Consiglio Nazionale delle Ricerche

Tipo di prodottoArticolo in rivista
TitoloFederated Learning with Cooperating Devices: A Consensus Approach for Massive IoT Networks
Anno di pubblicazione2020
FormatoElettronico
Autore/iSavazzi S.; Nicoli M.; Rampa V.
Affiliazioni autoriConsiglio Nazionale Delle Ricerche, IEIIT Institute, DIG Department, Politecnico di Milano, Milan, 20133
Autori CNR e affiliazioni
  • STEFANO SAVAZZI
  • VITTORIO RAMPA
Lingua/e
  • inglese
AbstractFederated learning (FL) is emerging as a new paradigm to train machine learning (ML) models in distributed systems. Rather than sharing and disclosing the training data set with the server, the model parameters (e.g., neural networks' weights and biases) are optimized collectively by large populations of interconnected devices, acting as local learners. FL can be applied to power-constrained Internet of Things (IoT) devices with slow and sporadic connections. In addition, it does not need data to be exported to third parties, preserving privacy. Despite these benefits, a main limit of existing approaches is the centralized optimization which relies on a server for aggregation and fusion of local parameters; this has the drawback of a single point of failure and scaling issues for increasing network size. This article proposes a fully distributed (or serverless) learning approach: the proposed FL algorithms leverage the cooperation of devices that perform data operations inside the network by iterating local computations and mutual interactions via consensus-based methods. The approach lays the groundwork for integration of FL within 5G and beyond networks characterized by decentralized connectivity and computing, with intelligence distributed over the end devices. The proposed methodology is verified by the experimental data sets collected inside an Industrial IoT (IIoT) environment.
Lingua abstractinglese
Altro abstract-
Lingua altro abstract-
Pagine da4641
Pagine a4654
Pagine totali-
RivistaIEEE Internet of Things Journal
Attiva dal 2014
Editore: Institute of Electrical and Electronics Engineers - New York, NY
Paese di pubblicazione: Stati Uniti d'America
Lingua: inglese
ISSN: 2327-4662
Titolo chiave: IEEE Internet of Things Journal
Numero volume della rivista7
Fascicolo della rivista-
DOI10.1109/JIOT.2020.2964162
Verificato da refereeSì: Internazionale
Stato della pubblicazionePublished version
Indicizzazione (in banche dati controllate)
  • Scopus (Codice:2-s2.0-85084918144)
Parole chiaveFederated Learning, Machine learning, signal processing, distributed learning, edge machine learning
Link (URL, URI)http://www.scopus.com/record/display.url?eid=2-s2.0-85084918144&origin=inward
Titolo parallelo-
Licenza-
Scadenza embargo-
Data di accettazione-
Note/Altre informazioni-
Strutture CNR
  • IEIIT — Istituto di elettronica e di ingegneria dell'informazione e delle telecomunicazioni
Moduli/Attività/Sottoprogetti CNR
  • DIT.AD003.083.001 : RADIOSENSE - Wireless Big Data Augmented Smart Industry
Progetti Europei
Allegati
Federated Learning with Cooperating Devices: A Consensus Approach for Massive IoT Networks
Descrizione: PDF completo (pubblicato su ArXiv)
Tipo documento: application/pdf
Federated Learning with Cooperating Devices: A Consensus Approach for Massive IoT Networks (documento privato )
Descrizione: pdf ieee
Tipo documento: application/pdf