TDSRL: Time Series Dual Self-Supervised Representation Learning for Anomaly Detection From Different Perspectives

Anomaly detection in time series is crucial for applications ranging from finance to industrial monitoring. Effective models need to capture both the inherent characteristics of time series data and the distinct patterns of anomalies. While traditional forecasting-based and reconstruction-based approaches have been successful, they tend to struggle with complex and evolving anomalies. For instance, stock market data exhibits ever-changing fluctuation patterns that defy straightforward modeling. In this article, we propose a novel method called Time Series Dual Self-Supervised Representation Learning (TDSRL) for robust anomaly detection. TDSRL attach great importance to the frequency domain information throughout the anomaly modeling process. We introduce a data degradation method that simulates real-world anomalies more naturally by operating in both time and frequency domains. Additionally, the key innovations also lie in dual self-supervised pretext tasks: one task characterises anomalies in relation to the entire time series, and the other focuses on local anomaly boundaries using contrastive learning. This significantly improves the network’s discrimination between anomaly and adjacent normal intervals. Consequently, TDSRL is expected to achieve a faster and stronger response to the anomalies, with the potential for early detection. Experimental results show that TDSRL outperforms state-of-the-art methods, making it a promising new direction for time series anomaly detection. The code of this article is available here: https://github.com/ys-Dai/TDSRL/tree/main.