Distributed machine learning is the problem of inferring a desired relation when the training data is distributed throughout a network of agents (e.g. robots in a robot swarm). Multiple families of distributed learning algorithms are based on the decentralized average consensus (DAC) protocol, an efficient algorithm for computing an average starting from local measurement vectors. The performance of DAC, however, is strongly dependent on the choice of a weighting matrix associated to the network. In this paper, we perform a comparative analysis of the relative performance of 4 different strategies for choosing the weighting matrix. As an applicative example, we consider the distributed sequential algorithm for Random Vector Functional-Link networks. As expected, our experimental simulations show that the training time required by the algorithm is drastically reduced when considering a proper initialization of the weights.

A comparison of consensus strategies for distributed learning of random vector functional-link networks / Fierimonte, Roberto; Scardapane, Simone; Panella, Massimo; Uncini, Aurelio. - STAMPA. - 54(2016), pp. 143-152. - SMART INNOVATION, SYSTEMS AND TECHNOLOGIES. [10.1007/978-3-319-33747-0_14].

A comparison of consensus strategies for distributed learning of random vector functional-link networks

SCARDAPANE, SIMONE;PANELLA, Massimo;UNCINI, Aurelio
2016

Abstract

Distributed machine learning is the problem of inferring a desired relation when the training data is distributed throughout a network of agents (e.g. robots in a robot swarm). Multiple families of distributed learning algorithms are based on the decentralized average consensus (DAC) protocol, an efficient algorithm for computing an average starting from local measurement vectors. The performance of DAC, however, is strongly dependent on the choice of a weighting matrix associated to the network. In this paper, we perform a comparative analysis of the relative performance of 4 different strategies for choosing the weighting matrix. As an applicative example, we consider the distributed sequential algorithm for Random Vector Functional-Link networks. As expected, our experimental simulations show that the training time required by the algorithm is drastically reduced when considering a proper initialization of the weights.
2016
Advances in Neural Networks: Computational Intelligence for ICT
978-3-319-33746-3
978-3-319-33747-0
Consensus; distributed machine learning; random vector functional-link; computer science (all); decision sciences (all)
02 Pubblicazione su volume::02a Capitolo o Articolo
A comparison of consensus strategies for distributed learning of random vector functional-link networks / Fierimonte, Roberto; Scardapane, Simone; Panella, Massimo; Uncini, Aurelio. - STAMPA. - 54(2016), pp. 143-152. - SMART INNOVATION, SYSTEMS AND TECHNOLOGIES. [10.1007/978-3-319-33747-0_14].
File allegati a questo prodotto
File Dimensione Formato  
Fierimonte_Comparison_2016.pdf

solo gestori archivio

Tipologia: Versione editoriale (versione pubblicata con il layout dell'editore)
Licenza: Tutti i diritti riservati (All rights reserved)
Dimensione 8.42 MB
Formato Adobe PDF
8.42 MB Adobe PDF   Contatta l'autore

I documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.

Utilizza questo identificativo per citare o creare un link a questo documento: https://hdl.handle.net/11573/903328
Citazioni
  • ???jsp.display-item.citation.pmc??? ND
  • Scopus 2
  • ???jsp.display-item.citation.isi??? 2
social impact