A Triple-Step Asynchronous Federated Learning Mechanism for Client Activation, Interaction Optimization, and Aggregation Enhancement
作者:You, Linlin; Liu, Sheng; Chang, Yi; Yuen, Chau
期刊:IEEE Internet of Things Journal, Volume 9, Issue 23, Pages 24199-24211, December 1, 2022 (中科院一区 国际top期刊)
Abstract:Federated Learning in asynchronous mode (AFL) is attracting much attention from both industry and academia to build intelligent cores for various Internet of Things (IoT) systems and services by harnessing sensitive data and idle computing resources dispersed at massive IoT devices in a privacy-preserving and interaction-unblocking manner. Since AFL is still in its infancy, it encounters three challenges that need to be resolved jointly, namely: 1) how to rationally utilize AFL clients, whose local data grow gradually, to avoid overlearning issues; 2) how to properly manage the client-server interaction with both communication cost reduced and model performance improved; and finally, 3) how to effectively and efficiently aggregate heterogeneous parameters received at the server to build a global model. To fill the gap, this article proposes a triple-step asynchronous federated learning mechanism (TrisaFed), which can: 1) activate clients with rich information according to an informative client activating strategy (ICA); 2) optimize the client-server interaction by a multiphase layer updating strategy (MLU); and 3) enhance the model aggregation function by a temporal weight fading strategy (TWF), and an informative weight enhancing strategy (IWE). Moreover, based on four standard data sets, TrisaFed is evaluated. As shown by the result, compared with four state-of-the-art baselines, TrisaFed can not only dramatically reduce the communication cost by over 80% but also can significantly improve the learning performance in terms of model accuracy and training speed by over 8% and 70%, respectively.
Keywords:client-server systems,cloud computing,computer network security,data privacy,Internet of Things,learning (artificial intelligence),resource allocation
摘要:异步模式下的联合学习( AFL )通过利用分散在海量物联网设备中的敏感数据和空闲计算资源，以隐私保护和交互畅通的方式为各种物联网系统和服务构建智能核心，正引起工业界和学术界的广泛关注。由于AFL尚处于起步阶段，它面临着三个需要共同解决的挑战，即：1 )如何合理利用本地数据逐渐增长的AFL客户，避免过度学习问题；2 )如何合理地管理客户端与服务器之间的交互，减少通信开销，提高模型性能；最后，3 )如何有效且高效地聚合服务器端接收到的异构参数来构建全局模型。为此，本文提出一种三步异步联邦学习机制( Trisa Fed )，该机制可以：1 )根据信息性客户端激活策略( ICA )激活信息丰富的客户端；2 )采用多阶段层更新策略( MLU )优化客户端-服务器交互；3 )通过时间权重衰减策略( TWF )和信息权重增强策略( IWE )增强模型聚合函数。此外，基于四个标准数据集对TrisaFed进行评估。结果表明，与4个最先进的基线相比，Trisa Fed不仅可以显著降低80 %以上的通信成本，而且可以显著提高模型精度和训练速度，分别提高8 %和70 %以上。
关键字:客服-服务系统,云计算,计算机网络安全,数据隐私,物联网,人工智能,资源分配
DOI:10.1109/JIOT.2022.3188556
原文链接:https://ieeexplore.ieee.org/document/9815310/keywords#keywords
注意：欢迎转载，转载时请注明来源
