Efficient Federated Learning with Heterogeneous Data and Adaptive Dropout

Fuente: arXiv
Salvato in:
Dettagli Bibliografici
Autori principali: Liu, Ji, Ma, Beichen, Yu, Qiaolin, Jin, Ruoming, Zhou, Jingbo, Zhou, Yang, Dai, Huaiyu, Wang, Haixun, Dou, Dejing, Valduriez, Patrick
Natura: Preprint
Pubblicazione: 2025
Soggetti:
Accesso online:
Tags: Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
_version_ 1866913940796080128
author Liu, Ji
Ma, Beichen
Yu, Qiaolin
Jin, Ruoming
Zhou, Jingbo
Zhou, Yang
Dai, Huaiyu
Wang, Haixun
Dou, Dejing
Valduriez, Patrick
author_facet Liu, Ji
Ma, Beichen
Yu, Qiaolin
Jin, Ruoming
Zhou, Jingbo
Zhou, Yang
Dai, Huaiyu
Wang, Haixun
Dou, Dejing
Valduriez, Patrick
contents Federated Learning (FL) is a promising distributed machine learning approach that enables collaborative training of a global model using multiple edge devices. The data distributed among the edge devices is highly heterogeneous. Thus, FL faces the challenge of data distribution and heterogeneity, where non-Independent and Identically Distributed (non-IID) data across edge devices may yield in significant accuracy drop. Furthermore, the limited computation and communication capabilities of edge devices increase the likelihood of stragglers, thus leading to slow model convergence. In this paper, we propose the FedDHAD FL framework, which comes with two novel methods: Dynamic Heterogeneous model aggregation (FedDH) and Adaptive Dropout (FedAD). FedDH dynamically adjusts the weights of each local model within the model aggregation process based on the non-IID degree of heterogeneous data to deal with the statistical data heterogeneity. FedAD performs neuron-adaptive operations in response to heterogeneous devices to improve accuracy while achieving superb efficiency. The combination of these two methods makes FedDHAD significantly outperform state-of-the-art solutions in terms of accuracy (up to 6.7% higher), efficiency (up to 2.02 times faster), and computation cost (up to 15.0% smaller).
format Preprint
id arxiv_https___arxiv_org_abs_2507_10430
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Efficient Federated Learning with Heterogeneous Data and Adaptive Dropout
Liu, Ji
Ma, Beichen
Yu, Qiaolin
Jin, Ruoming
Zhou, Jingbo
Zhou, Yang
Dai, Huaiyu
Wang, Haixun
Dou, Dejing
Valduriez, Patrick
Distributed, Parallel, and Cluster Computing
Artificial Intelligence
Machine Learning
Federated Learning (FL) is a promising distributed machine learning approach that enables collaborative training of a global model using multiple edge devices. The data distributed among the edge devices is highly heterogeneous. Thus, FL faces the challenge of data distribution and heterogeneity, where non-Independent and Identically Distributed (non-IID) data across edge devices may yield in significant accuracy drop. Furthermore, the limited computation and communication capabilities of edge devices increase the likelihood of stragglers, thus leading to slow model convergence. In this paper, we propose the FedDHAD FL framework, which comes with two novel methods: Dynamic Heterogeneous model aggregation (FedDH) and Adaptive Dropout (FedAD). FedDH dynamically adjusts the weights of each local model within the model aggregation process based on the non-IID degree of heterogeneous data to deal with the statistical data heterogeneity. FedAD performs neuron-adaptive operations in response to heterogeneous devices to improve accuracy while achieving superb efficiency. The combination of these two methods makes FedDHAD significantly outperform state-of-the-art solutions in terms of accuracy (up to 6.7% higher), efficiency (up to 2.02 times faster), and computation cost (up to 15.0% smaller).
title Efficient Federated Learning with Heterogeneous Data and Adaptive Dropout
topic Distributed, Parallel, and Cluster Computing
Artificial Intelligence
Machine Learning
url https://arxiv.org/abs/2507.10430