mlsanityData to 14 Oct 2026

Benchmarking Unsupervised Strategies for Anomaly Detection in Multivariate Time Series

arXiv 2506.20574 ↗First posted 25 Jun 2025cs.LG stat.MEcited by 1

Not on the map. Why?

Abstract (arXiv)

Anomaly detection in multivariate time series is an important problem across various fields such as healthcare, financial services, manufacturing or physics detector monitoring. Accurately identifying when unexpected errors or faults occur is essential, yet challenging, due to the unknown nature of anomalies and the complex interdependencies between time series dimensions. In this paper, we investigate transformer-based approaches for time series anomaly detection, focusing on the recently proposed iTransformer architecture. Our contributions are fourfold: (i) we explore the application of the iTransformer to time series anomaly detection, and analyse the influence of key parameters such as window size, step size, and model dimensions on performance; (ii) we examine methods for extracting anomaly labels from multidimensional anomaly scores and discuss appropriate evaluation metrics for such labels; (iii) we study the impact of anomalous data present during training and assess the effectiveness of alternative loss functions in mitigating their influence; and (iv) we present a comprehensive comparison of several transformer-based models across a diverse set of datasets for time series anomaly detection.

Key facts. Cited by 1 paper in the map (data through 14 Oct 2026). Builds on 24 of its 68 references that are in the map. First posted on arXiv 25 Jun 2025.

Builds on

24 of 68 references.

References · 24

  1. 2017Attention Is All You Needcited by 60,361
  2. 2022Generative Adversarial Networkscited by 5,627
  3. 2022Are Transformers Effective for Time Series Forecasting?cited by 1,424
  4. 2023iTransformer: Inverted Transformers Are Effective for Time Series Forecastingcited by 931
  5. 2022Transformers in Time Series: A Surveycited by 497
  6. 2020Evaluation: from precision, recall and F-measure to ROC, informedness, markedness and correlationcited by 425
  7. 2018Detecting Spacecraft Anomalies Using LSTMs and Nonparametric Dynamic Thresholdingcited by 410
  8. 2021Anomaly Transformer: Time Series Anomaly Detection with Association Discrepancycited by 394
  9. 2019Deep Learning for Anomaly Detection: A Surveycited by 358
  10. 2023Long-term Forecasting with TiDE: Time-series Dense Encodercited by 332
  11. 2021Graph Neural Network-Based Anomaly Detection in Multivariate Time Seriescited by 301
  12. 2017Soft-DTW: a Differentiable Loss Function for Time-Seriescited by 271
12 more
  1. 2022ADBench: Anomaly Detection Benchmarkcited by 232
  2. 2022TranAD: Deep Transformer Networks for Anomaly Detection in Multivariate Time Series Datacited by 214
  3. 2019Are We Really Making Much Progress? A Worrying Analysis of Recent Neural Recommendation Approachescited by 185
  4. 2020Multivariate Time-series Anomaly Detection via Graph Attention Networkcited by 167
  5. 2020Current Time Series Anomaly Detection Benchmarks are Flawed and are Creating the Illusion of Progresscited by 151
  6. 2022Deep Learning for Time Series Anomaly Detection: A Surveycited by 131
  7. 2021Learning Graph Structures with Transformer for Multivariate Time Series Anomaly Detection in IoTcited by 104
  8. 2021Towards a Rigorous Evaluation of Time-series Anomaly Detectioncited by 97
  9. 2020Anomaly Detection in Univariate Time-series: A Survey on the State-of-the-Artcited by 56
  10. 2022Transformers in Time-series Analysis: A Tutorialcited by 46
  11. 2021Do We Really Need Deep Learning Models for Time Series Forecasting?cited by 45
  12. 2014Metric Learning for Temporal Sequence Alignmentcited by 4

Built on by

Cited by year

Citing papers per year: 2025: 1.

1 paper.

  1. 2025Synthetic Data Generation with Lorenzetti for Time Series Anomaly Detection in High-Energy Physics Calorimeterscited by 0