Dynamic Circular Network-Based Federated Dual-View Learning for Multivariate Time Series Anomaly Detection

Multivariate time-series data exhibit intricate correlations in both temporal and spatial dimensions. However, existing network architectures often overlook dependencies in the spatial dimension and struggle to strike a balance between long-term and short-term patterns when extracting features from the data. Furthermore, industries within the business community are hesitant to share their raw data, which hinders anomaly prediction accuracy and detection performance. To address these challenges, the authors propose a dynamic circular network-based federated dual-view learning approach. Experimental results from four open-source datasets demonstrate that the method outperforms existing methods in terms of accuracy, recall, and F1_score for anomaly detection.