TFAD: A Decomposition Time Series Anomaly Detection Architecture with Time-Frequency Analysis

TL;DR

This paper introduces TFAD, a novel time-frequency analysis based architecture for time series anomaly detection that leverages both domains, incorporating decomposition and data augmentation to enhance performance and interpretability, achieving state-of-the-art results.

Contribution

The paper presents a new time-frequency based model for anomaly detection that integrates decomposition and data augmentation, addressing limitations of existing time-domain focused methods.

Findings

Achieves state-of-the-art performance on benchmark datasets.

Effective in both univariate and multivariate anomaly detection.

Improves interpretability through time-frequency analysis.

Abstract

Time series anomaly detection is a challenging problem due to the complex temporal dependencies and the limited label data. Although some algorithms including both traditional and deep models have been proposed, most of them mainly focus on time-domain modeling, and do not fully utilize the information in the frequency domain of the time series data. In this paper, we propose a Time-Frequency analysis based time series Anomaly Detection model, or TFAD for short, to exploit both time and frequency domains for performance improvement. Besides, we incorporate time series decomposition and data augmentation mechanisms in the designed time-frequency architecture to further boost the abilities of performance and interpretability. Empirical studies on widely used benchmark datasets show that our approach obtains state-of-the-art performance in univariate and multivariate time series anomaly detection tasks. Code is provided at https://github.com/DAMO-DI-ML/CIKM22-TFAD.