With the advancement of device capabilities, Internet of Things (IoT) devices can employ built-in hardware to perform machine learning (ML) tasks, extending their horizons in many promising directions. In traditional ML, data are sent to a server for training. However, this approach raises user privacy concerns. On the other hand, transferring user data to a cloud-centric environment results in increased latency. A decentralized ML technique, Federated learning (FL), has been proposed to enable devices to train locally on personal data and then send the data to a server for model aggregation. In these models, malicious devices, or devices with a minor contribution to a global model, increase communication rounds and resource usage. Likewise, heterogeneous data, such as non-independent and identically distributed (Non-IID), may decrease accuracy of the FL model. This paper proposes a mechanism to quantify device contributions based on weight divergence. We propose an outlier-removal approach which identifies irrelevant device updates. Client selection probabilities are computed using a Bayesian model. To obtain a global model, we employ a novel merging algorithm utilizing weight shifting values to ensure convergence towards more accurate predictions. A simulation using the MNIST dataset employing both non-iid and iid devices, distributed on 10 Jetson Nano devices, shows that our approach converges faster, significantly reduces communication cost, and improves accuracy.


    Zugriff

    Zugriff prüfen

    Verfügbarkeit in meiner Bibliothek prüfen

    Bestellung bei Subito €


    Exportieren, teilen und zitieren



    Titel :

    Fast converging Federated Learning with Non-IID Data


    Beteiligte:
    Naas, Si-Ahmed (Autor:in) / Sigg, Stephan (Autor:in)


    Erscheinungsdatum :

    01.06.2023


    Format / Umfang :

    2866265 byte





    Medientyp :

    Aufsatz (Konferenz)


    Format :

    Elektronische Ressource


    Sprache :

    Englisch



    Fast Converging Genetic Algorithm and Its Application

    Jie, Y. / Binggang, C. / Weixiang, S. | British Library Online Contents | 2001


    Fast Wireless Federated Learning with Adaptive Synchronous Degree Control

    Chen, Zhixiong / Yi, Wenqiang / Shin, Hyundong et al. | IEEE | 2024


    Fast Converging ADMM-Penalized Algorithm for Turbo-Like OVXDM

    Lin, Peng / Wang, Yafeng / Li, Daoben | IEEE | 2017



    Converging technologies

    Online Contents | 2012