DCdetector: Dual Attention Contrastive Representation Learning for Time Series Anomaly Detection

Abstract

Time series anomaly detection is critical for a wide range of applications. It aims to identify deviant samples from the normal sample distribution in time series. The most fundamental challenge for this task is to learn a representation map that enables effective discrimination of anomalies. Reconstruction-based methods still dominate, but the representation learning with anomalies might hurt the performance with its large abnormal loss. On the other hand, contrastive learning aims to find a representation that can clearly distinguish any instance from the others, which can bring a more natural and promising representation for time series anomaly detection. In this paper, we propose DCdetector, a multi-scale dual attention contrastive representation learning model. DCdetector utilizes a novel dual attention asymmetric design to create the permutated environment and pure contrastive loss to guide the learning process, thus learning a permutation invariant representation with superior discrimination abilities. Extensive experiments show that DCdetector achieves state-of-the-art results on multiple time series anomaly detection benchmark datasets. Code is publicly available at https://github.com/DAMO-DI-ML/KDD2023-DCdetector.

Accepted by ACM SIGKDD International Conference on Knowledge Discovery & Data Mining (KDD 2023)

References in corpus (4)

• Time-Series Anomaly Detection Service at Microsoft
• Time Series Change Point Detection with Self-Supervised Contrastive Predictive Coding
• Series2Graph: Graph-based Subsequence Anomaly Detection for Time Series
• Local Evaluation of Time Series Anomaly Detection Algorithms

Cited by in corpus (6)

• Foundation Models for Time Series Analysis: A Tutorial and Survey
• A Comprehensive Survey of Deep Transfer Learning for Anomaly Detection in Industrial Time Series: Methods, Applications, and Directions
• DACAD: Domain Adaptation Contrastive Learning for Anomaly Detection in Multivariate Time Series
• A Review on Self-Supervised Learning for Time Series Anomaly Detection: Recent Advances and Open Challenges
• Noise-Resilient Point-wise Anomaly Detection in Time Series Using Weak Segment Labels
• TriP-LLM: A Tri-Branch Patch-wise Large Language Model Framework for Time-Series Anomaly Detection