Unit-Modulus Wireless Federated Learning Via Penalty Alternating Minimization

TL;DR

This paper introduces a unit-modulus wireless federated learning framework that uses phase shifting to efficiently upload and compute model parameters, reducing communication delays and costs.

Contribution

It proposes a novel UMWFL framework with a PAM algorithm to optimize phase shifts, avoiding complex signal processing and improving training and testing performance.

Findings

Achieves smaller training losses than benchmark schemes

Reduces communication delays and implementation costs

Demonstrates improved testing errors in CARLA platform

Abstract

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.