On the Limit Performance of Floating Gossip

TL;DR

This paper analyzes the theoretical limit performance of Floating Gossip, a distributed, location-based gossip learning scheme, considering both communication and computation aspects in dynamic, infrastructure-less environments.

Contribution

It introduces a mean field model to evaluate the maximum data incorporation in models, accounting for both communication and computing impacts, validated by simulations.

Findings

Floating Gossip effectively supports continuous, cooperative model training.

The model accurately predicts data incorporation limits under various system parameters.

Simulation results confirm the theoretical analysis.

Abstract

In this paper we investigate the limit performance of Floating Gossip, a new, fully distributed Gossip Learning scheme which relies on Floating Content to implement location-based probabilistic evolution of machine learning models in an infrastructure-less manner. We consider dynamic scenarios where continuous learning is necessary, and we adopt a mean field approach to investigate the limit performance of Floating Gossip in terms of amount of data that users can incorporate into their models, as a function of the main system parameters. Different from existing approaches in which either communication or computing aspects of Gossip Learning are analyzed and optimized, our approach accounts for the compound impact of both aspects. We validate our results through detailed simulations, proving good accuracy. Our model shows that Floating Gossip can be very effective in implementing continuous training and update of machine learning models in a cooperative manner, based on opportunistic exchanges among moving users.