Imperial College London
Portrait Picture

ProfessorDenizGunduz

Faculty of Engineering, Department of Electrical and Electronic Engineering

Professor in Information Processing
 
 
 
//

Contact

 

+44 (0)20 7594 6218d.gunduz Website

 
 
//

Assistant

 

Ms Joan O'Brien +44 (0)20 7594 6316

 
//

Location

 

1016Electrical EngineeringSouth Kensington Campus

//

Summary

 

Publications

Citation

BibTex format

@article{Amiri:2022:10.1109/twc.2021.3103874,
author = {Amiri, MM and Gunduz, D and Kulkarni, SR and Vincent, Poor H},
doi = {10.1109/twc.2021.3103874},
journal = {IEEE Transactions on Wireless Communications},
pages = {1422--1437},
title = {Convergence of federated learning over a noisy downlink},
url = {http://dx.doi.org/10.1109/twc.2021.3103874},
volume = {21},
year = {2022}
}
Download

RIS format (EndNote, RefMan)

TY  - JOUR
AB  - We study federated learning (FL), where power-limited wireless devices utilize their local datasets to collaboratively train a global model with the help of a remote parameter server (PS). The PS has access to the global model and shares it with the devices for local training using their datasets, and the devices return the result of their local updates to the PS to update the global model. The algorithm continues until the convergence of the global model. This framework requires downlink transmission from the PS to the devices and uplink transmission from the devices to the PS. The goal of this study is to investigate the impact of the bandwidth-limited shared wireless medium on the performance of FL with a focus on the downlink. To this end, the downlink and uplink channels are modeled as fading broadcast and multiple access channels, respectively, both with limited bandwidth. For downlink transmission, we first introduce a digital approach, where a quantization technique is employed at the PS followed by a capacity-achieving channel code to transmit the global model update over the wireless broadcast channel at a common rate such that all the devices can decode it. Next, we propose analog downlink transmission, where the global model is broadcast by the PS in an uncoded manner. We consider analog transmission over the uplink in both cases, since its superiority over digital transmission for uplink has been well studied in the literature. We further analyze the convergence behavior of the proposed analog transmission approach over the downlink assuming that the uplink transmission is error-free. Numerical experiments show that the analog downlink approach provides significant improvement over the digital one with a more notable improvement when the data distribution across the devices is not independent and identically distributed. The experimental results corroborate the convergence analysis, and show that a smaller number of local iterations should be used when
AU  - Amiri,MM
AU  - Gunduz,D
AU  - Kulkarni,SR
AU  - Vincent,Poor H
DO  - 10.1109/twc.2021.3103874
EP  - 1437
PY  - 2022///
SN  - 1536-1276
SP  - 1422
TI  - Convergence of federated learning over a noisy downlink
T2  - IEEE Transactions on Wireless Communications
UR  - http://dx.doi.org/10.1109/twc.2021.3103874
UR  - https://ieeexplore.ieee.org/document/9515709
UR  - http://hdl.handle.net/10044/1/92901
VL  - 21
ER  -
Download