arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2210.17469cs.LGcs.DCeess.SP
收藏

盲异步空中联合边缘学习

Blind Asynchronous Over-the-Air Federated Edge Learning

KTH Royal Institute of Technology(KTH皇家理工学院);Princeton University(普林斯顿大学)

Saeed Razavikia, Jaume Anguera Peris, Jose Mairton B. da Silva, Carlo Fischione

摘要:

联邦边缘学习(FEEL)是一种分布式机器学习技术,其中每个设备通过独立地对其数据执行本地计算来训练全局推理模型。最近,FEEL已经与空中计算(OAC)合并,其中通过利用模拟信号的叠加来在空中计算全局模型。然而,当使用OAC实现FEEL时,存在如何对模拟信号进行预编码以克服接收器处的任何时间不对准的挑战。在这项工作中,我们提出了一种新的同步免费的方法来恢复在空中的全球模型的参数,而不需要任何先验信息的时间错位。为此,我们构造了一个基于范数最小化问题的凸优化,通过求解凸半定规划直接恢复全局模型。所提出的方法的性能进行评估,通过数值实验的精度和收敛性。我们表明,我们提出的算法是接近理想的同步情况下的$10\%$,并执行$4\times$比简单的情况下,没有使用恢复方法。

英文摘要:

Federated Edge Learning (FEEL) is a distributed machine learning technique where each device contributes to training a global inference model by independently performing local computations with their data. More recently, FEEL has been merged with over-the-air computation (OAC), where the global model is calculated over the air by leveraging the superposition of analog signals. However, when implementing FEEL with OAC, there is the challenge on how to precode the analog signals to overcome any time misalignment at the receiver. In this work, we propose a novel synchronization-free method to recover the parameters of the global model over the air without requiring any prior information about the time misalignments. For that, we construct a convex optimization based on the norm minimization problem to directly recover the global model by solving a convex semi-definite program. The performance of the proposed method is evaluated in terms of accuracy and convergence via numerical experiments. We show that our proposed algorithm is close to the ideal synchronized scenario by $10\%$, and performs $4\times$ better than the simple case where no recovering method is used.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑