This paper aims to develop distributed learning algorithms for Random Vector Functional-Link (RVFL) networks, where training data is distributed under a decentralized information structure. Two algorithms are proposed by using Decentralized Average Consensus (DAC) and Alternating Direction Method of Multipliers (ADMM) strategies, respectively. These algorithms work in a fully distributed fashion and have no requirement on coordination from a central agent during the learning process. For distributed learning, the goal is to build a common learner model which optimizes the system performance over the whole set of local data. In this work, it is assumed that all stations know the initial weights of the input layer, the output weights of local RVFL networks can be shared through communication channels among neighboring nodes only, and local datasets are blocked strictly. The proposed learning algorithms are evaluated over five benchmark datasets. Experimental results with comparisons show that the DAC-based learning algorithm performs favorably in terms of effectiveness, efficiency and computational complexity, followed by the ADMM-based learning algorithm with promising accuracy but higher computational burden.
This paper aims to develop distributed learning algorithms for Random Vector Functional-Link (RVFL) networks, where training data is distributed under a decentralized information structure. Two algorithms are proposed by using Decentralized Average Consensus (DAC) and Alternating Direction Method of Multipliers (ADMM) strategies, respectively. These algorithms work in a fully distributed fashion and have no requirement on coordination from a central agent during the learning process. For distributed learning, the goal is to build a common learner model which optimizes the system performance over the whole set of local data. In this work, it is assumed that all stations know the initial weights of the input layer, the output weights of local RVFL networks can be shared through communication channels among neighboring nodes only, and local datasets are blocked strictly. The proposed learning algorithms are evaluated over five benchmark datasets. Experimental results with comparisons show that the DAC-based learning algorithm performs favorably in terms of effectiveness, efficiency and computational complexity, followed by the ADMM-based learning algorithm with promising accuracy but higher computational burden.
Distributed learning for random vector functional-link networks / Scardapane, Simone; Dianhui, Wang; Panella, Massimo; Uncini, Aurelio. - In: INFORMATION SCIENCES. - ISSN 0020-0255. - STAMPA. - 301:(2015), pp. 271-284. [10.1016/j.ins.2015.01.007]
Distributed learning for random vector functional-link networks
SCARDAPANE, SIMONE;PANELLA, Massimo;UNCINI, Aurelio
2015
Abstract
This paper aims to develop distributed learning algorithms for Random Vector Functional-Link (RVFL) networks, where training data is distributed under a decentralized information structure. Two algorithms are proposed by using Decentralized Average Consensus (DAC) and Alternating Direction Method of Multipliers (ADMM) strategies, respectively. These algorithms work in a fully distributed fashion and have no requirement on coordination from a central agent during the learning process. For distributed learning, the goal is to build a common learner model which optimizes the system performance over the whole set of local data. In this work, it is assumed that all stations know the initial weights of the input layer, the output weights of local RVFL networks can be shared through communication channels among neighboring nodes only, and local datasets are blocked strictly. The proposed learning algorithms are evaluated over five benchmark datasets. Experimental results with comparisons show that the DAC-based learning algorithm performs favorably in terms of effectiveness, efficiency and computational complexity, followed by the ADMM-based learning algorithm with promising accuracy but higher computational burden.File | Dimensione | Formato | |
---|---|---|---|
Dichiarazione_conformità 12-01-2015.pdf
solo gestori archivio
Tipologia:
Altro materiale allegato
Licenza:
Tutti i diritti riservati (All rights reserved)
Dimensione
421.46 kB
Formato
Adobe PDF
|
421.46 kB | Adobe PDF | Contatta l'autore |
Scardapane_Distributed-learning_2015.pdf
solo gestori archivio
Tipologia:
Versione editoriale (versione pubblicata con il layout dell'editore)
Licenza:
Tutti i diritti riservati (All rights reserved)
Dimensione
771.6 kB
Formato
Adobe PDF
|
771.6 kB | Adobe PDF | Contatta l'autore |
I documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.