Friends in Unexpected Places: Enhancing Local Fairness in Federated Learning through Clustering

Fuente: arXiv
Guardado en:
Detalles Bibliográficos
Autores principales: Yang, Yifan, Payani, Ali, Naghizadeh, Parinaz
Formato: Preprint
Publicado: 2024
Materias:
Acceso en línea:
Etiquetas: Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
_version_ 1866916766693720064
author Yang, Yifan
Payani, Ali
Naghizadeh, Parinaz
author_facet Yang, Yifan
Payani, Ali
Naghizadeh, Parinaz
contents Federated Learning (FL) has been a pivotal paradigm for collaborative training of machine learning models across distributed datasets. In heterogeneous settings, it has been observed that a single shared FL model can lead to low local accuracy, motivating personalized FL algorithms. In parallel, fair FL algorithms have been proposed to enforce group fairness on the global models. Again, in heterogeneous settings, global and local fairness do not necessarily align, motivating the recent literature on locally fair FL. In this paper, we propose new FL algorithms for heterogeneous settings, spanning the space between personalized and locally fair FL. Building on existing clustering-based personalized FL methods, we incorporate a new fairness metric into cluster assignment, enabling a tunable balance between local accuracy and fairness. Our methods match or exceed the performance of existing locally fair FL approaches, without explicit fairness intervention. We further demonstrate (numerically and analytically) that personalization alone can improve local fairness and that our methods exploit this alignment when present.
format Preprint
id arxiv_https___arxiv_org_abs_2407_19331
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Friends in Unexpected Places: Enhancing Local Fairness in Federated Learning through Clustering
Yang, Yifan
Payani, Ali
Naghizadeh, Parinaz
Machine Learning
Computers and Society
Federated Learning (FL) has been a pivotal paradigm for collaborative training of machine learning models across distributed datasets. In heterogeneous settings, it has been observed that a single shared FL model can lead to low local accuracy, motivating personalized FL algorithms. In parallel, fair FL algorithms have been proposed to enforce group fairness on the global models. Again, in heterogeneous settings, global and local fairness do not necessarily align, motivating the recent literature on locally fair FL. In this paper, we propose new FL algorithms for heterogeneous settings, spanning the space between personalized and locally fair FL. Building on existing clustering-based personalized FL methods, we incorporate a new fairness metric into cluster assignment, enabling a tunable balance between local accuracy and fairness. Our methods match or exceed the performance of existing locally fair FL approaches, without explicit fairness intervention. We further demonstrate (numerically and analytically) that personalization alone can improve local fairness and that our methods exploit this alignment when present.
title Friends in Unexpected Places: Enhancing Local Fairness in Federated Learning through Clustering
topic Machine Learning
Computers and Society
url https://arxiv.org/abs/2407.19331