Federated Learning (FL) is an enabling technology for Machine Learning in scenarios in which it is impossible, for privacy and/or regulatory reasons, to analyze data in a centralized manner. FL envisages that distributed clients cooperate to learn a model without any data exchange, in favor of a model averaging procedure that is coordinated by a server. In this work, we present the Adaptive Federated Learning (AdaFed) algorithm, that extends the original Federated Averaging algorithm by: (i) dynamically weighting the local models, based on their performance, for the averaging procedure; (ii) adapting the loss function at every communication round depending on the training behavior. This work specializes AdaFed for both classification and regression tasks, and reports several validation tests on benchmarking dataset, showing its enhanced robustness against unbalanced data distributions and adversarial clients.

An Adaptive Model Averaging Procedure for Federated Learning (AdaFed) / Giuseppi, A.; Torre, L. D.; Menegatti, D.; Priscoli, F. D.; Pietrabissa, A.; Poli, C.. - In: JOURNAL OF ADVANCES IN INFORMATION TECHNOLOGY. - ISSN 1798-2340. - 13:6(2022), pp. 539-548. [10.12720/jait.13.6.539-548]

An Adaptive Model Averaging Procedure for Federated Learning (AdaFed)

Giuseppi A.
Primo
;
Menegatti D.
;
Priscoli F. D.
;
Pietrabissa A.
;
2022

Abstract

Federated Learning (FL) is an enabling technology for Machine Learning in scenarios in which it is impossible, for privacy and/or regulatory reasons, to analyze data in a centralized manner. FL envisages that distributed clients cooperate to learn a model without any data exchange, in favor of a model averaging procedure that is coordinated by a server. In this work, we present the Adaptive Federated Learning (AdaFed) algorithm, that extends the original Federated Averaging algorithm by: (i) dynamically weighting the local models, based on their performance, for the averaging procedure; (ii) adapting the loss function at every communication round depending on the training behavior. This work specializes AdaFed for both classification and regression tasks, and reports several validation tests on benchmarking dataset, showing its enhanced robustness against unbalanced data distributions and adversarial clients.
2022
adaptive learning; deep neural networks; distributed learning systems; federated learning
01 Pubblicazione su rivista::01a Articolo in rivista
An Adaptive Model Averaging Procedure for Federated Learning (AdaFed) / Giuseppi, A.; Torre, L. D.; Menegatti, D.; Priscoli, F. D.; Pietrabissa, A.; Poli, C.. - In: JOURNAL OF ADVANCES IN INFORMATION TECHNOLOGY. - ISSN 1798-2340. - 13:6(2022), pp. 539-548. [10.12720/jait.13.6.539-548]
File allegati a questo prodotto
File Dimensione Formato  
Giuseppi_An-adaptive_2022.pdf

accesso aperto

Tipologia: Versione editoriale (versione pubblicata con il layout dell'editore)
Licenza: Creative commons
Dimensione 2.29 MB
Formato Adobe PDF
2.29 MB Adobe PDF
Giuseppi_adafed_2022.pdf

accesso aperto

Note: 10.12720/jait.13.6.539-548
Tipologia: Documento in Pre-print (manoscritto inviato all'editore, precedente alla peer review)
Licenza: Tutti i diritti riservati (All rights reserved)
Dimensione 1.02 MB
Formato Adobe PDF
1.02 MB Adobe PDF

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/11573/1661494
Citazioni
  • ???jsp.display-item.citation.pmc??? ND
  • Scopus 8
  • ???jsp.display-item.citation.isi??? 3
social impact