文献类型：期刊文献

英文题名：FedUR: Federated Learning Optimization Through Adaptive Centralized Learning Optimizers

作者：Zhang, Hengrun[1];Zeng, Kai[2];Lin, Shuai[3]

机构：[1]East China Univ Sci & Technol, Dept Comp Sci & Engn, Shanghai 200237, Peoples R China;[2]George Mason Univ, Dept Elect & Comp Engn, Fairfax, VA 22030 USA;[3]Shanghai Inst Technol, Sch Econ & Management, Shanghai 200235, Peoples R China

年份：2023

卷号：71

起止页码：2622

外文期刊名：IEEE TRANSACTIONS ON SIGNAL PROCESSING

收录：;EI(收录号：20232914403880);WOS:【SCI-EXPANDED(收录号:WOS:001041904500001)】；

语种：英文

外文关键词：Federated learning; momentum; adaptive learning rate; convergence performance; communication overhead

摘要：Introducing adaptiveness to federated learning has recently ushered in a new way to optimize its convergence performance. However, adaptive learning strategies originally designed in centralized machine learning are in na?ve extended to federated learning in existing works, which does not necessarily improve convergence performance and further reduce communication overhead as expected. In this paper, we fully investigate those centralized learning-based adaptive learning strategies, and propose an adaptive Federated learning algorithm targeting the model parameter Update Rule, called FedUR. Convergence upper bounds under FedUR are derived from the aspect of both local iterations and global aggregations. Through comparison with the convergence upper bounds of original federated learning, we theoretically analyze how those strategies should be tuned to help federated learning effectively optimize convergence performance and reduce overall communication overhead. Extensive experiments are conducted based on several real datasets and machine learning models, which show that FedUR can effectively increase final convergence accuracy with even lower communication overhead requirement.