Federated Learning (FL) is a recent distributed technique to extract knowledge, i.e. an abstract understanding obtained from a set of information through experience and analysis. Vehicular networks are highly mobile networks in which a large spectrum of data types is distributed. So far, no mechanisms have been defined that distribute FL model updates in vehicular networks based on which nodes are likely to hold the right data for training, and when. In turn, this potentially limits FL model training speed and accuracy. In this paper, we describe protocols to exchange model-based training requirements based on the Vehicular Knowledge Networking framework. Based on this understanding, we define vehicular mobility and data distribution-aware FL orchestration mechanisms. An evaluation of the approach using a federated variant of the MNIST dataset shows training speed and model accuracy improvements compared to traditional FL training approaches.


    Zugriff

    Zugriff prüfen

    Verfügbarkeit in meiner Bibliothek prüfen

    Bestellung bei Subito €


    Exportieren, teilen und zitieren



    Titel :

    On the Orchestration of Federated Learning through Vehicular Knowledge Networking


    Beteiligte:
    Deveaux, Duncan (Autor:in) / Higuchi, Takamasa (Autor:in) / Ucar, Seyhan (Autor:in) / Wang, Chang-Heng (Autor:in) / Harri, Jerome (Autor:in) / Altintas, Onur (Autor:in)


    Erscheinungsdatum :

    2020-12-16


    Format / Umfang :

    1962646 byte





    Medientyp :

    Aufsatz (Konferenz)


    Format :

    Elektronische Ressource


    Sprache :

    Englisch



    VEHICULAR KNOWLEDGE NETWORKING ASSISTED ADAS CONFIGURATION

    UCAR SYEHAN / HIGUCHI TAKAMASA / ALTINTAS ONUR et al. | Europäisches Patentamt | 2023

    Freier Zugriff

    Risk Avoidance by Vehicular Knowledge Networking

    Ucar, Seyhan / Higuchi, Takamasa / Altintas, Onur | IEEE | 2022


    VEHICULAR KNOWLEDGE NETWORKING ASSISTED ADAS CONFIGURATION

    UCAR SEYHAN / HIGUCHI TAKAMASA / ALTINTAS ONUR et al. | Europäisches Patentamt | 2023

    Freier Zugriff

    VEHICULAR KNOWLEDGE NETWORKING ASSISTED ADAS CONFIGURATION

    UCAR SEYHAN / HIGUCHI TAKAMASA / ALTINTAS ONUR et al. | Europäisches Patentamt | 2024

    Freier Zugriff

    Vehicular cooperative perception through action branching and federated reinforcement learning

    Abdel-Aziz, M. K. (Mohamed K.) / Perfecto, C. (Cristina) / Samarakoon, S. (Sumudu) et al. | BASE | 2022

    Freier Zugriff