MadSGM: Multivariate Anomaly Detection with Score-based Generative Models

TL;DR

MadSGM introduces a novel multivariate time-series anomaly detection method using score-based generative models, integrating multiple anomaly measurement factors for improved robustness and accuracy in unsupervised settings.

Contribution

It proposes MadSGM, a new anomaly detection approach that combines reconstruction, density, and gradient-based measurements with a conditional score network.

Findings

Outperforms existing methods on five benchmark datasets.

Achieves the most robust and accurate anomaly detection results.

Effectively integrates multiple anomaly measurement factors.

Abstract

The time-series anomaly detection is one of the most fundamental tasks for time-series. Unlike the time-series forecasting and classification, the time-series anomaly detection typically requires unsupervised (or self-supervised) training since collecting and labeling anomalous observations are difficult. In addition, most existing methods resort to limited forms of anomaly measurements and therefore, it is not clear whether they are optimal in all circumstances. To this end, we present a multivariate time-series anomaly detector based on score-based generative models, called MadSGM, which considers the broadest ever set of anomaly measurement factors: i) reconstruction-based, ii) density-based, and iii) gradient-based anomaly measurements. We also design a conditional score network and its denoising score matching loss for the time-series anomaly detection. Experiments on five real-world benchmark datasets illustrate that MadSGM achieves the most robust and accurate predictions.