EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

MLAD: A Multi-Task Learning Framework for Anomaly Detection

Kunqi Li iD, Zhiqin Tang iD, Shuming Liang iD, Zhidong Li iD, Bin Liang iD

Sensors · 01.07.2025 · 25 (13) · 4115

DOI: 10.3390/s25134115 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Sensors, online erschienen am 01.07.2025. Verfasst von Kunqi Li und 4 weiteren Autor:innen. Beteiligte Einrichtung: Faculty of Engineering and IT, University of Technology Sydney, 15 Broadway, Sydney, NSW 2007, Australia. Die Arbeit wurde bisher 4-mal zitiert (Crossref) und nennt 32 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0).

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Anomaly detection in multivariate time series is a critical task across a range of real-world domains, such as industrial automation and the internet of things. These environments are generally monitored by various types of sensors that produce complex, high-dimensional time-series data with intricate cross-sensor dependencies. While existing methods often utilize sequence modeling or graph neural networks to capture global sensor relationships, they typically treat all sensors uniformly—potentially overlooking the benefit of grouping sensors with similar temporal patterns. To this end, we propose a novel framework called Multi-task Learning Anomaly Detection (MLAD), which leverages clustering techniques to group sensors based on their temporal characteristics, and employs a multi-task learning paradigm to jointly capture both shared patterns across all sensors and specialized patterns within each cluster. MLAD consists of four key modules: (1) sensor clustering based on sensors’ time series, (2) representation learning with a cluster-constrained graph neural network, (3) multi-task forecasting with shared and cluster-specific learning layers, and (4) anomaly scoring. Extensive experiments on three public datasets demonstrate that MLAD achieves superior detection performance over state-of-the-art baselines. Ablation studies further validate the effectiveness of the modules of our MLAD. This study highlights the value of incorporating sensor heterogeneity into model design, which contributes to more accurate and robust anomaly detection in sensor-based monitoring systems.

Schlagwörter

Stichwörter der Autor:innen

anomaly detectiongraph neural networksmulti-task learningmultivariate time seriessensor clustering

Autor:innen und Institutionen

  • Faculty of Engineering and IT, University of Technology Sydney, 15 Broadway, Sydney, NSW 2007, Australia.

ORCID-Profile: Kunqi Li, Zhiqin Tang, Shuming Liang, Zhidong Li, Bin Liang

Zitieren

APA

Li, K., Tang, Z., Liang, S., Li, Z., & Liang, B. (2025). MLAD: A Multi-Task Learning Framework for Anomaly Detection. Sensors, 25(13), 4115. https://doi.org/10.3390/s25134115

Vancouver

Li K, Tang Z, Liang S, Li Z, Liang B. MLAD: A Multi-Task Learning Framework for Anomaly Detection. Sensors. 2025;25(13):4115. doi:10.3390/s25134115

BibTeX
@article{Li2025,
  author = {Li, Kunqi and Tang, Zhiqin and Liang, Shuming and Li, Zhidong and Liang, Bin},
  title = {MLAD: A Multi-Task Learning Framework for Anomaly Detection},
  journal = {Sensors},
  year = {2025},
  volume = {25},
  number = {13},
  pages = {4115},
  doi = {10.3390/s25134115}
}
Kostenlos starten →