TY - GEN
T1 - How Robust is Federated Learning to Communication Error? A Comparison Study Between Uplink and Downlink Channels
AU - Qu, Linping
AU - Song, Shenghui
AU - Tsui, Chi Ying
AU - Mao, Yuyi
N1 - Publisher Copyright:
© 2024 IEEE.
PY - 2024/7/3
Y1 - 2024/7/3
N2 - Because of its privacy-preserving capability, federated learning (FL) has attracted significant attention from both academia and industry. However, when being implemented over wireless networks, it is not clear how much communication error can be tolerated by FL. This paper investigates the robustness of FL to the uplink and downlink communication error. Our theoretical analysis reveals that the robustness depends on two critical parameters, namely the number of clients and the numerical range of model parameters. It is also shown that the uplink communication in FL can tolerate a higher bit error rate (BER) than downlink communication, and this difference is quantified by a proposed formula. The findings and theoretical analyses are further validated by extensive experiments.
AB - Because of its privacy-preserving capability, federated learning (FL) has attracted significant attention from both academia and industry. However, when being implemented over wireless networks, it is not clear how much communication error can be tolerated by FL. This paper investigates the robustness of FL to the uplink and downlink communication error. Our theoretical analysis reveals that the robustness depends on two critical parameters, namely the number of clients and the numerical range of model parameters. It is also shown that the uplink communication in FL can tolerate a higher bit error rate (BER) than downlink communication, and this difference is quantified by a proposed formula. The findings and theoretical analyses are further validated by extensive experiments.
KW - bit error rate (BER)
KW - Federated learning (FL)
KW - uplink and downlink
UR - http://www.scopus.com/inward/record.url?scp=85198858151&partnerID=8YFLogxK
U2 - 10.1109/WCNC57260.2024.10570687
DO - 10.1109/WCNC57260.2024.10570687
M3 - Conference article published in proceeding or book
AN - SCOPUS:85198858151
T3 - IEEE Wireless Communications and Networking Conference, WCNC
BT - 2024 IEEE Wireless Communications and Networking Conference, WCNC 2024 - Proceedings
PB - Institute of Electrical and Electronics Engineers Inc.
T2 - 25th IEEE Wireless Communications and Networking Conference, WCNC 2024
Y2 - 21 April 2024 through 24 April 2024
ER -