mlsanityData to 7 Oct 2026

Learning Unified Representations of Normalcy for Time Series Anomaly Detection

arXiv 2605.09685 ↗First posted 10 May 2026cs.LG cs.AIcited by 0

Not on the map. Why?

Abstract (arXiv)

The core challenge in unsupervised anomaly detection is identifying abnormal patterns without prior knowledge of their characteristics. While existing methods have addressed aspects of this problem, they often struggle to learn a robust representation of the normal data distribution that is distinct from anomalous patterns. In this paper, we present a novel framework, Unified Unsupervised Anomaly Detection (U2AD), that comprehensively addresses anomaly detection in multivariate time series. Our approach learns the underlying data distribution of normal samples by utilizing score-based generative modeling. We introduce a novel time-dependent score network and a unified training objective that together delineate the manifold of normal data while considering both local and global temporal contexts. Reconstruction is then performed via a deterministic sampling process using an ordinary differential equation solver. Our extensive experimental evaluations demonstrate that U2AD not only outperforms current state-of-the-art methods in detection accuracy but also identifies anomalies at significantly earlier stages of their occurrence.

Key facts. No citing papers in the map yet (data through 7 Oct 2026). Builds on 32 of its 62 references that are in the map. First posted on arXiv 10 May 2026.

Builds on

32 of 62 references.

References · 32

  1. 2017Attention Is All You Needcited by 59,932
  2. 2020Denoising Diffusion Probabilistic Modelscited by 20,851
  3. 2019PyTorch: An Imperative Style, High-Performance Deep Learning Librarycited by 20,160
  4. 2015U-Net: Convolutional Networks for Biomedical Image Segmentationcited by 19,604
  5. 2020Score-Based Generative Modeling through Stochastic Differential Equationscited by 8,964
  6. 2022TimesNet: Temporal 2D-Variation Modeling for General Time Series Analysiscited by 1,030
  7. 2021CSDI: Conditional Score-based Diffusion Models for Probabilistic Time Series Imputationcited by 577
  8. 2018Detecting Spacecraft Anomalies Using LSTMs and Nonparametric Dynamic Thresholdingcited by 407
  9. 2021Anomaly Transformer: Time Series Anomaly Detection with Association Discrepancycited by 387
  10. 2019Sliced Score Matching: A Scalable Approach to Density and Score Estimationcited by 381
  11. 2021Autoregressive Denoising Diffusion Models for Multivariate Probabilistic Time Series Forecastingcited by 332
  12. 2016A Kernelized Stein Discrepancy for Goodness-of-fit Tests and Model Evaluationcited by 236
20 more
  1. 2018Unsupervised Anomaly Detection via Variational Auto-Encoder for Seasonal KPIs in Web Applicationscited by 223
  2. 2022TranAD: Deep Transformer Networks for Anomaly Detection in Multivariate Time Series Datacited by 211
  3. 2017A Multimodal Anomaly Detector for Robot-Assisted Feeding Using an LSTM-based Variational Autoencodercited by 209
  4. 2018A Deep Neural Network for Unsupervised Anomaly Detection and Diagnosis in Multivariate Time Series Datacited by 181
  5. 2019MAD-GAN: Multivariate Anomaly Detection for Time Series Data with Generative Adversarial Networkscited by 176
  6. 2016Sequential Neural Models with Stochastic Layerscited by 115
  7. 2023DCdetector: Dual Attention Contrastive Representation Learning for Time Series Anomaly Detectioncited by 103
  8. 2022Deep Isolation Forest for Anomaly Detectioncited by 90
  9. 2023Generative Time Series Forecasting with Diffusion, Denoise, and Disentanglementcited by 89
  10. 2020Interacting particle solutions of Fokker-Planck equations through gradient-log-density estimationcited by 87
  11. 2021An Evaluation of Anomaly Detection and Diagnosis in Multivariate Time Seriescited by 68
  12. 2020TadGAN: Time Series Anomaly Detection Using Generative Adversarial Networkscited by 55
  13. 2021Neural Contextual Anomaly Detection for Time Seriescited by 42
  14. 2022Calibrated One-class Classification for Unsupervised Time Series Anomaly Detectioncited by 39
  15. 2023ImDiffusion: Imputed Diffusion Models for Multivariate Time Series Anomaly Detectioncited by 38
  16. 2020TAnoGAN: Time Series Anomaly Detection with Generative Adversarial Networkscited by 29
  17. 2019Learning Energy-Based Models in High-Dimensional Spaces with Multi-scale Denoising Score Matchingcited by 26
  18. 2023MEMTO: Memory-guided Transformer for Multivariate Time Series Anomaly Detectioncited by 26
  19. 2022TiSAT: Time Series Anomaly Transformercited by 15
  20. 2023MadSGM: Multivariate Anomaly Detection with Score-based Generative Modelscited by 1

Built on by

Not cited yet.

Similar, not cited

Close in wording, no citation either way

  1. 2025Physics-Informed Diffusion Models for Unsupervised Anomaly Detection in Multivariate Time Series
  2. 2026LEARN-TS: LLM-Enhanced Alignment and Reconstruction with Normality Guidance for Multivariate Time-Series Anomaly Detection
  3. 2026LLM-Generated Feature Pools for Time Series Anomaly Detection
  4. 2023Contaminated Multivariate Time-Series Anomaly Detection with Spatio-Temporal Graph Conditional Diffusion Models
  5. 2025Towards Foundation Models for Zero-Shot Time Series Anomaly Detection: Leveraging Synthetic Data and Relative Context Discrepancy
  6. 2026CARE: A Cascaded Framework for Efficient and Reliable Time Series Anomaly Detection
  7. 2026Detecting Time Series Anomalies Like an Expert: A Multi-Agent LLM Framework with Specialized Analyzers
  8. 2026FirstDiff: One-Step Diffusion-Based Anomaly Detection for Multivariate Time Series via Initial Noise Prediction