Private Federated Learning With Misaligned Power Allocation via Over-the-Air Computation

Yan, Na, Wang, Kezhi, Pan, Cunhua and Chai, Kok Keong (2022) Private Federated Learning With Misaligned Power Allocation via Over-the-Air Computation. IEEE Communications Letters, 26 (9). pp. 1994-1998. ISSN 1089-7798

FINAL VERSION.pdf - Accepted Version

Download (384kB) | Preview
Official URL:


To further preserve the data privacy of federated learning (FL), we propose a differentially private FL (DPFL) scheme with misaligned power allocation (MPA-DPFL). Unlike most existing over-the-air FL studies, in MPA-DPFL, the gradients are aggregated through over-the-air computation (Aircomp) but do not need to be aligned in the transmission. Therefore, MPA-DPFL can avoid the problem that the signal-to-noise ratio (SNR) of the system is limited by the device with the worst channel condition. We formulate an optimization problem to minimize the optimality gap of MPA-DPFL while guaranteeing a certain degree of privacy protection. Additionally, we demonstrate that the MPA-DPFL is more suitable than the DPFL with aligned power allocation (APA-DPFL) when the channel condition of a device in the system is lower than a threshold. The analytical results are validated through simulation.

Item Type: Article
Additional Information: Funding information: 10.13039/501100004543-China Scholarship Council
Uncontrolled Keywords: Collaborative work, Computational modeling, Data privacy, Optimization, Privacy, Resource management, Signal to noise ratio, Training, federated learning, over-the-air computation, power allocation
Subjects: G400 Computer Science
H600 Electronic and Electrical Engineering
Department: Faculties > Engineering and Environment > Computer and Information Sciences
Depositing User: Rachel Branson
Date Deposited: 26 Sep 2022 09:57
Last Modified: 26 Sep 2022 10:00

Actions (login required)

View Item View Item


Downloads per month over past year

View more statistics