Skip to Main content Skip to Navigation
New interface
Conference papers

UCBFed: Using Reinforcement Learning Method to Tackle the Federated Optimization Problem

Abstract : 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.
Complete list of metadata

https://hal.inria.fr/hal-03384857
Contributor : Hal Ifip Connect in order to contact the contributor
Submitted on : Tuesday, October 19, 2021 - 10:53:45 AM
Last modification on : Friday, August 5, 2022 - 2:43:25 PM
Long-term archiving on: : Thursday, January 20, 2022 - 6:37:41 PM

File

 Restricted access
To satisfy the distribution rights of the publisher, the document is embargoed until : 2024-01-01

Please log in to resquest access to the document

Licence


Distributed under a Creative Commons Attribution 4.0 International License

Identifiers

Citation

Wanqi Chen, Xin Zhou. UCBFed: Using Reinforcement Learning Method to Tackle the Federated Optimization Problem. 21th IFIP International Conference on Distributed Applications and Interoperable Systems (DAIS), Jun 2021, Valletta, Malta. pp.99-105, ⟨10.1007/978-3-030-78198-9_7⟩. ⟨hal-03384857⟩

Share

Metrics

Record views

40