Deep Variational Graph Convolutional Recurrent Network for Multivariate Time Series Anomaly Detection

Anomaly detection within multivariate time series (MTS) is an essential task in both data mining and service quality management. Many recent works on anomaly detection focus on designing unsupervised probabilistic models to extract robust normal patterns of MTS. In this paper, we model channel dependency and stochasticity within MTS by developing an embedding-guided probabilistic generative network. We combine it with adaptive Variational Graph Convolutional Recurrent Network (VGCRN) to model both spatial and temporal fine-grained correlations in MTS. To explore hierarchical latent representations, we further extend VGCRN into a deep variational network, which captures multilevel information at different layers and is robust to noisy time series. Moreover, we develop an upwarddownward variational inference scheme that considers both forecasting-based and reconstructionbased losses, achieving an accurate posterior approximation of latent variables with better MTS representations. The experiments verify the superiority of the proposed method over the current state of the art.