Evolving Proxy Kills Drift: Data-Efficient Streaming Time Series Anomaly Detection
Time series anomaly detection aims to identify samples that deviate from a normal sample distribution in a time series, enabling various web-centric applications. Most existing approaches are static, tar geting pre-defined types of anomalies. These methods thus fail to workwellonstreamingtimeserieswithchangingdatadistributions and anomaly formats. To contend with such streaming time series and to accommodate memory constraints, we propose the first data-efficient streaming time series anomaly detection framework, called DESS. To accumulate historical knowledge, DESS includes a novel evolving proxy generation module to synthesize a small but informative proxy summarizing the historical data, facilitating data efficiency. Next, DESS employs an innovative heterogeneous tem poral feature extraction module to explicitly capture correlations of multi-level time series semantics. Finally, DESS enables fast stream ing anomaly detection by employing a parameter-efficient training scheme that only activates a subset of lightweight parameters while ensuring performance. Extensive experiments on real data offer insight into the effectiveness and efficiency of DESS, showing that it is able to outperform the best baselines by up to 17.53% while reducing the training time by up to 64.88%.
