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

Wenchao Chen, Long Tian, Bo Chen, Liang Dai, Zhibin Duan, Mingyuan Zhou
Proceedings of the 39th International Conference on Machine Learning, PMLR 162:3621-3633, 2022.

Abstract

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 sensor dependency and stochasticity within MTS by developing an embedding-guided probabilistic generative network. We combine it with adaptive variational graph convolutional recurrent network %and get variational GCRN (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 upward-downward variational inference scheme that considers both forecasting-based and reconstruction-based losses, achieving an accurate posterior approximation of latent variables with better MTS representations. The experiments verify the superiority of the proposed method over current state-of-the-art methods.

Cite this Paper

BibTeX
@InProceedings{pmlr-v162-chen22x, title = {Deep Variational Graph Convolutional Recurrent Network for Multivariate Time Series Anomaly Detection}, author = {Chen, Wenchao and Tian, Long and Chen, Bo and Dai, Liang and Duan, Zhibin and Zhou, Mingyuan}, booktitle = {Proceedings of the 39th International Conference on Machine Learning}, pages = {3621--3633}, year = {2022}, editor = {Chaudhuri, Kamalika and Jegelka, Stefanie and Song, Le and Szepesvari, Csaba and Niu, Gang and Sabato, Sivan}, volume = {162}, series = {Proceedings of Machine Learning Research}, month = {17--23 Jul}, publisher = {PMLR}, pdf = {https://proceedings.mlr.press/v162/chen22x/chen22x.pdf}, url = {https://proceedings.mlr.press/v162/chen22x.html}, abstract = {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 sensor dependency and stochasticity within MTS by developing an embedding-guided probabilistic generative network. We combine it with adaptive variational graph convolutional recurrent network %and get variational GCRN (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 upward-downward variational inference scheme that considers both forecasting-based and reconstruction-based losses, achieving an accurate posterior approximation of latent variables with better MTS representations. The experiments verify the superiority of the proposed method over current state-of-the-art methods.} }
Endnote
%0 Conference Paper %T Deep Variational Graph Convolutional Recurrent Network for Multivariate Time Series Anomaly Detection %A Wenchao Chen %A Long Tian %A Bo Chen %A Liang Dai %A Zhibin Duan %A Mingyuan Zhou %B Proceedings of the 39th International Conference on Machine Learning %C Proceedings of Machine Learning Research %D 2022 %E Kamalika Chaudhuri %E Stefanie Jegelka %E Le Song %E Csaba Szepesvari %E Gang Niu %E Sivan Sabato %F pmlr-v162-chen22x %I PMLR %P 3621--3633 %U https://proceedings.mlr.press/v162/chen22x.html %V 162 %X 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 sensor dependency and stochasticity within MTS by developing an embedding-guided probabilistic generative network. We combine it with adaptive variational graph convolutional recurrent network %and get variational GCRN (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 upward-downward variational inference scheme that considers both forecasting-based and reconstruction-based losses, achieving an accurate posterior approximation of latent variables with better MTS representations. The experiments verify the superiority of the proposed method over current state-of-the-art methods.
APA
Chen, W., Tian, L., Chen, B., Dai, L., Duan, Z. & Zhou, M.. (2022). Deep Variational Graph Convolutional Recurrent Network for Multivariate Time Series Anomaly Detection. Proceedings of the 39th International Conference on Machine Learning, in Proceedings of Machine Learning Research 162:3621-3633 Available from https://proceedings.mlr.press/v162/chen22x.html.

Related Material