Hierarchical federated learning (HFL) allows edge devices aggregate trained parameters at local before global aggregation. However, data distribution as well as the service or application types of edge devices should be considered at the same time. In this paper, we propose a selective HFL (SHFL) algorithm that not only aims at accelerating model convergence but also at improving model robustness for independent and identically distributed (IID) data and non-IID data. The SHFL firstly performs clustering based on the data distribution of each client, then each cluster performs their training for local FL. After that, an extra FL training is performed as finetuning the aggregated model. The simulation results demonstrate that SHFL algorithm is superior to classic FL algorithms and an existing FL algorithm with hierarchical clustering scheme, especially for non-IID data.


    Access

    Check access

    Check availability in my library

    Order at Subito €


    Export, share and cite



    Title :

    SHFL: Selective Hierarchical Federated Learning for Non-IID Data Distribution


    Contributors:


    Publication date :

    2024-06-24


    Size :

    799677 byte





    Type of media :

    Conference paper


    Type of material :

    Electronic Resource


    Language :

    English



    Adaptive Transceiver Design for Wireless Hierarchical Federated Learning

    Zhou, Fangtong / Chen, Xu / Shan, Hangguan et al. | IEEE | 2023


    Toward Robust Hierarchical Federated Learning in Internet of Vehicles

    Zhou, Hongliang / Zheng, Yifeng / Huang, Hejiao et al. | IEEE | 2023


    Hierarchical Federated Learning with Edge Optimization in Constrained Networks

    Zhang, Xiaoyang / Tham, Chen-Khong / Wang, Wenyi | IEEE | 2024


    Federated Learning Framework Coping with Hierarchical Heterogeneity in Cooperative ITS

    Song, Rui / Zhou, Liguo / Lakshminarasimhan, Venkatnarayanan et al. | IEEE | 2022


    CAV decision-making method applying selective federated learning

    FU YUCHUAN / TANG XINLONG / LI CHANGLE | European Patent Office | 2023

    Free access