SGC-based Anomaly Detection for Multivariate Time Series

In industrial facilities or IT systems, there are lots of multivariate time series generated from various metrics. Anomaly detection in multivariate time series is of great importance in applications such as fault diagnosis and root cause discovery. Recently, some unsupervised methods have made great progress in this task, especially the reconstruction architecture of autoencoders AEs , learning normal distribution, and producing a significant error for anomalies. Although AEs can reconstruct subtle abnormal patterns well with the powerful generalization ability, it also leads to a high false negative. Moreover, these AE-based models ignore the dependence among variables at different time scales. In this paper, we propose an enhanced anomaly detection framework that builds upon the Multiscale Wavelet Graph Autoencoder MEGA by substituting the Graph Convolutional Network GCN with Simplified Graph Convolution SGC to augment the model's performance. The core idea is to leverage the spectral methods of SGC to process the multivariate time series data obtained by integrating Discrete Wavelet Transform DWT into the AE. Experiments have been conducted on three public multivariate time-series anomaly detection datasets. The results indicate that the improved model utilizing SGC performs comparably to MEGA, yet in certain scenarios, it may provide slightly better outcomes.