mlsanityData to 14 Oct 2026

Generalist Representation, Specialist Detection: TS-Router for Time-Series Anomaly Detection

arXiv 2610.00978 ↗First posted 1 Oct 2026cs.LG cs.AIcited by 0

Not on the map. Why?

Abstract (arXiv)

Time-series anomaly detection (TSAD) is difficult to generalize across datasets because heterogeneous temporal dynamics imply different notions of normality and favor different detection criteria. While time-series foundation models provide transferable representations, coupling them with a fixed anomaly-scoring mechanism can overlook this variation. This motivates a different perspective on foundation-model-based TSAD: using foundation models to coordinate specialized anomaly criteria rather than directly imposing a universal one. Based on this view, we propose TS-Router, a generalist-representation, specialist-detection framework that estimates the relative competence of heterogeneous anomaly detectors from pretrained temporal representations and selects suitable specialists for each target series. To avoid relying on specialist-performance labels from real tasks, we derive soft competence supervision from specialists' relative performance on labeled simulated tasks. At deployment, routing requires no target anomaly labels, and only the selected specialists are fitted unsupervisedly on the target series. We bound Top-(k) set-competence regret under representation coverage and conditional competence stability. Across 16 real-world benchmarks and four complementary evaluation metrics, TS-Router achieves the best overall average rank. Controlled ablations with multiple frozen TSFM encoders further support the use of pretrained representations for competence estimation and adaptive specialist selection. The code is available at https://anonymous.4open.science/r/TS-Router-D8FF.

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Builds on 18 of its 36 references that are in the map. First posted on arXiv 1 Oct 2026.

Builds on

18 of 36 references.

References · 18

  1. 2024Chronos: Learning the Language of Time Seriescited by 759
  2. 2023A decoder-only foundation model for time-series forecastingcited by 692
  3. 2024MOMENT: A Family of Open Time-series Foundation Modelscited by 482
  4. 2021Anomaly Transformer: Time Series Anomaly Detection with Association Discrepancycited by 394
  5. 2021Graph Neural Network-Based Anomaly Detection in Multivariate Time Seriescited by 301
  6. 2024Time-MoE: Billion-Scale Time Series Foundation Models with Mixture of Expertscited by 287
  7. 2022TranAD: Deep Transformer Networks for Anomaly Detection in Multivariate Time Series Datacited by 214
  8. 2019Time-Series Anomaly Detection Service at Microsoftcited by 165
  9. 2023DCdetector: Dual Attention Contrastive Representation Learning for Time Series Anomaly Detectioncited by 103
  10. 2024UniTS: A Unified Multi-Task Time Series Modelcited by 94
  11. 2024Towards a General Time Series Anomaly Detector with Adaptive Bottlenecks and Dual Adversarial Decoderscited by 38
  12. 2023AnomalyBERT: Self-Supervised Transformer for Time Series Anomaly Detection using Data Degradation Schemecited by 25
6 more
  1. 2024LogFormer: A Pre-train and Tuning Pipeline for Log Anomaly Detectioncited by 15
  2. 2025Towards Foundation Models for Zero-Shot Time Series Anomaly Detection: Leveraging Synthetic Data and Relative Context Discrepancycited by 10
  3. 2024DACAD: Domain Adaptation Contrastive Learning for Anomaly Detection in Multivariate Time Seriescited by 7
  4. 2025Robust and Explainable Detector of Time Series Anomaly via Augmenting Multiclass Pseudo-Anomaliescited by 7
  5. 2025Open Challenges in Time Series Anomaly Detection: An Industry Perspectivecited by 5
  6. 2025CICADA: Cross-Domain Interpretable Coding for Anomaly Detection and Adaptation in Multivariate Time Seriescited by 3

Built on by

Not cited yet.