Masked Graph Neural Networks for Unsupervised Anomaly Detection in Multivariate Time Series

• Published in: Sensors (Basel, Switzerland) Vol. 23; no. 17; p. 7552
• Main Authors: Xu, Kang, Li, Yuan, Li, Yixuan, Xu, Liyan, Li, Ruiyao, Dong, Zhenjiang
• Format: Journal Article
• Language: English
• Published: Basel MDPI AG 31.08.2023; MDPI
• Subjects: Analysis; Deep learning; Forecasts and trends; graph neural network; Internet of Things; Kao Tsu, Emperor of China; masked strategy; multivariate time series; Neural networks; Sensors; Time series; unsupervised anomaly detection; Germany
• ISSN: 1424-8220; 1424-8220
• DOI: 10.3390/s23177552

Anomaly detection has been widely used in grid operation and maintenance, machine fault detection, and so on. In these applications, the multivariate time-series data from multiple sensors with latent relationships are always high-dimensional, which makes multivariate time-series anomaly detection particularly challenging. In existing unsupervised anomaly detection methods for multivariate time series, it is difficult to capture the complex associations among multiple sensors. Graph neural networks (GNNs) can model complex relations in the form of a graph, but the observed time-series data from multiple sensors lack explicit graph structures. GNNs cannot automatically learn the complex correlations in the multivariate time-series data or make good use of the latent relationships among time-series data. In this paper, we propose a new method—masked graph neural networks for unsupervised anomaly detection (MGUAD). MGUAD can learn the structure of the unobserved causality among sensors to detect anomalies. To robustly learn the temporal context from adjacent time points of time-series data from the same sensor, MGUAD randomly masks some points of the time-series data from the sensor and reconstructs the masked time points. Similarly, to robustly learn the graph-level context from adjacent nodes or edges in the relation graph of multivariate time series, MGUAD masks some nodes or edges in the graph under the framework of a GNN. Comprehensive experiments are conducted on three public datasets. According to the experimental findings, MGUAD outperforms state-of-the-art anomaly detection methods.