Unit-Modulus Wireless Federated Learning Via Penalty Alternating Minimization

Wang，Shuai1,2; Li，Dachuan2; Wang，Rui1; Hao，Qi2; Wu，Yik Chung3; Ng，Derrick Wing Kwan4

10.1109/GLOBECOM46510.2021.9685788

2021

IEEE Global Communications Conference (GLOBECOM)

2334-0983

2576-6813

978-1-7281-8105-9

2021 IEEE Global Communications Conference, GLOBECOM 2021 - Proceedings

1-7

DEC 07-11, 2021

null,Madrid,SPAIN

345 E 47TH ST, NEW YORK, NY 10017 USA

IEEE

Wireless federated learning (FL) is an emerging machine learning paradigm that trains a global parametric model from distributed datasets via wireless communications. This paper proposes a unit-modulus wireless FL (UMWFL) framework, which simultaneously uploads local model parameters and computes global model parameters via optimized phase shifting. The proposed framework avoids sophisticated baseband signal processing, leading to both low communication delays and implementation costs. A training loss bound is derived and a penalty alternating minimization (PAM) algorithm is proposed to minimize the nonconvex nonsmooth loss bound. Experimental results in the Car Learning to Act (CARLA) platform show that the proposed UMWFL framework with PAM algorithm achieves smaller training losses and testing errors than those of the benchmark scheme.

Wireless communication Training Costs Computational modeling Signal processing algorithms Minimization Collaborative work

第一

英语

CPCI-S ; EI

National Natural Science Foundation of China[62001203];

Computer Science ; Engineering ; Telecommunications

Computer Science, Information Systems ; Computer Science, Theory & Methods ; Engineering, Electrical & Electronic ; Telecommunications

WOS:000790747204026

20221311872695

Pulse amplitude modulation

2-s2.0-85120959887

Scopus

1.Southern University of Science and Technology,Department of Electrical and Electronic Engineering,China
2.Southern University of Science and Technology,Department of Computer Science and Engineering,China
3.University of Hong Kong,Department of Electrical and Electronic Engineering,Hong Kong,Hong Kong
4.School of Electrical Engineering and Telecommunications,University of New South Wales,Australia

Wang，Shuai,Li，Dachuan,Wang，Rui,et al. Unit-Modulus Wireless Federated Learning Via Penalty Alternating Minimization[C]. 345 E 47TH ST, NEW YORK, NY 10017 USA:IEEE,2021:1-7.