arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2407.03247cs.DC
收藏

通过基于不确定性的非对称互惠学习桥接联邦学习中的模型异构性

Bridging Model Heterogeneity in Federated Learning via Uncertainty-based Asymmetrical Reciprocity Learning

Jiaqi Wang, Chenxu Zhao, Lingjuan Lyu, Quanzeng You, Mengdi Huai, Fenglong Ma

AI总结:

本文提出 FedType 框架,通过小型相同代理模型和基于不确定性的非对称互惠学习方法,在无需公共数据的情况下桥接联邦学习中的模型异构性,同时保障隐私并降低通信成本。

摘要:

本文提出了 FedType,一个简单但具有开创性的框架,旨在填补联邦学习(FL)中异构模型聚合的研究空白。FedType 为客户端引入小型相同的代理模型,作为信息交换的代理,同时确保模型安全并实现高效通信。为了在客户端上的大型私有模型和小型代理模型之间传递知识,我们提出了一种新颖的基于不确定性的非对称互惠学习方法,无需任何公共数据。在基准数据集上进行的综合实验证明了 FedType 在不同设置下的有效性和泛化能力。我们的方法通过桥接模型异构性、消除对公共数据的依赖、优先考虑客户端隐私以及降低通信成本,重新定义了联邦学习范式。

英文摘要:

This paper presents FedType, a simple yet pioneering framework designed to fill research gaps in heterogeneous model aggregation within federated learning (FL). FedType introduces small identical proxy models for clients, serving as agents for information exchange, ensuring model security, and achieving efficient communication simultaneously. To transfer knowledge between large private and small proxy models on clients, we propose a novel uncertainty-based asymmetrical reciprocity learning method, eliminating the need for any public data. Comprehensive experiments conducted on benchmark datasets demonstrate the efficacy and generalization ability of FedType across diverse settings. Our approach redefines federated learning paradigms by bridging model heterogeneity, eliminating reliance on public data, prioritizing client privacy, and reducing communication costs.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑