arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2408.09762cs.LG
收藏

非IID数据集下分层架构中的序贯联邦学习

Sequential Federated Learning in Hierarchical Architecture on Non-IID Datasets

Beijing Institute of Technology(北京理工大学);Sun Yat-Sen University(中山大学);Zhejiang Lab(之江实验室);Wuhan University(武汉大学)

Xingrun Yan, Shiyuan Zuo, Rongfei Fan, Han Hu, Li Shen, Puning Zhao, Yong Luo

AI总结:

针对联邦学习通信开销瓶颈问题,将序贯联邦学习引入分层架构并提出Fed-CHS算法,移除中心PS,在多种数据异构场景下收敛性可比基线,且通信开销更低、测试准确率更高。

摘要:

在真实的联邦学习(FL)系统中,客户端与参数服务器(PS)之间传递模型参数的通信开销往往是瓶颈。在客户端和PS之间设置多个边缘服务器(ES)的分层联邦学习(HFL)可部分缓解通信压力,但仍需PS聚合来自多个ES的模型参数。为进一步降低通信开销,我们首次将序贯联邦学习(SFL)引入HFL,该方案移除了中心PS,每次迭代仅需在两个相邻ES之间传递全局模型即可完成模型训练,并提出了一种适配该组合框架的新算法,命名为Fed-CHS。我们推导了该算法在强凸和非凸损失函数下、多种数据异构设置中的收敛性结果,表明其收敛性能与单独的HFL或SFL算法相当。实验结果证明,与基线方法相比,我们提出的Fed-CHS在节省通信开销和测试准确率方面均更具优势。

英文摘要:

In a real federated learning (FL) system, communication overhead for passing model parameters between the clients and the parameter server (PS) is often a bottleneck. Hierarchical federated learning (HFL) that poses multiple edge servers (ESs) between clients and the PS can partially alleviate communication pressure but still needs the aggregation of model parameters from multiple ESs at the PS. To further reduce communication overhead, we bring sequential FL (SFL) into HFL for the first time, which removes the central PS and enables the model training to be completed only through passing the global model between two adjacent ESs for each iteration, and propose a novel algorithm adaptive to such a combinational framework, referred to as Fed-CHS. Convergence results are derived for strongly convex and non-convex loss functions under various data heterogeneity setups, which show comparable convergence performance with the algorithms for HFL or SFL solely. Experimental results provide evidence of the superiority of our proposed Fed-CHS on both communication overhead saving and test accuracy over baseline methods.

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。

↑