Prototype-oriented unsupervised anomaly detection for multivariate time series

Yuxin Li, Wenchao Chen, Bo Chen, Dongsheng Wang, Long Tian, Mingyuan Zhou
Proceedings of the 40th International Conference on Machine Learning, PMLR 202:19407-19424, 2023.

Abstract

Unsupervised anomaly detection (UAD) of multivariate time series (MTS) aims to learn robust representations of normal multivariate temporal patterns. Existing UAD methods try to learn a fixed set of mappings for each MTS, entailing expensive computation and limited model adaptation. To address this pivotal issue, we propose a prototype-oriented UAD (PUAD) method under a probabilistic framework. Specifically, instead of learning the mappings for each MTS, the proposed PUAD views multiple MTSs as the distribution over a group of prototypes, which are extracted to represent a diverse set of normal patterns. To learn and regulate the prototypes, PUAD introduces a reconstruction-based unsupervised anomaly detection approach, which incorporates a prototype-oriented optimal transport method into a Transformer-powered probabilistic dynamical generative framework. Leveraging meta-learned transferable prototypes, PUAD can achieve high model adaptation capacity for new MTSs. Experiments on five public MTS datasets all verify the effectiveness of the proposed UAD method.

Cite this Paper

BibTeX
@InProceedings{pmlr-v202-li23d, title = {Prototype-oriented unsupervised anomaly detection for multivariate time series}, author = {Li, Yuxin and Chen, Wenchao and Chen, Bo and Wang, Dongsheng and Tian, Long and Zhou, Mingyuan}, booktitle = {Proceedings of the 40th International Conference on Machine Learning}, pages = {19407--19424}, year = {2023}, editor = {Krause, Andreas and Brunskill, Emma and Cho, Kyunghyun and Engelhardt, Barbara and Sabato, Sivan and Scarlett, Jonathan}, volume = {202}, series = {Proceedings of Machine Learning Research}, month = {23--29 Jul}, publisher = {PMLR}, pdf = {https://proceedings.mlr.press/v202/li23d/li23d.pdf}, url = {https://proceedings.mlr.press/v202/li23d.html}, abstract = {Unsupervised anomaly detection (UAD) of multivariate time series (MTS) aims to learn robust representations of normal multivariate temporal patterns. Existing UAD methods try to learn a fixed set of mappings for each MTS, entailing expensive computation and limited model adaptation. To address this pivotal issue, we propose a prototype-oriented UAD (PUAD) method under a probabilistic framework. Specifically, instead of learning the mappings for each MTS, the proposed PUAD views multiple MTSs as the distribution over a group of prototypes, which are extracted to represent a diverse set of normal patterns. To learn and regulate the prototypes, PUAD introduces a reconstruction-based unsupervised anomaly detection approach, which incorporates a prototype-oriented optimal transport method into a Transformer-powered probabilistic dynamical generative framework. Leveraging meta-learned transferable prototypes, PUAD can achieve high model adaptation capacity for new MTSs. Experiments on five public MTS datasets all verify the effectiveness of the proposed UAD method.} }
Endnote
%0 Conference Paper %T Prototype-oriented unsupervised anomaly detection for multivariate time series %A Yuxin Li %A Wenchao Chen %A Bo Chen %A Dongsheng Wang %A Long Tian %A Mingyuan Zhou %B Proceedings of the 40th International Conference on Machine Learning %C Proceedings of Machine Learning Research %D 2023 %E Andreas Krause %E Emma Brunskill %E Kyunghyun Cho %E Barbara Engelhardt %E Sivan Sabato %E Jonathan Scarlett %F pmlr-v202-li23d %I PMLR %P 19407--19424 %U https://proceedings.mlr.press/v202/li23d.html %V 202 %X Unsupervised anomaly detection (UAD) of multivariate time series (MTS) aims to learn robust representations of normal multivariate temporal patterns. Existing UAD methods try to learn a fixed set of mappings for each MTS, entailing expensive computation and limited model adaptation. To address this pivotal issue, we propose a prototype-oriented UAD (PUAD) method under a probabilistic framework. Specifically, instead of learning the mappings for each MTS, the proposed PUAD views multiple MTSs as the distribution over a group of prototypes, which are extracted to represent a diverse set of normal patterns. To learn and regulate the prototypes, PUAD introduces a reconstruction-based unsupervised anomaly detection approach, which incorporates a prototype-oriented optimal transport method into a Transformer-powered probabilistic dynamical generative framework. Leveraging meta-learned transferable prototypes, PUAD can achieve high model adaptation capacity for new MTSs. Experiments on five public MTS datasets all verify the effectiveness of the proposed UAD method.
APA
Li, Y., Chen, W., Chen, B., Wang, D., Tian, L. & Zhou, M.. (2023). Prototype-oriented unsupervised anomaly detection for multivariate time series. Proceedings of the 40th International Conference on Machine Learning, in Proceedings of Machine Learning Research 202:19407-19424 Available from https://proceedings.mlr.press/v202/li23d.html.

Related Material