no code implementations • 1 Nov 2022 • Jun Zhan, Chengkun Wu, Canqun Yang, Qiucheng Miao, Xiandong Ma
In this paper, we propose a novel semi-supervised anomaly detection framework based on a heterogeneous feature network (HFN) for MTS, learning heterogeneous structure information from a mass of unlabeled time-series data to improve the accuracy of anomaly detection, and using attention coefficient to provide an explanation for the detected anomalies.