Forecast-based Multi-aspect Framework for Multivariate Time-series Anomaly Detection

TL;DR

This paper introduces FMUAD, a novel unsupervised multivariate time-series anomaly detection framework that separately captures different anomaly traits and outperforms existing forecast-based methods.

Contribution

The paper presents FMUAD, a flexible multi-aspect framework that explicitly models various anomaly types with independent modules, improving detection accuracy.

Findings

FMUAD outperforms state-of-the-art forecast-based anomaly detectors.

The framework effectively captures spatial, temporal, and correlation anomalies.

Extensive experiments validate its superior performance across datasets.

Abstract

Today's cyber-world is vastly multivariate. Metrics collected at extreme varieties demand multivariate algorithms to properly detect anomalies. However, forecast-based algorithms, as widely proven approaches, often perform sub-optimally or inconsistently across datasets. A key common issue is they strive to be one-size-fits-all but anomalies are distinctive in nature. We propose a method that tailors to such distinction. Presenting FMUAD - a Forecast-based, Multi-aspect, Unsupervised Anomaly Detection framework. FMUAD explicitly and separately captures the signature traits of anomaly types - spatial change, temporal change and correlation change - with independent modules. The modules then jointly learn an optimal feature representation, which is highly flexible and intuitive, unlike most other models in the category. Extensive experiments show our FMUAD framework consistently outperforms other state-of-the-art forecast-based anomaly detectors.