mlsanityData to 14 Oct 2026

No Scale Left Behind: Multi-Scale Autoencoder with Bi-directional Attention for Time Series Anomaly Detection

arXiv 2609.38004 ↗First posted 29 Sep 2026cs.LG cs.AIcited by 0

Not on the map. Why?

Abstract (arXiv)

Time series anomaly detection (TSAD) plays a crucial role in healthcare, finance, industrial monitoring, and other sectors. Within and between these settings, anomalies span vastly different temporal scales, from sub-second point spikes to multi-hour drift patterns. However, most existing TSAD methods commit to a single temporal granularity, and multi-scale designs either analyze different scales in isolation or are constrained to a predefined coarse-to-fine hierarchy, both failing to sufficiently capture multi-scale interactions. To resolve this limitation, we propose Multi-Scale Autoencoder with Cross-Scale Attention for TSAD (MSCAD), a simple yet powerful semi-supervised TSAD framework founded on parallel autoencoder branches corresponding to different patch sizes. A stack of symmetric bidirectional cross-scale attention blocks enables every pair of scales to exchange information before reconstruction without allowing any single scale to be privileged. On the comprehensive TSB-AD benchmark (40 datasets, 530 series), MSCAD achieves large performance gains against 50 baselines across multiple metrics, with VUS-PR of 0.57(+9.6%) on the univariate split and 0.47(+9.3%) on the multivariate split compared to the state-of-the-art.

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Builds on 33 of its 77 references that are in the map. First posted on arXiv 29 Sep 2026.

Builds on

33 of 77 references.

References · 33

  1. 2022A Time Series is Worth 64 Words: Long-term Forecasting with Transformerscited by 2,039
  2. 2022TimesNet: Temporal 2D-Variation Modeling for General Time Series Analysiscited by 1,058
  3. 2023iTransformer: Inverted Transformers Are Effective for Time Series Forecastingcited by 931
  4. 2024Chronos: Learning the Language of Time Seriescited by 759
  5. 2023A decoder-only foundation model for time-series forecastingcited by 692
  6. 2023One Fits All:Power General Time Series Analysis by Pretrained LMcited by 632
  7. 2024MOMENT: A Family of Open Time-series Foundation Modelscited by 482
  8. 2018Detecting Spacecraft Anomalies Using LSTMs and Nonparametric Dynamic Thresholdingcited by 410
  9. 2021Anomaly Transformer: Time Series Anomaly Detection with Association Discrepancycited by 394
  10. 2024TimeMixer: Decomposable Multiscale Mixing for Time Series Forecastingcited by 346
  11. 2018Unsupervised Anomaly Detection via Variational Auto-Encoder for Seasonal KPIs in Web Applicationscited by 224
  12. 2023FITS: Modeling Time Series with 10k Parameterscited by 195
21 more
  1. 2019Time-Series Anomaly Detection Service at Microsoftcited by 165
  2. 2020Current Time Series Anomaly Detection Benchmarks are Flawed and are Creating the Illusion of Progresscited by 151
  3. 2020COPOD: Copula-Based Outlier Detectioncited by 146
  4. 2023Lag-Llama: Towards Foundation Models for Probabilistic Time Series Forecastingcited by 113
  5. 2024Pathformer: Multi-scale Transformers with Adaptive Pathways for Time Series Forecastingcited by 104
  6. 2023DCdetector: Dual Attention Contrastive Representation Learning for Time Series Anomaly Detectioncited by 103
  7. 2021Towards a Rigorous Evaluation of Time-series Anomaly Detectioncited by 97
  8. 2024CATCH: Channel-Aware multivariate Time Series Anomaly Detection via Frequency Patchingcited by 94
  9. 2018Extended Isolation Forestcited by 81
  10. 2022Local Evaluation of Time Series Anomaly Detection Algorithmscited by 79
  11. 2021An Evaluation of Anomaly Detection and Diagnosis in Multivariate Time Seriescited by 68
  12. 2018Precision and Recall for Time Seriescited by 67
  13. 2020Exathlon: A Benchmark for Explainable Anomaly Detection over Time Seriescited by 56
  14. 2022Scaleformer: Iterative Multi-scale Refining Transformers for Time Series Forecastingcited by 54
  15. 2023Multi-resolution Time-Series Transformer for Long-term Forecastingcited by 41
  16. 2024Towards a General Time Series Anomaly Detector with Adaptive Bottlenecks and Dual Adversarial Decoderscited by 38
  17. 2016Multivariate Industrial Time Series with Cyber-Attack Simulation: Fault Detection Using an LSTM-based Predictive Data Modelcited by 34
  18. 2024TimeSeriesBench: An Industrial-Grade Benchmark for Time Series Anomaly Detection Modelscited by 23
  19. 2025CrossAD: Time Series Anomaly Detection with Cross-scale Associations and Cross-window Modelingcited by 12
  20. 2024ElasTST: Towards Robust Varied-Horizon Forecasting with Elastic Time-Series Transformercited by 10
  21. 2024Peri-midFormer: Periodic Pyramid Transformer for Time Series Analysiscited by 5

Built on by

Not cited yet.