<ul><li>DConAD is a differencing-based contrastive representation learning framework for time series anomaly detection.</li><li>It aims to capture robust and representative dependencies within time series for identifying anomalies.</li><li>DConAD generates differential data and utilizes transformer-based architecture to enhance the robustness of representation learning.</li><li>Experimental results demonstrate the superiority and effectiveness of DConAD compared to nine baselines.</li></ul>

DConAD: A Differencing-based Contrastive Representation Learning Framework for Time Series Anomaly Detection

Discover more