On the Limit Performance of Floating Gossip
This work addresses the challenge of cooperative, continuous training for moving users in decentralized settings, representing an incremental improvement by combining communication and computing aspects in Gossip Learning.
The paper tackles the problem of continuous machine learning in dynamic, infrastructure-less environments by analyzing the limit performance of Floating Gossip, a fully distributed scheme that uses location-based probabilistic evolution. The results, validated through simulations, show that Floating Gossip can effectively incorporate data into models as a function of system parameters, achieving good accuracy.
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.