A Parameter-Efficient Federated Framework for Streaming Time Series Anomaly Detection via Lightweight Adaptation

With the proliferation of mobile sensing techniques, huge amounts of time series data are continuously generated and accumulated in various domains, fueling considerable real-world mobile computing applications. In this context, time series anomaly detection is practically important. It endeavors to identify deviant samples from the normal distribution in time series data. Existing approaches generally assume that all the time series data is available at a central location. However, with the increasing deployment of edge devices, we are witnessing a decentralized collection of time series data. To bridge the gap between decentralized data and centralized anomaly detection algorithms, we propose a Parameter-efficient Federated Anomaly Detection framework via Lightweight Adaptation (PeFAD-LA) that addresses growing privacy concerns. PeFAD-LA innovatively employs a pre-trained large language model (PLM or LLM) as the core of the client's local model, which can benefit from its cross-modality knowledge transfer capability. To reduce the communication overhead and the local model adaptation cost, we propose a parameter-efficient federated training module that requires clients to fine-tune only small-scale parameters and transmit them to the server for updates. Further, to handle anomalies in streaming time series, a lightweight adaptation module is employed to overcome concept drift. PeFAD-LA utilizes an anomaly-driven mask selection strategy to mitigate the impact of neglected anomalies during training. A novel dual knowledge transfer mechanism is designed to harness the useful knowledge across clients and sequentially learned data. Extensive experiments on real data offer evidence of the effectiveness and efficiency of the proposed framework.