University of Oulu

A. Elgabli, J. Park, C. B. Issaid and M. Bennis, "Harnessing Wireless Channels for Scalable and Privacy-Preserving Federated Learning," in IEEE Transactions on Communications, vol. 69, no. 8, pp. 5194-5208, Aug. 2021, doi: 10.1109/TCOMM.2021.3078783

Harnessing wireless channels for scalable and privacy-preserving federated learning

Saved in:
Author: Elgabli, Anis1; Park, Jihong2; Issaid, Chaouki Ben1;
Organizations: 1Centre of Wireless Communications, University of Oulu, 90014 Oulu, Finland
2School of Information Technology, Deakin University, Geelong, VIC 3220, Australia
Format: article
Version: accepted version
Access: open
Online Access: PDF Full Text (PDF, 2.3 MB)
Persistent link: http://urn.fi/urn:nbn:fi-fe2021101450962
Language: English
Published: Institute of Electrical and Electronics Engineers, 2021
Publish Date: 2021-10-14
Description:

Abstract

Wireless connectivity is instrumental in enabling scalable federated learning (FL), yet wireless channels bring challenges for model training, in which channel randomness perturbs each worker’s model update while multiple workers’ updates incur significant interference under limited bandwidth. To address these challenges, in this work we formulate a novel constrained optimization problem, and propose an FL framework harnessing wireless channel perturbations and interference for improving privacy, bandwidth-efficiency, and scalability. The resultant algorithm is coined analog federated ADMM (A-FADMM) based on analog transmissions and the alternating direction method of multipliers (ADMM). In A-FADMM, all workers upload their model updates to the parameter server (PS) using a single channel via analog transmissions, during which all models are perturbed and aggregated over-the-air. This not only saves communication bandwidth, but also hides each worker’s exact model update trajectory from any eavesdropper including the honest-but-curious PS, thereby preserving data privacy against model inversion attacks. We formally prove the convergence and privacy guarantees of A-FADMM for convex functions under time-varying channels, and numerically show the effectiveness of A-FADMM under noisy channels and stochastic non-convex functions, in terms of convergence speed and scalability, as well as communication bandwidth and energy efficiency.

see all

Series: IEEE transactions on communications
ISSN: 0090-6778
ISSN-E: 1558-0857
ISSN-L: 0090-6778
Volume: 69
Issue: 8
Pages: 5194 - 5208
DOI: 10.1109/TCOMM.2021.3078783
OADOI: https://oadoi.org/10.1109/TCOMM.2021.3078783
Type of Publication: A1 Journal article – refereed
Field of Science: 213 Electronic, automation and communications engineering, electronics
Subjects:
Copyright information: © 2021 IEEE. Personal use of this material is permitted. Permission from IEEE must be obtained for all other uses, in any current or future media, including reprinting/republishing this material for advertising or promotional purposes, creating new collective works, for resale or redistribution to servers or lists, or reuse of any copyrighted component of this work in other works.