R and AUC-P, respectively. Our code is available at https://github.com/mala-lab/TimeRadar.

Keywords

Time Series, Foundation Model, Anomaly Detection

Discipline

Artificial Intelligence and Robotics | Databases and Information Systems

Research Areas

Intelligent Systems and Optimization

Areas of Excellence

Digital transformation

Publication

KDD '26: Proceedings of the 32nd ACM SIGKDD Conference on Knowledge Discovery and Data Mining V.2, Jeju Island, South Korea, August 9-13

First Page

1602

Last Page

1613

Identifier

10.1145/3770855.3818062

Publisher

ACM

City or Country

New York

Additional URL

https://doi.org/10.1145/3770855.3818062

This document is currently not available here.

Share

COinS