Causality-Aware Contrastive Learning for Robust Multivariate Time-Series Anomaly Detection

TL;DR

This paper introduces CAROTS, a causality-aware contrastive learning approach that enhances multivariate time-series anomaly detection by leveraging causal relationships to distinguish normal and abnormal patterns.

Contribution

It proposes a novel contrastive learning pipeline that incorporates causality-preserving and -disturbing data augmentations to improve anomaly detection in multivariate time-series.

Findings

CAROTS outperforms existing methods on multiple real-world datasets.

Causality-aware augmentation improves anomaly detection accuracy.

The method effectively separates normal and abnormal samples based on causal relationships.

Abstract

Utilizing the complex inter-variable causal relationships within multivariate time-series provides a promising avenue toward more robust and reliable multivariate time-series anomaly detection (MTSAD) but remains an underexplored area of research. This paper proposes Causality-Aware contrastive learning for RObust multivariate Time-Series (CAROTS), a novel MTSAD pipeline that incorporates the notion of causality into contrastive learning. CAROTS employs two data augmentors to obtain causality-preserving and -disturbing samples that serve as a wide range of normal variations and synthetic anomalies, respectively. With causality-preserving and -disturbing samples as positives and negatives, CAROTS performs contrastive learning to train an encoder whose latent space separates normal and abnormal samples based on causality. Moreover, CAROTS introduces a similarity-filtered one-class contrastive loss that encourages the contrastive learning process to gradually incorporate more semantically diverse samples with common causal relationships. Extensive experiments on five real-world and two synthetic datasets validate that the integration of causal relationships endows CAROTS with improved MTSAD capabilities. The code is available at https://github.com/kimanki/CAROTS.