Yan, Na, Wang, Kezhi, Pan, Cunhua and Chai, Kok Keong (2022) Performance Analysis for Channel-Weighted Federated Learning in OMA Wireless Networks. IEEE Signal Processing Letters, 29. pp. 772-776. ISSN 1070-9908
|
Text
Performance_Analysis_for_Channel-Weighted_Federated_Learning_in_OMA_Wireless_Networks.pdf - Accepted Version Download (1MB) | Preview |
Abstract
To alleviate the negative impact of noise on wireless federated learning (FL), we propose a channel-weighted aggregation scheme of FL (CWA-FL), in which the parameter server (PS) makes aggregation of the gradients according to the channel conditions of devices.} \textcolor{blue}{In the proposed scheme}, the gradients are transmitted to the PS in an uncoded way through an orthogonal multiple access (OMA) channel\textcolor{blue}{, which can avoid the synchronization issue among devices faced by over-the-air FL.} The convergence analysis of CWA-FL is conducted and the theoretical results show that the scheme can converge with the rate of O(1/T). Simulation results show that the proposed scheme performs better than the equal-weighted aggregation scheme of FL (EWA-FL) and is more robust to noise.
| Item Type: | Article |
|---|---|
| Additional Information: | Funding information: This work of Na Yan was supported by China Scholarship Council. |
| Uncontrolled Keywords: | Federated learning, aggregation of gradients, orthogonal multiple access, convergence analysis |
| Subjects: | G400 Computer Science H600 Electronic and Electrical Engineering |
| Department: | Faculties > Engineering and Environment > Computer and Information Sciences |
| Depositing User: | John Coen |
| Date Deposited: | 21 Mar 2022 11:04 |
| Last Modified: | 08 Apr 2022 13:45 |
| URI: | http://nrl.northumbria.ac.uk/id/eprint/48706 |
Actions (login required)
 |
View Item |
Downloads
Downloads per month over past year
