TY - GEN
T1 - Performance-Aware Client and Quantization Level Selection Algorithm for Fast Federated Learning
AU - Seo, Sangwon
AU - Lee, Jaewook
AU - Ko, Haneul
AU - Pack, Sangheon
N1 - Funding Information:
ACKNOWLEDGEMENT This research was supported by National Research Foundation (NRF) of Korea Grant funded by the Korean Government (MSIT) (No. 2021R1A4A3022102 and 2020R1A2C3006786).
Publisher Copyright:
© 2022 IEEE.
PY - 2022
Y1 - 2022
N2 - In federated learning (FL), which clients are selected and which quantization levels are chosen for the deep model parameters have significant impacts on the learning time as well as the learning accuracy. In this paper, we formulate a joint optimization problem on the client and quantization level selections. As a low complexity solution to the formulated problem, we develop a performance-aware client and quantization level selection (PA-CQLS) algorithm where the FL server estimates the individual round times of clients based on their computing power and channel quality, and determines the most appropriate clients and quantization levels accordingly. Simulation results show that PA-CQLS can reduce the round time by up to 70% compared to conventional algorithms.
AB - In federated learning (FL), which clients are selected and which quantization levels are chosen for the deep model parameters have significant impacts on the learning time as well as the learning accuracy. In this paper, we formulate a joint optimization problem on the client and quantization level selections. As a low complexity solution to the formulated problem, we develop a performance-aware client and quantization level selection (PA-CQLS) algorithm where the FL server estimates the individual round times of clients based on their computing power and channel quality, and determines the most appropriate clients and quantization levels accordingly. Simulation results show that PA-CQLS can reduce the round time by up to 70% compared to conventional algorithms.
UR - http://www.scopus.com/inward/record.url?scp=85130751466&partnerID=8YFLogxK
U2 - 10.1109/WCNC51071.2022.9771600
DO - 10.1109/WCNC51071.2022.9771600
M3 - Conference contribution
AN - SCOPUS:85130751466
T3 - IEEE Wireless Communications and Networking Conference, WCNC
SP - 1892
EP - 1897
BT - 2022 IEEE Wireless Communications and Networking Conference, WCNC 2022
PB - Institute of Electrical and Electronics Engineers Inc.
T2 - 2022 IEEE Wireless Communications and Networking Conference, WCNC 2022
Y2 - 10 April 2022 through 13 April 2022
ER -