Guardado en:
Detalles Bibliográficos
Autores principales: Licciardi, Alessandro, Raineri, Roberta, Proskurnikov, Anton, Rondoni, Lamberto, Zino, Lorenzo
Formato: Preprint
Publicado: 2025
Materias:
Acceso en línea:https://arxiv.org/abs/2506.02897
Etiquetas: Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
_version_ 1866914093119569920
author Licciardi, Alessandro
Raineri, Roberta
Proskurnikov, Anton
Rondoni, Lamberto
Zino, Lorenzo
author_facet Licciardi, Alessandro
Raineri, Roberta
Proskurnikov, Anton
Rondoni, Lamberto
Zino, Lorenzo
contents Federated Learning (FL) enables privacy-preserving collaborative model training, but its effectiveness is often limited by client data heterogeneity. We introduce a client-selection algorithm that (i) dynamically forms nonoverlapping coalitions of clients based on asymptotic agreement and (ii) selects one representative from each coalition to minimize the variance of model updates. Our approach is inspired by social-network modeling, leveraging homophily-based proximity matrices for spectral clustering and techniques for identifying the most informative individuals to estimate a group's aggregate opinion. We provide theoretical convergence guarantees for the algorithm under mild, standard FL assumptions. Finally, we validate our approach by benchmarking it against three strong heterogeneity-aware baselines; the results show higher accuracy and faster convergence, indicating that the framework is both theoretically grounded and effective in practice.
format Preprint
id arxiv_https___arxiv_org_abs_2506_02897
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Socially inspired Adaptive Coalition and Client Selection in Federated Learning
Licciardi, Alessandro
Raineri, Roberta
Proskurnikov, Anton
Rondoni, Lamberto
Zino, Lorenzo
Machine Learning
Federated Learning (FL) enables privacy-preserving collaborative model training, but its effectiveness is often limited by client data heterogeneity. We introduce a client-selection algorithm that (i) dynamically forms nonoverlapping coalitions of clients based on asymptotic agreement and (ii) selects one representative from each coalition to minimize the variance of model updates. Our approach is inspired by social-network modeling, leveraging homophily-based proximity matrices for spectral clustering and techniques for identifying the most informative individuals to estimate a group's aggregate opinion. We provide theoretical convergence guarantees for the algorithm under mild, standard FL assumptions. Finally, we validate our approach by benchmarking it against three strong heterogeneity-aware baselines; the results show higher accuracy and faster convergence, indicating that the framework is both theoretically grounded and effective in practice.
title Socially inspired Adaptive Coalition and Client Selection in Federated Learning
topic Machine Learning
url https://arxiv.org/abs/2506.02897