Completion Time Minimization of Fog-RAN-Assisted Federated Learning With Rate-Splitting Transmission

TL;DR

This paper proposes a rate-splitting transmission method for federated learning over fog radio access networks, optimizing communication and training parameters to minimize completion time amid limited fronthaul capacity.

Contribution

It introduces a novel rate-splitting transmission approach that enables hybrid decoding, improving efficiency in federated learning with constrained fronthaul links.

Findings

Rate-splitting transmission reduces completion time.

Proposed method outperforms edge-only or cloud-only decoding schemes.

Optimization of transmission and quantization strategies enhances FL performance.

Abstract

This work studies federated learning (FL) over a fog radio access network, in which multiple internet-of-things (IoT) devices cooperatively learn a shared machine learning model by communicating with a cloud server (CS) through distributed access points (APs). Under the assumption that the fronthaul links connecting APs to CS have finite capacity, a rate-splitting transmission at IoT devices (IDs) is proposed which enables hybrid edge and cloud decoding of split uplink messages. The problem of completion time minimization for FL is tackled by optimizing the rate-splitting transmission and fronthaul quantization strategies along with training hyperparameters such as precision and iteration numbers. Numerical results show that the proposed rate-splitting transmission achieves notable gains over benchmark schemes which rely solely on edge or cloud decoding.