Federated Learning for Multivariate Time Series Anomaly Detection in Industrial Automation

Khayyam Nosrati; Martin Uray; Saverio Messineo; Olaf Sassnick; Stefan Huber

Federated Learning for Multivariate Time Series Anomaly Detection in Industrial Automation

Machine Learning 2026-05-28 v1

Authors: Khayyam Nosrati , Martin Uray , Saverio Messineo , Olaf Sassnick , Stefan Huber

Abstract

Federated learning (FL) has broadened the horizon for multivariate time series anomaly detection (MTSAD). However, benchmarking such anomaly detection methods within FL paradigm poses data-centric challenges. The existing datasets do not counteract these challenges since they do not simultaneously provide sufficient scale, accurate labels, and freedom from common flaws. In addition, the role of cyclic process behavior, which is common in discrete industrial automation, remains underexplored for MTSAD for the current state of research. This paper aims to shed more light on the literature and address these gaps by introducing a dataset designed with cyclic dynamics arising from the repetitive nature of discrete automation processes and evaluates selected MTSAD methods on both the proposed dataset and a public benchmark dataset.

Keywords

federated learning anomaly detection time series classification

Cite

@article{arxiv.2605.27486,
  title  = {Federated Learning for Multivariate Time Series Anomaly Detection in Industrial Automation},
  author = {Khayyam Nosrati and Martin Uray and Saverio Messineo and Olaf Sassnick and Stefan Huber},
  journal= {arXiv preprint arXiv:2605.27486},
  year   = {2026}
}

Comments

Preprint. Accepted at the DEXA International Workshop on Optimisation of Industrial Production with AI Algorithms 2026 (DEXA AI4IP 2026)

Federated Learning for Multivariate Time Series Anomaly Detection in Industrial Automation

Abstract

Keywords

Cite

Comments

Related papers