This paper investigates the model aggregation process in an over-the-air federated learning (AirFL) system, where an intelligent reflecting surface (IRS) is deployed to assist the transmission from users to the base station (BS). With the purpose of overcoming the absence of the security examination against malicious individuals, successive interference cancellation (SIC) is adopted as a basis to support analyzing statistic characteristics of model parameters from devices. The objective of this paper is to minimize the mean-square-error by jointly optimizing the receive beamforming vector at the BS, transmit power allocation at users, and phase shift matrix of the IRS, subject to the transmit power constraint for devices, unit-modulus constraint for reflecting elements, SIC decoding order constraint and quality-of-service constraint. To address this complicated problem, alternating optimization is employed to decompose it into three subproblems, where the optimal receive beamforming vector is obtained by solving the first subproblem with the Lagrange dual method. Then, the convex relaxation method is applied to the transmit power allocation subproblem to find a suboptimal solution. Eventually, the phase shift matrix subproblem is addressed by invoking the semidefinite relaxation. Simulation results validate the availability of IRS and the effectiveness of the proposed scheme in improving federated learning performance.
翻译:本文调查了超空联合学习系统(AirFL)中的模型汇总过程,该系统部署了一个智能反射表面(IRS),以协助用户向基地站传送信号。为了克服恶意个人缺乏安全检查的问题,连续取消干扰(SIC),作为支持分析设备模型参数统计特征的基础。本文件的目标是通过在BS联合优化接收波形矢量,向用户传输权力分配和IRS的相向转换矩阵,但需服从设备传输动力限制,对反映要素的单位模式限制,SIC解码命令限制和服务质量限制。为了解决这一复杂问题,采用交替优化,将其分解成三个子问题,通过用Lagrange双向方法解决第一个子问题,最大限度地减少平均方位向矢量,向用户传输动力分配,向用户和IRS的相位转换矩阵,但需服从设备传输动力限制,对反映要素的单位模式限制,SICD解码命令限制和服务质量限制。为了解决这一复杂问题,采用交替优化的方法将模型分解成矢量,通过解双向双向双向双向两种方法解决。然后,在Simpreplalstalstalevlationstalevalstalstmlation silstalstalstalismlationalismmlationalmlationalmessmolmolmolmolmolmmolmolmmmmolmolmolmolmolmmmmolmolmolmolmolmolmolmolmolmolmolmolmolmolmolmolmolmolddaldddaldaldaldddddddddddaldaldaldaldaldaldaldaldaldaldaldaldaldaldaldaldaldaldddddaldddddddalddddddaldaldaldaldaldaldaldaldaldaldaldaldaldaldaldaldaldaldaldaldaldaldaldaldaldaldaldaldaldaldal 。最后将采用, 。 。 。 。