Salvato in:
Dettagli Bibliografici
Autori principali: Fernández-Piñeiro, Pablo, Ferández-Veiga, Manuel, Díaz-Redondo, Rebeca P., Fernández-Vilas, Ana, González-Soto, Martín
Natura: Preprint
Pubblicazione: 2024
Soggetti:
Accesso online:https://arxiv.org/abs/2411.09267
Tags: Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
_version_ 1866916480427229184
author Fernández-Piñeiro, Pablo
Ferández-Veiga, Manuel
Díaz-Redondo, Rebeca P.
Fernández-Vilas, Ana
González-Soto, Martín
author_facet Fernández-Piñeiro, Pablo
Ferández-Veiga, Manuel
Díaz-Redondo, Rebeca P.
Fernández-Vilas, Ana
González-Soto, Martín
contents In prototype-based federated learning, the exchange of model parameters between clients and the master server is replaced by transmission of prototypes or quantized versions of the data samples to the aggregation server. A fully decentralized deployment of prototype-based learning, without a central agregartor of prototypes, is more robust upon network failures and reacts faster to changes in the statistical distribution of the data, suggesting potential advantages and quick adaptation in dynamic learning tasks, e.g., when the data sources are IoT devices or when data is non-iid. In this paper, we consider the problem of designing a communication-efficient decentralized learning system based on prototypes. We address the challenge of prototype redundancy by leveraging on a twofold data compression technique, i.e., sending only update messages if the prototypes are informationtheoretically useful (via the Jensen-Shannon distance), and using clustering on the prototypes to compress the update messages used in the gossip protocol. We also use parallel instead of sequential gossiping, and present an analysis of its age-of-information (AoI). Our experimental results show that, with these improvements, the communications load can be substantially reduced without decreasing the convergence rate of the learning algorithm.
format Preprint
id arxiv_https___arxiv_org_abs_2411_09267
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Towards efficient compression and communication for prototype-based decentralized learning
Fernández-Piñeiro, Pablo
Ferández-Veiga, Manuel
Díaz-Redondo, Rebeca P.
Fernández-Vilas, Ana
González-Soto, Martín
Machine Learning
In prototype-based federated learning, the exchange of model parameters between clients and the master server is replaced by transmission of prototypes or quantized versions of the data samples to the aggregation server. A fully decentralized deployment of prototype-based learning, without a central agregartor of prototypes, is more robust upon network failures and reacts faster to changes in the statistical distribution of the data, suggesting potential advantages and quick adaptation in dynamic learning tasks, e.g., when the data sources are IoT devices or when data is non-iid. In this paper, we consider the problem of designing a communication-efficient decentralized learning system based on prototypes. We address the challenge of prototype redundancy by leveraging on a twofold data compression technique, i.e., sending only update messages if the prototypes are informationtheoretically useful (via the Jensen-Shannon distance), and using clustering on the prototypes to compress the update messages used in the gossip protocol. We also use parallel instead of sequential gossiping, and present an analysis of its age-of-information (AoI). Our experimental results show that, with these improvements, the communications load can be substantially reduced without decreasing the convergence rate of the learning algorithm.
title Towards efficient compression and communication for prototype-based decentralized learning
topic Machine Learning
url https://arxiv.org/abs/2411.09267