Federated Learning (FL) emerged as a decentralized paradigm to train models while preserving privacy. However, conventional FL struggles with data heterogeneity and class imbalance, which degrade model performance. Clustered FL balances personalization and decentralized training by grouping clients with analogous data distributions, enabling improved accuracy while adhering to privacy constraints. This approach effectively mitigates the adverse impact of heterogeneity in FL. In this work, we propose a novel clustered FL method, FedGWC (Federated Gaussian Weighting Clustering), which groups clients based on their data distribution, allowing training of a more ro- bust and personalized model on the identified clus- ters. FedGWC identifies homogeneous clusters by transforming individual empirical losses to model client interactions with a Gaussian reward mechanism. Additionally, we introduce the Wasserstein Adjusted Score, a new clustering metric for FL to evaluate cluster cohesion with respect to the individual class distribution. Our experiments on benchmark datasets show that FedGWC outperforms existing FL algorithms in cluster quality and classification accuracy, validating the efficacy of our approach. Code is available at https: //github.com/davedleo/FedGWC
Interaction-Aware Gaussian Weighting for Clustered Federated Learning / Leo, Davide; Fanì, Eros; Caputo, Barbara; Ciccone, Marco. - ELETTRONICO. - 267:(2025). (Intervento presentato al convegno 42nd International Conference on Machine Learning (ICML 2025) tenutosi a Vancouver, Canada nel 13/07/2025 - 19/07/2025).
Interaction-Aware Gaussian Weighting for Clustered Federated Learning
Barbara Caputo;Marco Ciccone
2025
Abstract
Federated Learning (FL) emerged as a decentralized paradigm to train models while preserving privacy. However, conventional FL struggles with data heterogeneity and class imbalance, which degrade model performance. Clustered FL balances personalization and decentralized training by grouping clients with analogous data distributions, enabling improved accuracy while adhering to privacy constraints. This approach effectively mitigates the adverse impact of heterogeneity in FL. In this work, we propose a novel clustered FL method, FedGWC (Federated Gaussian Weighting Clustering), which groups clients based on their data distribution, allowing training of a more ro- bust and personalized model on the identified clus- ters. FedGWC identifies homogeneous clusters by transforming individual empirical losses to model client interactions with a Gaussian reward mechanism. Additionally, we introduce the Wasserstein Adjusted Score, a new clustering metric for FL to evaluate cluster cohesion with respect to the individual class distribution. Our experiments on benchmark datasets show that FedGWC outperforms existing FL algorithms in cluster quality and classification accuracy, validating the efficacy of our approach. Code is available at https: //github.com/davedleo/FedGWCPubblicazioni consigliate
I documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.
https://hdl.handle.net/11583/3003711
			
		
	
	
	
			      	Attenzione
Attenzione! I dati visualizzati non sono stati sottoposti a validazione da parte dell'ateneo
