In federated learning (FL), distributed clients can collaboratively train a shared global model while retaining their own training data locally. Nevertheless, the performance of FL is often limited by the slow convergence due to poor communications links when FL is deployed over wireless networks. Due to the scarceness of radio resources, it is crucial to select clients precisely and allocate communication resource accurately for enhancing FL performance. To address these challenges, in this paper, a joint optimization problem of client selection and resource allocation is formulated, aiming to minimize the total time consumption of each round in FL over a non-orthogonal multiple access (NOMA) enabled wireless network. Specifically, considering the staleness of the local FL models, we propose an age of update (AoU) based novel client selection scheme. Subsequently, the closed-form expressions for resource allocation are derived by monotonicity analysis and dual decomposition method. In addition, a server-side artificial neural network (ANN) is proposed to predict the FL models of clients who are not selected at each round to further improve FL performance. Finally, extensive simulation results demonstrate the superior performance of the proposed schemes over FL performance, average AoU and total time consumption.

翻译：在联邦学习（FL）中，分布式客户端可以在本地保留自身训练数据的同时协作训练共享的全局模型。然而，当FL部署于无线网络时，由于通信链路质量不佳，其性能往往受限于缓慢的收敛速度。鉴于无线资源的稀缺性，精确选择客户端并准确分配通信资源对于提升FL性能至关重要。为应对这些挑战，本文构建了客户端选择与资源分配的联合优化问题，旨在最小化非正交多址接入（NOMA）无线网络中FL每轮训练的总耗时。具体而言，考虑本地FL模型的陈旧性，我们提出了一种基于更新年龄（AoU）的新型客户端选择方案。进而，通过单调性分析与对偶分解法推导出资源分配的闭式表达式。此外，本文提出在服务器端使用人工神经网络（ANN）预测每轮未被选中客户端的FL模型，以进一步改善FL性能。最终，大量仿真结果表明，所提方案在FL性能、平均AoU及总耗时方面均具有显著优势。