Guardado en:
Detalles Bibliográficos
Autores principales: Soltany, Milad, Pourpanah, Farhad, Molahasani, Mahdiyar, Greenspan, Michael, Etemad, Ali
Formato: Preprint
Publicado: 2024
Materias:
Acceso en línea:https://arxiv.org/abs/2412.11408
Etiquetas: Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
_version_ 1866929705389654016
author Soltany, Milad
Pourpanah, Farhad
Molahasani, Mahdiyar
Greenspan, Michael
Etemad, Ali
author_facet Soltany, Milad
Pourpanah, Farhad
Molahasani, Mahdiyar
Greenspan, Michael
Etemad, Ali
contents In this paper, we propose a novel approach, Federated Domain Generalization with Label Smoothing and Balanced Decentralized Training (FedSB), to address the challenges of data heterogeneity within a federated learning framework. FedSB utilizes label smoothing at the client level to prevent overfitting to domain-specific features, thereby enhancing generalization capabilities across diverse domains when aggregating local models into a global model. Additionally, FedSB incorporates a decentralized budgeting mechanism which balances training among clients, which is shown to improve the performance of the aggregated global model. Extensive experiments on four commonly used multi-domain datasets, PACS, VLCS, OfficeHome, and TerraInc, demonstrate that FedSB outperforms competing methods, achieving state-of-the-art results on three out of four datasets, indicating the effectiveness of FedSB in addressing data heterogeneity.
format Preprint
id arxiv_https___arxiv_org_abs_2412_11408
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Federated Domain Generalization with Label Smoothing and Balanced Decentralized Training
Soltany, Milad
Pourpanah, Farhad
Molahasani, Mahdiyar
Greenspan, Michael
Etemad, Ali
Machine Learning
Artificial Intelligence
In this paper, we propose a novel approach, Federated Domain Generalization with Label Smoothing and Balanced Decentralized Training (FedSB), to address the challenges of data heterogeneity within a federated learning framework. FedSB utilizes label smoothing at the client level to prevent overfitting to domain-specific features, thereby enhancing generalization capabilities across diverse domains when aggregating local models into a global model. Additionally, FedSB incorporates a decentralized budgeting mechanism which balances training among clients, which is shown to improve the performance of the aggregated global model. Extensive experiments on four commonly used multi-domain datasets, PACS, VLCS, OfficeHome, and TerraInc, demonstrate that FedSB outperforms competing methods, achieving state-of-the-art results on three out of four datasets, indicating the effectiveness of FedSB in addressing data heterogeneity.
title Federated Domain Generalization with Label Smoothing and Balanced Decentralized Training
topic Machine Learning
Artificial Intelligence
url https://arxiv.org/abs/2412.11408