Decentralized federated learning (DFL) has gained popularity due to its practicality across various applications. Compared to the centralized version, training a shared model among a large number of nodes in DFL is more challenging, as there is no central server to coordinate the training process. Especially when distributed nodes suffer from limitations in communication or computational resources, DFL will experience extremely inefficient and unstable training. Motivated by these challenges, in this paper, we develop a novel algorithm based on the framework of the inexact alternating direction method (iADM). On one hand, our goal is to train a shared model with a sparsity constraint. This constraint enables us to leverage one-bit compressive sensing (1BCS), allowing transmission of one-bit information among neighbour nodes. On the other hand, communication between neighbour nodes occurs only at certain steps, reducing the number of communication rounds. Therefore, the algorithm exhibits notable communication efficiency. Additionally, as each node selects only a subset of neighbours to participate in the training, the algorithm is robust against stragglers. Additionally, complex items are computed only once for several consecutive steps and subproblems are solved inexactly using closed-form solutions, resulting in high computational efficiency. Finally, numerical experiments showcase the algorithm's effectiveness in both communication and computation.


    Zugriff

    Zugriff prüfen

    Verfügbarkeit in meiner Bibliothek prüfen

    Bestellung bei Subito €


    Exportieren, teilen und zitieren



    Titel :

    Communication-Efficient Decentralized Federated Learning via One-Bit Compressive Sensing


    Beteiligte:
    Zhou, Shenglong (Autor:in) / Xu, Kaidi (Autor:in) / Li, Geoffrey Ye (Autor:in)


    Erscheinungsdatum :

    24.06.2024


    Format / Umfang :

    374917 byte





    Medientyp :

    Aufsatz (Konferenz)


    Format :

    Elektronische Ressource


    Sprache :

    Englisch




    Communication-efficient and federated multi-agent reinforcement learning

    Krouka, M. (Mounssif) / Elgabli, A. (Anis) / Issaid, C. B. (Chaouki Ben) et al. | BASE | 2022

    Freier Zugriff


    A Decentralized Blockchain-Enabled Federated Learning Approach for Vehicular Networks

    Sultana, Shirin / Hossain, Jahin / Billah, Maruf et al. | IEEE | 2023


    Cluster Based Pseudo Hierarchical Decentralized Federated Learning in UAV Networks

    Rayudu Tummala, Veera Manikantha / Hazra, Abhishek / Kalita, Alakesh et al. | IEEE | 2024