Unsupervised Time Series Anomaly Prediction with Importance-based Generative Contrastive Learning
This addresses the need for anomaly prediction in scenarios like environmental prevention and cyber-physical systems without requiring labeled data, though it is incremental as it builds on existing unsupervised and contrastive learning approaches.
The paper tackles the problem of unsupervised time series anomaly prediction, which is challenging due to the lack of labeled data and unseen anomalies, and proposes IGCL to outperform state-of-the-art baselines on seven benchmark datasets.
Time series anomaly prediction plays an essential role in many real-world scenarios, such as environmental prevention and prompt maintenance of cyber-physical systems. However, existing time series anomaly prediction methods mainly require supervised training with plenty of manually labeled data, which are difficult to obtain in practice. Besides, unseen anomalies can occur during inference, which could differ from the labeled training data and make these models fail to predict such new anomalies. In this paper, we study a novel problem of unsupervised time series anomaly prediction. We provide a theoretical analysis and propose Importance-based Generative Contrastive Learning (IGCL) to address the aforementioned problems. IGCL distinguishes between normal and anomaly precursors, which are generated by our anomaly precursor pattern generation module. To address the efficiency issues caused by the potential complex anomaly precursor combinations, we propose a memory bank with importance-based scores to adaptively store representative anomaly precursors and generate more complicated anomaly precursors. Extensive experiments on seven benchmark datasets show our method outperforms state-of-the-art baselines on unsupervised time series anomaly prediction problems.