Saved in:
Bibliographic Details
Main Authors: Feng, Chao, Guan, Hongjie, Celdrán, Alberto Huertas, von der Assen, Jan, Bovet, Gérôme, Stiller, Burkhard
Format: Preprint
Published: 2024
Subjects:
Online Access:https://arxiv.org/abs/2410.07678
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866909448378777600
author Feng, Chao
Guan, Hongjie
Celdrán, Alberto Huertas
von der Assen, Jan
Bovet, Gérôme
Stiller, Burkhard
author_facet Feng, Chao
Guan, Hongjie
Celdrán, Alberto Huertas
von der Assen, Jan
Bovet, Gérôme
Stiller, Burkhard
contents Non-Independent and Identically Distributed (non-IID) data in Federated Learning (FL) causes client drift issues, leading to slower convergence and reduced model performance. While existing approaches mitigate this issue in Centralized FL (CFL) using a central server, Decentralized FL (DFL) remains underexplored. In DFL, the absence of a central entity results in nodes accessing a global view of the federation, further intensifying the challenges of non-IID data. Drawing on the entropy pooling algorithm employed in financial contexts to synthesize diverse investment opinions, this work proposes the Federated Entropy Pooling (FedEP) algorithm to mitigate the non-IID challenge in DFL. FedEP leverages Gaussian Mixture Models (GMM) to fit local data distributions, sharing statistical parameters among neighboring nodes to estimate the global distribution. Aggregation weights are determined using the entropy pooling approach between local and global distributions. By sharing only synthetic distribution information, FedEP preserves data privacy while minimizing communication overhead. Experimental results demonstrate that FedEP achieves faster convergence and outperforms state-of-the-art methods in various non-IID settings.
format Preprint
id arxiv_https___arxiv_org_abs_2410_07678
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle FedEP: Tailoring Attention to Heterogeneous Data Distribution with Entropy Pooling for Decentralized Federated Learning
Feng, Chao
Guan, Hongjie
Celdrán, Alberto Huertas
von der Assen, Jan
Bovet, Gérôme
Stiller, Burkhard
Machine Learning
Non-Independent and Identically Distributed (non-IID) data in Federated Learning (FL) causes client drift issues, leading to slower convergence and reduced model performance. While existing approaches mitigate this issue in Centralized FL (CFL) using a central server, Decentralized FL (DFL) remains underexplored. In DFL, the absence of a central entity results in nodes accessing a global view of the federation, further intensifying the challenges of non-IID data. Drawing on the entropy pooling algorithm employed in financial contexts to synthesize diverse investment opinions, this work proposes the Federated Entropy Pooling (FedEP) algorithm to mitigate the non-IID challenge in DFL. FedEP leverages Gaussian Mixture Models (GMM) to fit local data distributions, sharing statistical parameters among neighboring nodes to estimate the global distribution. Aggregation weights are determined using the entropy pooling approach between local and global distributions. By sharing only synthetic distribution information, FedEP preserves data privacy while minimizing communication overhead. Experimental results demonstrate that FedEP achieves faster convergence and outperforms state-of-the-art methods in various non-IID settings.
title FedEP: Tailoring Attention to Heterogeneous Data Distribution with Entropy Pooling for Decentralized Federated Learning
topic Machine Learning
url https://arxiv.org/abs/2410.07678