Federated Learning is a distributed and privacy-preserving machine learning technique that allows local clients to learn a model without sharing their own data by coordinating with a global server. In this work, we present the Adaptive Federated Learning (AdaFed) algorithm, which aims at improving the training performance of deep neural networks in Federated Learning settings by: (i) dynamically weighting the local models in the model averaging procedure; (ii) by adapting the loss function used by the federation at every communication round. We discuss the specialisation of AdaFed for both classification and regression tasks, providing several validation examples. Due to its adaptive design, the AdaFed algorithm showed a robust behaviour against unbalanced data distributions and adversarial clients.

AdaFed: Performance-based Adaptive Federated Learning / Giuseppi, Alessandro; Della Torre, Lucrezia; Menegatti, Danilo; Pietrabissa, Antonio. - (2021), pp. 38-43. ((Intervento presentato al convegno ICAAI 2021: 2021 The 5th International Conference on Advances in Artificial Intelligence (ICAAI) tenutosi a United Kingdom [10.1145/3505711.3505717].

AdaFed: Performance-based Adaptive Federated Learning

Giuseppi, Alessandro;Menegatti, Danilo;Pietrabissa, Antonio
2021

Abstract

Federated Learning is a distributed and privacy-preserving machine learning technique that allows local clients to learn a model without sharing their own data by coordinating with a global server. In this work, we present the Adaptive Federated Learning (AdaFed) algorithm, which aims at improving the training performance of deep neural networks in Federated Learning settings by: (i) dynamically weighting the local models in the model averaging procedure; (ii) by adapting the loss function used by the federation at every communication round. We discuss the specialisation of AdaFed for both classification and regression tasks, providing several validation examples. Due to its adaptive design, the AdaFed algorithm showed a robust behaviour against unbalanced data distributions and adversarial clients.
ICAAI 2021: 2021 The 5th International Conference on Advances in Artificial Intelligence (ICAAI)
Deep Neural Networks; Federated Learning; Distributed Learning-Systems
04 Pubblicazione in atti di convegno::04b Atto di convegno in volume
AdaFed: Performance-based Adaptive Federated Learning / Giuseppi, Alessandro; Della Torre, Lucrezia; Menegatti, Danilo; Pietrabissa, Antonio. - (2021), pp. 38-43. ((Intervento presentato al convegno ICAAI 2021: 2021 The 5th International Conference on Advances in Artificial Intelligence (ICAAI) tenutosi a United Kingdom [10.1145/3505711.3505717].
File allegati a questo prodotto
Non ci sono file associati a questo prodotto.

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/11573/1627181
 Attenzione

Attenzione! I dati visualizzati non sono stati sottoposti a validazione da parte dell'ateneo

Citazioni
  • ???jsp.display-item.citation.pmc??? ND
  • Scopus 2
  • ???jsp.display-item.citation.isi??? ND
social impact