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.
2021, ICAAI 2021: 2021 The 5th International Conference on Advances in Artificial Intelligence (ICAAI), Pages 38-43
AdaFed: Performance-based Adaptive Federated Learning (04b Atto di convegno in volume)
Giuseppi Alessandro, Della Torre Lucrezia, Menegatti Danilo, Pietrabissa Antonio
Gruppo di ricerca: Networked Systems