Client Selection and Cost-Efficient Joint Optimization for NOMA-Enabled Hierarchical Federated Learning

Bibo Wu, Fang Fang, Xianbin Wang, Donghong Cai, Shu Fu, Zhiguo Ding

    Research output: Contribution to journalArticlepeer-review

    Abstract

    Hierarchical federated learning (HFL) shows great advantages over conventional two-layer federated learning (FL) in reducing network overhead and interaction latency while still retaining the data privacy of distributed FL clients. However, the communication and energy overhead still pose a bottleneck for HFL performance, especially as the number of clients raises dramatically. To tackle this issue, we propose a non-orthogonal multiple access (NOMA) enabled HFL system under semi-synchronous cloud model aggregation in this paper, aiming to minimize the total cost of time and energy at each HFL global round. Specifically, we first propose a novel fuzzy logic based client selection policy considering client heterogeneity in multiple aspects, including channel quality, data quantity and model staleness. Subsequently, given the fuzzy based client-edge association, a joint edge server scheduling and resource allocation problem is formulated. Utilizing problem decomposition, we firstly derive the closed-form solution for the edge server scheduling subproblem via the penalty dual decomposition (PDD) method. Next, a deep deterministic policy gradient (DDPG) based algorithm is proposed to tackle the resource allocation subproblem considering time-varying environments. Finally, extensive simulations demonstrate that the proposed scheme outperforms the considered benchmarks regarding HFL performance improvement and total cost reduction.

    Original languageBritish English
    Pages (from-to)1
    Number of pages1
    JournalIEEE Transactions on Wireless Communications
    DOIs
    StateAccepted/In press - 2024

    Keywords

    • Client selection
    • Costs
    • Data models
    • deep reinforcement learning
    • Fuzzy logic
    • hierarchical federated learning
    • NOMA
    • resource allocation
    • Resource management
    • Servers
    • Training

    Fingerprint

    Dive into the research topics of 'Client Selection and Cost-Efficient Joint Optimization for NOMA-Enabled Hierarchical Federated Learning'. Together they form a unique fingerprint.

    Cite this