In this paper, we investigate over-the-air model aggregation in a federated edge learning (FEEL) system. We introduce a Markovian probability model to characterize the intrinsic temporal structure of the model aggregation series. With this temporal probability model, we formulate the model aggregation problem as to infer the desired aggregated update given all the past observations from a Bayesian perspective. We develop a message passing based algorithm, termed temporal-structure-assisted gradient aggregation (TSA-GA), to fulfil this estimation task with low complexity and near-optimal performance. We further establish the state evolution (SE) analysis to characterize the behaviour of the proposed TSA-GA algorithm, and derive an explicit bound of the expected loss reduction of the FEEL system under certain standard regularity conditions. In addition, we develop an expectation maximization (EM) strategy to learn the unknown parameters in the Markovian model. We show that the proposed TSAGA algorithm significantly outperforms the state-of-the-art, and is able to achieve comparable learning performance as the error-free benchmark in terms of both convergence rate and final test accuracy.
翻译:在本文中,我们在一个联合边际学习系统(FEEL)中调查超空模型集成。我们引入了马尔科维亚概率模型模型,以描述模型集成的内在时间结构。我们利用这个时间概率模型模型,在从巴伊西亚角度对以往所有观察进行的所有观察后,在推算预期的综合更新方面,设计出模型集成问题。我们开发了一个基于信息的传导算法,称为时间结构辅助梯度汇总(TSA-GA),以低复杂性和接近最佳性能完成这一估算任务。我们进一步建立了国家演进分析,以描述拟议的TSA-GA算法的行为,并得出在某些标准常规条件下预期减少感觉损失的明确界限。此外,我们还开发了预期最大化战略,以学习Markovian模型中未知参数。我们表明,拟议的TSAGA算法大大超越了最新技术,并且能够取得可比较的学习业绩,作为在趋同率和最终测试准确性两方面的无误基准。