TFAD: A Decomposition Time Series Anomaly Detection Architecture with 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.

Accepted by the ACM International Conference on Information and Knowledge Management (CIKM 2022)

References in corpus (6)

• Time-Series Anomaly Detection Service at Microsoft
• An Evaluation of Anomaly Detection and Diagnosis in Multivariate Time Series
• TranAD: Deep Transformer Networks for Anomaly Detection in Multivariate Time Series Data
• Adaptive Performance Anomaly Detection for Online Service Systems via Pattern Sketching
• AutoAI-TS: AutoAI for Time Series Forecasting
• Online Time Series Anomaly Detection with State Space Gaussian Processes

Cited by in corpus (6)

• DCdetector: Dual Attention Contrastive Representation Learning for Time Series Anomaly Detection
• RCAgent: Cloud Root Cause Analysis by Autonomous Agents with Tool-Augmented Large Language Models
• Explainable Time Series Anomaly Detection using Masked Latent Generative Modeling
• Scalable Transformer for High Dimensional Multivariate Time Series Forecasting
• A Co-training Approach for Noisy Time Series Learning
• Noise-Resilient Point-wise Anomaly Detection in Time Series Using Weak Segment Labels