mlsanityData to 7 Oct 2026

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

arXiv 2602.19068 ↗First posted 22 Feb 2026cs.LGcited by 0

Not on the map. Why?

Abstract (arXiv)

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.

Key facts. No citing papers in the map yet (data through 7 Oct 2026). Builds on 24 of its 62 references that are in the map. First posted on arXiv 22 Feb 2026.

Builds on

24 of 62 references.

References · 24

  1. 2020Language Models are Few-Shot Learnerscited by 32,199
  2. 2022A Time Series is Worth 64 Words: Long-term Forecasting with Transformerscited by 1,981
  3. 2024Chronos: Learning the Language of Time Seriescited by 712
  4. 2023One Fits All:Power General Time Series Analysis by Pretrained LMcited by 615
  5. 2024Unified Training of Universal Time Series Forecasting Transformerscited by 588
  6. 2024MOMENT: A Family of Open Time-series Foundation Modelscited by 453
  7. 2018Detecting Spacecraft Anomalies Using LSTMs and Nonparametric Dynamic Thresholdingcited by 407
  8. 2021Anomaly Transformer: Time Series Anomaly Detection with Association Discrepancycited by 387
  9. 2024Time-MoE: Billion-Scale Time Series Foundation Models with Mixture of Expertscited by 280
  10. 2021Monash Time Series Forecasting Archivecited by 256
  11. 2024Foundation Models for Time Series Analysis: A Tutorial and Surveycited by 234
  12. 2020Current Time Series Anomaly Detection Benchmarks are Flawed and are Creating the Illusion of Progresscited by 148
12 more
  1. 2024Tiny Time Mixers (TTMs): Fast Pre-trained Models for Enhanced Zero/Few-Shot Forecasting of Multivariate Time Seriescited by 120
  2. 2023DCdetector: Dual Attention Contrastive Representation Learning for Time Series Anomaly Detectioncited by 103
  3. 2024CATCH: Channel-Aware multivariate Time Series Anomaly Detection via Frequency Patchingcited by 91
  4. 2022Local Evaluation of Time Series Anomaly Detection Algorithmscited by 79
  5. 2021Unsupervised Time Series Outlier Detection with Diversity-Driven Convolutional Ensembles -- Extended Versioncited by 35
  6. 2024Towards a General Time Series Forecasting Model with Unified Representation and Adaptive Transfercited by 31
  7. 2024In-Context Fine-Tuning for Time-Series Foundation Modelscited by 31
  8. 2022Detecting Multivariate Time Series Anomalies with Zero Known Labelcited by 21
  9. 2024KAN-AD: Time Series Anomaly Detection with Kolmogorov-Arnold Networkscited by 20
  10. 2023Unraveling the "Anomaly" in Time Series Anomaly Detection: A Self-supervised Tri-domain Solutioncited by 12
  11. 2023Learning Multi-Pattern Normalities in the Frequency Domain for Efficient Time Series Anomaly Detectioncited by 3
  12. 2026Diversified Scaling Inference in Time Series Foundation Modelscited by 2

Built on by

Not cited yet.