Beyond Marginals: Learning Joint Spatio-Temporal Patterns for Multivariate Anomaly Detection
This addresses the challenge of detecting subtle anomalies in multivariate time series for applications like monitoring systems, though it appears incremental by building on existing techniques like transformers and copulas.
The paper tackles the problem of multivariate anomaly detection by modeling time-varying non-linear spatio-temporal correlations in time series data, achieving improved performance through a method that decouples marginal distributions, temporal dynamics, and inter-variable dependencies using a transformer encoder and copula-based likelihood.
In this paper, we aim to improve multivariate anomaly detection (AD) by modeling the \textit{time-varying non-linear spatio-temporal correlations} found in multivariate time series data . In multivariate time series data, an anomaly may be indicated by the simultaneous deviation of interrelated time series from their expected collective behavior, even when no individual time series exhibits a clearly abnormal pattern on its own. In many existing approaches, time series variables are assumed to be (conditionally) independent, which oversimplifies real-world interactions. Our approach addresses this by modeling joint dependencies in the latent space and decoupling the modeling of \textit{marginal distributions, temporal dynamics, and inter-variable dependencies}. We use a transformer encoder to capture temporal patterns, and to model spatial (inter-variable) dependencies, we fit a multi-variate likelihood and a copula. The temporal and the spatial components are trained jointly in a latent space using a self-supervised contrastive learning objective to learn meaningful feature representations to separate normal and anomaly samples.