Statistics and Learning Theory
Federated Learning

Wireless Federated Learning with Local Differential Privacy

Mohamed Seif, Ravi Tandon, Ming Li

Date & Time

01:00 am – 01:00 am


In this paper, we study the problem of federated learning (FL) over a wireless channel, modeled by a Gaussian multiple access channel (MAC), subject to local differential privacy (LDP) constraints. We show that the superposition nature of the wireless channel provides a dual benefit of bandwidth efficient gradient aggregation, in conjunction with strong LDP guarantees for the users. We propose a private wireless gradient aggregation scheme, which shows that when aggregating gradients from K users, the privacy leakage per user scales as O(1√K) compared to orthogonal transmission in which the privacy leakage scales as a constant. We also present analysis for the convergence rate of the proposed private FL aggregation algorithm and study the tradeoffs between wireless resources, convergence, and privacy.


Mohamed Seif

University of Arizona

Ravi Tandon

University of Arizona

Ming Li

University of Arizona

Session Chair

Changho Suh

Korea Advanced Institute of Science and Technology