This paper presents a novel two-stage deep reinforcement learning (DRL) algorithm built on a Transformer Encoder-based Deep Deterministic Policy Gradient (TEDDPG) framework, named TS-TEDDPG, which jointly optimizes the learning latency, energy consumption and model accuracy of Asynchronous Federated Learning (AFL) systems with prescribed security. The CPU configuration of local training and the transmit power of model uploading are learnt by the TEDDPG in the first stage. A linear programming-based device scheduling and cooperative jamming strategy is designed to efficiently optimize the rest of the decisions in the second stage and evaluates the immediate reward to train the TEDDPG. Experimental results based on a CNN model and the MNIST dataset demonstrate that the proposed TS-TEDDPG can reduce the training latency and energy consumption by 68.6% compared to its benchmarks, when the required test accuracy is 0.9.


    Zugriff

    Zugriff prüfen

    Verfügbarkeit in meiner Bibliothek prüfen

    Bestellung bei Subito €


    Exportieren, teilen und zitieren



    Titel :

    Privacy-Preserving Resource Allocation for Asynchronous Federated Learning


    Beteiligte:
    Chen, Xiaojing (Autor:in) / Zhou, Zheer (Autor:in) / Ni, Wei (Autor:in) / Pan, Guangjin (Autor:in) / Wang, Xin (Autor:in) / Zhang, Shunqing (Autor:in) / Sun, Yanzan (Autor:in)


    Erscheinungsdatum :

    24.06.2024


    Format / Umfang :

    1558231 byte





    Medientyp :

    Aufsatz (Konferenz)


    Format :

    Elektronische Ressource


    Sprache :

    Englisch



    FedGRU: Privacy-preserving Traffic Flow Prediction via Federated Learning

    Liu, Yi / Zhang, Shuyu / Zhang, Chenhan et al. | IEEE | 2020




    Preserving Privacy with Federated Learning in Route Choice Behavior Modeling

    Kweon, Yonghyeon / Sun, Bingrong / Park, B. Brian | Transportation Research Record | 2021


    Efficient privacy-preserving federated learning method for Internet of Ships

    Zehui ZHANG / Cong GUAN / Hang GAO et al. | DOAJ | 2022

    Freier Zugriff