Multivariate time series anomaly detection improves with correlation aware reconstruction
Correlation-Aware Reconstruction for Multivariate Time Series Anomaly Detection
Machine Learning
Summary
Detecting unusual patterns in data streams from many sensors at once is hard because sometimes the sensors look fine individually, but their combined behavior is off. The authors propose a new detection method that separately learns how each sensor changes over time and how sensors relate to each other, then combines these insights to spot anomalies better. They tested their method on a large benchmark and found it outperforms many existing approaches. This helps catch subtle joint anomalies that older methods might miss.
What this means in practice
- •For industrial monitoring teams: Identify subtle faults in complex sensor networks by detecting anomalies in inter-sensor relationships, improving early warning systems for manufacturing or energy plants.
- •For financial fraud detection teams: Detect anomalies in multiple financial indicators that individually seem normal but collectively indicate suspicious activity, enhancing fraud monitoring systems.
Authors
Md. Johir Raihan, Zahra Zamanzadeh Darban, Yueyang Liu, Flora D. Salim, Levin Kuhlmann, Mahsa Salehi
Abstract
Reconstruction-based detectors for multivariate time series anomaly detection typically learn a single entangled representation of normal behavior and flag anomalies based on reconstruction error. However, real-world anomalies are not only isolated spikes in a single channel but also disruptions in the relationships between channels, where each sensor individually appears normal, but their joint behavior deviates from the norm. Because these models compress both temporal evolution and inter-channel structure into this single space, they lack an explicit mechanism to isolate such inter-channel dependencies from normal temporal dependencies, leading to lower detection rates for cross-channel anomalies. We propose CARMA (Correlation-Aware Reconstruction for Multivariate Time Series Anomaly Detection), which is a reconstruction-based variational autoencoder with two complementary latent spaces: a temporal latent that captures sequential dynamics, and a correlation latent that is trained to reconstruct the window's pairwise Pearson correlations. Both representations are fused in the signal decoder, and anomalies are detected from the reconstruction error. We evaluate CARMA on the TSB-AD-M benchmark suite (17 datasets, 180 series) against 29 baseline methods, and show that it significantly outperforms all of them across multiple threshold-free and range-aware metrics, achieving a VUS-PR of 0.4929. Ablations show that removing the correlation branch degrades performance, that adding a second latent without supervision recovers only part of the gain, and that supervising the correlation latent with an explicit correlation target accounts for the rest and produces a sharper error response at anomalies.