基于储备池状态分析的联邦学习用于时间序列异常检测
Federated Learning with Reservoir State Analysis for Time Series Anomaly Detection
AI总结：
本文提出增量联邦学习方法 IncFed MD-RS，通过共享并迭代更新储备池状态的马氏距离统计参数，在保护隐私的同时高效检测时间序列异常。
摘要：
随着数据隐私担忧日益增加，联邦学习已成为一种颇具前景的框架，可在不共享本地分布式数据的情况下训练机器学习模型。在联邦学习中，多个客户端进行本地模型训练、服务器进行模型集成，这一过程仅通过模型参数共享来重复进行。现有的大多数联邦学习方法都假设训练深度学习模型，而这类模型通常计算需求很高。为解决这一问题，我们提出了带有储备池状态分析的联邦学习方法，以同时追求计算效率和数据隐私保护。具体而言，我们的方法依赖于面向时间序列异常检测的储备池状态马哈拉诺比斯距离（Mahalanobis Distance of Reservoir States，MD-RS）方法，该方法学习正常输入的储备池状态分布，并基于与所学分布的偏差来检测异常。对 MD-RS 中统计参数的迭代更新使增量联邦学习（IncFed MD-RS）成为可能。我们使用时间序列异常检测的基准数据集评估了 IncFed MD-RS 的性能。结果表明，尤其在客户端数据相对较短且具有异构性时，IncFed MD-RS 优于其他采用深度学习和储备池计算模型的联邦学习方法。我们证明，与其他方法相比，IncFed MD-RS 对样本数据减少具有鲁棒性。我们还表明，通过对储备池状态进行子采样，可以在不降低性能的情况下减少 IncFed MD-RS 的计算成本。所提出的方法尤其适用于要求计算效率、算法简单性和低通信成本的异常检测应用。
英文摘要：
With a growing data privacy concern, federated learning has emerged as a promising framework to train machine learning models without sharing locally distributed data. In federated learning, local model training by multiple clients and model integration by a server are repeated only through model parameter sharing. Most existing federated learning methods assume training deep learning models, which are often computationally demanding. To deal with this issue, we propose federated learning methods with reservoir state analysis to seek computational efficiency and data privacy protection simultaneously. Specifically, our method relies on Mahalanobis Distance of Reservoir States (MD-RS) method targeting time series anomaly detection, which learns a distribution of reservoir states for normal inputs and detects anomalies based on a deviation from the learned distribution. Iterative updating of statistical parameters in the MD-RS enables incremental federated learning (IncFed MD-RS). We evaluate the performance of IncFed MD-RS using benchmark datasets for time series anomaly detection. The results show that IncFed MD-RS outperforms other federated learning methods with deep learning and reservoir computing models particularly when clients' data are relatively short and heterogeneous. We demonstrate that IncFed MD-RS is robust against reduced sample data compared to other methods. We also show that the computational cost of IncFed MD-RS can be reduced by subsampling from the reservoir states without performance degradation. The proposed method is beneficial especially in anomaly detection applications where computational efficiency, algorithm simplicity, and low communication cost are required.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
