In modern real-world applications, the need of using a decentralized data processing approach has progressively increased, facing complexity and handling issues. Pervasive data and ubiquitous computational capacity have enabled the proficient use of distributed implementation of machine learning algorithms, especially for forecasting problems. We provide in this paper a new, fully distributed prediction approach based on the Long Short-Term Memory deep neural network. When placed in a network of interconnected agents, the single predictors are able to improve the prediction accuracy by means of the Alternating Direction Method of Multipliers consensus procedure on some network parameters. Experimental tests on real-world time series prove the efficacy of the proposed approach, which regulates the information exchange in the network through high-level structures in the considered models.

ADMM consensus for deep LSTM networks / Rosato, A.; Succetti, F.; Barbirotta, M.; Panella, M.. - (2020), pp. 1-8. ((Intervento presentato al convegno 2020 International Joint Conference on Neural Networks, IJCNN 2020 tenutosi a Glasgow (virtual), U.K. [10.1109/IJCNN48605.2020.9207512].

ADMM consensus for deep LSTM networks

Rosato A.;Succetti F.;Barbirotta M.;Panella M.
2020

Abstract

In modern real-world applications, the need of using a decentralized data processing approach has progressively increased, facing complexity and handling issues. Pervasive data and ubiquitous computational capacity have enabled the proficient use of distributed implementation of machine learning algorithms, especially for forecasting problems. We provide in this paper a new, fully distributed prediction approach based on the Long Short-Term Memory deep neural network. When placed in a network of interconnected agents, the single predictors are able to improve the prediction accuracy by means of the Alternating Direction Method of Multipliers consensus procedure on some network parameters. Experimental tests on real-world time series prove the efficacy of the proposed approach, which regulates the information exchange in the network through high-level structures in the considered models.
2020 International Joint Conference on Neural Networks, IJCNN 2020
ADMMcConsensus; deep LSTM networks; time series prediction
04 Pubblicazione in atti di convegno::04b Atto di convegno in volume
ADMM consensus for deep LSTM networks / Rosato, A.; Succetti, F.; Barbirotta, M.; Panella, M.. - (2020), pp. 1-8. ((Intervento presentato al convegno 2020 International Joint Conference on Neural Networks, IJCNN 2020 tenutosi a Glasgow (virtual), U.K. [10.1109/IJCNN48605.2020.9207512].
File allegati a questo prodotto
File Dimensione Formato  
Rosato_ADMM_2020.pdf

solo gestori archivio

Tipologia: Versione editoriale (versione pubblicata con il layout dell'editore)
Licenza: Tutti i diritti riservati (All rights reserved)
Dimensione 4.17 MB
Formato Adobe PDF
4.17 MB Adobe PDF   Visualizza/Apri   Richiedi una copia

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/11573/1461039
Citazioni
  • ???jsp.display-item.citation.pmc??? ND
  • Scopus 1
  • ???jsp.display-item.citation.isi??? 1
social impact