Anomaly Detection for Sparse and Irregular Multivariate Time Series with Latent SDEs

2026-06-17

AI Summary

This work addresses the challenge of anomaly detection in sparse, irregularly sampled, or partially observed multivariate time series—a setting where existing methods often fail due to their reliance on uniform sampling assumptions. To overcome this limitation, the paper introduces latent stochastic differential equations (Latent SDEs) into multivariate time series anomaly detection for the first time, formulating a continuous-time generative model that naturally accommodates missing values and non-uniform observations. By integrating variational inference with neural networks, the approach effectively captures latent periodic dynamics while modeling temporal irregularities. Evaluated on six standard benchmarks, the proposed method achieves state-of-the-art performance, demonstrating particularly significant gains under high sparsity and exhibiting superior robustness and adaptability compared to current baselines.

Abstract

Multivariate time series anomaly detection (MTSAD) is critical for a wide range of application areas, such as industrial monitoring, cybersecurity, or healthcare. Real-world data is often sparse, irregularly sampled or partially observed, yet existing methods assume uniformly sampled time series. We propose a generative approach based on Latent SDEs that projects the observed time series on a continuous-time stochastic dynamical system, directly being able to handle missing observations and irregular sampling, while also naturally capturing possible cyclic behavior that many real-world use cases inherently possess. Experiments on six anomaly benchmark datasets show that our proposed method ranks first among state-of-the-art baselines. We further demonstrate that our method remains robust under severe data sparsity, while performance significantly degrades for the tested baseline methods. These results highlight latent SDEs as a natural inductive bias for anomaly detection in multivariate time series, especially in presence of real-world irregularities.

Problem

• anomaly detection
• sparse time series
• irregular sampling
• multivariate time series
• missing observations

Innovation

• Latent SDEs
• anomaly detection
• irregular time series
• multivariate time series
• generative modeling