Generative AI-Powered Plugin for Robust Federated Learning in Heterogeneous IoT Networks

Fuente: arXiv
Guardado en:
Detalles Bibliográficos
Autores principales: Lee, Youngjoon, Gong, Jinu, Kang, Joonhyuk
Formato: Preprint
Publicado: 2024
Materias:
Acceso en línea:
Etiquetas: Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
_version_ 1866914167626137600
author Lee, Youngjoon
Gong, Jinu
Kang, Joonhyuk
author_facet Lee, Youngjoon
Gong, Jinu
Kang, Joonhyuk
contents Federated learning enables edge devices to collaboratively train a global model while maintaining data privacy by keeping data localized. However, the Non-IID nature of data distribution across devices often hinders model convergence and reduces performance. In this paper, we propose a novel plugin for federated optimization methods that approximates Non-IID data distributions to IID through generative AI-enhanced data augmentation and balanced sampling strategy. The key idea is to synthesize additional data for underrepresented classes on each edge device, leveraging generative AI to create a more balanced dataset across the FL network. Additionally, a balanced sampling approach at the central server selectively includes only the most IID-like devices, accelerating convergence while maximizing the global model's performance. Experimental results validate that our approach significantly improves convergence speed and robustness against data imbalance, establishing a flexible, privacy-preserving FL plugin that is applicable even in data-scarce environments.
format Preprint
id arxiv_https___arxiv_org_abs_2410_23824
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Generative AI-Powered Plugin for Robust Federated Learning in Heterogeneous IoT Networks
Lee, Youngjoon
Gong, Jinu
Kang, Joonhyuk
Machine Learning
Signal Processing
Federated learning enables edge devices to collaboratively train a global model while maintaining data privacy by keeping data localized. However, the Non-IID nature of data distribution across devices often hinders model convergence and reduces performance. In this paper, we propose a novel plugin for federated optimization methods that approximates Non-IID data distributions to IID through generative AI-enhanced data augmentation and balanced sampling strategy. The key idea is to synthesize additional data for underrepresented classes on each edge device, leveraging generative AI to create a more balanced dataset across the FL network. Additionally, a balanced sampling approach at the central server selectively includes only the most IID-like devices, accelerating convergence while maximizing the global model's performance. Experimental results validate that our approach significantly improves convergence speed and robustness against data imbalance, establishing a flexible, privacy-preserving FL plugin that is applicable even in data-scarce environments.
title Generative AI-Powered Plugin for Robust Federated Learning in Heterogeneous IoT Networks
topic Machine Learning
Signal Processing
url https://arxiv.org/abs/2410.23824