%0 Conference Proceedings
%T UCBFed: Using Reinforcement Learning Method to Tackle the Federated Optimization Problem
%+ Chinese Academy of Sciences [Beijing] (CAS)
%+ University of Chinese Academy of Sciences [Beijing] (UCAS)
%A Chen, Wanqi
%A Zhou, Xin
%Z Part 3: Distributed Algorithms
%< avec comité de lecture
%( Lecture Notes in Computer Science
%B 21th IFIP International Conference on Distributed Applications and Interoperable Systems (DAIS)
%C Valletta, Malta
%Y Miguel Matos
%Y Fabíola Greve
%I Springer International Publishing
%3 Distributed Applications and Interoperable Systems
%V LNCS-12718
%P 99-105
%8 2021-06-14
%D 2021
%R 10.1007/978-3-030-78198-9_7
%K Federated learning
%K Upper Confidence Bound
%K Distributed learning
%K Optimization
%Z Computer Science [cs]
%Z Computer Science [cs]/Networking and Internet Architecture [cs.NI]Conference papers
%X Federated learning is a novel research area of AI technology that focus on distributed training and privacy preservation. Current federated optimization algorithms face serious challenge in the aspects of speed and accuracy, especially in non-i.i.d scenario. In this work, we propose UCBFed, a federated optimization algorithm that uses the Upper Confidence Bound (UCB) method to heuristically select participating clients in each round’s optimization process. We evaluate our algorithm in multiple federated distributed datasets. Comparing to most widely-used FedAvg and FedOpt, the UCBFed we proposed is superior in both the final accuracy and communication efficiency.
%G English
%Z TC 6
%Z WG 6.1
%2 https://inria.hal.science/hal-03384857/document
%2 https://inria.hal.science/hal-03384857/file/509420_1_En_7_Chapter.pdf
%L hal-03384857
%U https://inria.hal.science/hal-03384857
%~ IFIP-LNCS
%~ IFIP
%~ IFIP-TC
%~ IFIP-WG
%~ IFIP-TC6
%~ IFIP-WG6-1
%~ IFIP-DAIS
%~ IFIP-LNCS-12718