DACAD: Domain Adaptation Contrastive Learning for Anomaly Detection in Multivariate Time Series

TL;DR

DACAD introduces a novel contrastive learning framework for multivariate time series anomaly detection that effectively transfers knowledge across domains and handles limited labeled data by combining supervised, self-supervised, and domain adaptation techniques.

Contribution

It proposes a new domain adaptation contrastive learning model with anomaly injection and a center-based entropy classifier for improved multivariate time series anomaly detection.

Findings

DACAD outperforms existing methods in cross-domain anomaly detection.

The anomaly injection mechanism enhances generalization to unseen anomalous classes.

DACAD demonstrates robustness with limited labeled data across multiple datasets.

Abstract

In time series anomaly detection (TSAD), the scarcity of labeled data poses a challenge to the development of accurate models. Unsupervised domain adaptation (UDA) offers a solution by leveraging labeled data from a related domain to detect anomalies in an unlabeled target domain. However, existing UDA methods assume consistent anomalous classes across domains. To address this limitation, we propose a novel Domain Adaptation Contrastive learning model for Anomaly Detection in multivariate time series (DACAD), combining UDA with contrastive learning. DACAD utilizes an anomaly injection mechanism that enhances generalization across unseen anomalous classes, improving adaptability and robustness. Additionally, our model employs supervised contrastive loss for the source domain and self-supervised contrastive triplet loss for the target domain, ensuring comprehensive feature representation learning and domain-invariant feature extraction. Finally, an effective Center-based Entropy Classifier (CEC) accurately learns normal boundaries in the source domain. Extensive evaluations on multiple real-world datasets and a synthetic dataset highlight DACAD's superior performance in transferring knowledge across domains and mitigating the challenge of limited labeled data in TSAD.