Toward Personalized Federated Learning Via Group Collaboration in IIoT

Jianfeng Lu, Haibo Liu, Riheng Jia, Jiangtao Wang, Lichao Sun, Shaohua Wan

    Research output: Contribution to journalArticlepeer-review

    3 Citations (Scopus)

    Abstract

    Despite the rapid growth of successful examples of Federated Learning (FL), it faces the heterogeneity of data, models, and devices in emerging applications of Industrial Internet of Things (IIoT). Existing efforts mainly focus on training multiple personalized models by adopting a global, cluster, or pairwise fashion. However, the global collaboration doesn't work well in case of the non-IID data distribution, cluster collaboration is often inefficient due to the single cluster pattern and high computational cost, and pairwise collaboration incurs the limitations of collaboration scope and communication efficiency. To address the problems, we propose a novel Personalized FL (PFL) framework with the game-theoretic insights, called group collaboration, to overcome the shortcomings of status quo. Specifically, we first formulate the group collaboration in PFL as a multi-leader multi-follower Stackelberg game, and then develop an ϵ -better response to efficiently characterize its unique equilibrium through cautiously proposing a potential function. Since the existing equilibrium may not be optimal, we further design a Robin Hood mechanism by using the idea of transferable utility to improve the performance of the training model. Meanwhile, we also prove that the new mechanism is sustainable and can converge to a stable state with an upper bound of the training loss. Last, extensive experiments on a simulated dataset and four real-world datasets demonstrate the superiority of our proposed approach compared to the state-of-the-art.
    Original languageEnglish
    Pages (from-to)8923-8932
    Number of pages10
    JournalIEEE Transactions on Industrial Informatics
    Volume19
    Issue number8
    Early online date18 Nov 2022
    DOIs
    Publication statusPublished - 1 Aug 2023

    Keywords

    • Collaboration
    • Computational modeling
    • Data models
    • Federated learning
    • Games
    • Industrial Internet of Things
    • Informatics
    • Training
    • group collaboration
    • heterogeneity
    • industrial Internet of Things
    • potential game

    ASJC Scopus subject areas

    • Control and Systems Engineering
    • Information Systems
    • Computer Science Applications
    • Electrical and Electronic Engineering

    Fingerprint

    Dive into the research topics of 'Toward Personalized Federated Learning Via Group Collaboration in IIoT'. Together they form a unique fingerprint.

    Cite this