UAV-Aided Decentralized Learning over Mesh Networks

TL;DR

This paper explores how UAVs can enhance decentralized machine learning over mesh networks by acting as flying relays, improving connectivity and convergence speed in sparse wireless environments.

Contribution

It introduces an optimized UAV trajectory to facilitate decentralized learning in sparse mesh networks, addressing connectivity challenges.

Findings

UAVs significantly improve learning convergence in sparse networks

Optimized UAV paths enhance communication efficiency

Experiments demonstrate UAVs' essential role in decentralized learning

Abstract

Decentralized learning empowers wireless network devices to collaboratively train a machine learning (ML) model relying solely on device-to-device (D2D) communication. It is known that the convergence speed of decentralized optimization algorithms severely depends on the degree of the network connectivity, with denser network topologies leading to shorter convergence time. Consequently, the local connectivity of real world mesh networks, due to the limited communication range of its wireless nodes, undermines the efficiency of decentralized learning protocols, rendering them potentially impracticable. In this work we investigate the role of an unmanned aerial vehicle (UAV), used as flying relay, in facilitating decentralized learning procedures in such challenging conditions. We propose an optimized UAV trajectory, that is defined as a sequence of waypoints that the UAV visits sequentially in order to transfer intelligence across sparsely connected group of users. We then provide a series of experiments highlighting the essential role of UAVs in the context of decentralized learning over mesh networks.