Skip to main content
QUICK REVIEW

[论文解读] Federated Learning in Multi-RIS Aided Systems

Wanli Ni, Yuanwei Liu|arXiv (Cornell University)|Oct 26, 2020
Advanced Wireless Communication Technologies参考文献 39被引用 17
一句话总结

本文提出一种交替优化算法,通过使用多个可重构智能表面(RISs)来最小化空中联邦学习(AirFL)中的聚合误差并加速收敛。通过联合优化发射功率、接收标量、相位偏移和设备选择,该方法利用RIS辅助的信道重配置减少信号失真,与基线方法相比,实现了更快的收敛速度和更高的模型精度。

ABSTRACT

This paper investigates the problem of model aggregation in federated learning systems aided by multiple reconfigurable intelligent surfaces (RISs). The effective integration of computation and communication is achieved by over-the-air computation (AirComp). Since all local parameters are transmitted over shared wireless channels, the undesirable propagation error inevitably deteriorates the performance of global aggregation. The objective of this work is to 1) reduce the signal distortion of AirComp; 2) enhance the convergence rate of federated learning. Thus, the mean-square-error and the device set are optimized by designing the transmit power, controlling the receive scalar, tuning the phase shifts, and selecting participants in the model uploading process. The formulated mixed-integer non-linear problem (P0) is decomposed into a non-convex problem (P1) with continuous variables and a combinatorial problem (P2) with integer variables. To solve subproblem (P1), the closed-form expressions for transceivers are first derived, then the multi-antenna cases are addressed by the semidefinite relaxation. Next, the problem of phase shifts design is tackled by invoking the penalty-based successive convex approximation method. In terms of subproblem (P2), the difference-of-convex programming is adopted to optimize the device set for convergence acceleration, while satisfying the aggregation error demand. After that, an alternating optimization algorithm is proposed to find a suboptimal solution for problem (P0). Finally, simulation results demonstrate that i) the designed algorithm can converge faster and aggregate model more accurately compared to baselines; ii) the training loss and prediction accuracy of federated learning can be improved significantly with the aid of multiple RISs.

研究动机与目标

  • 解决无线信道中空中联邦学习(AirFL)的信号失真和聚合误差问题。
  • 提升多RIS辅助系统中AirFL的收敛速度和模型精度。
  • 联合优化发射功率、接收标量、RIS相位偏移和设备选择,以增强系统性能。
  • 在非正交多址接入(NOMA)和RIS信道重配置条件下,最小化模型聚合的均方误差(MSE)。
  • 平衡学习性能与网络能效及设备选择。

提出的方法

  • 将问题分解为非凸连续优化问题(P1)和相位偏移与设备集选择的组合整数问题(P2)。
  • 推导出用于最小化MSE的收发器闭式表达式,并在多天线场景中应用半定松弛(SDR)。
  • 采用基于惩罚的连续凸逼近(SCA)方法优化RIS相位偏移。
  • 应用差凸(DC)规划优化设备集,以实现更快收敛,同时满足聚合误差约束。
  • 提出一种交替优化算法,迭代求解P1和P2,并分析其收敛性和复杂度。
  • 该算法联合优化发射功率、接收标量、相位偏移和设备选择,以最小化聚合误差。

实验结果

研究问题

  • RQ1如何利用多个RIS最小化空中联邦学习中的信号失真?
  • RQ2如何实现发射功率、接收标量、RIS相位偏移和设备选择的最优联合设计,以加速AirFL收敛?
  • RQ3RIS辅助的信道重配置如何提升AirFL系统中的模型聚合精度?
  • RQ4在多RIS AirFL系统中,学习性能、能效与网络寿命之间存在何种权衡?
  • RQ5所提出的算法是否能相比基线方法实现更快的收敛速度和更低的聚合误差?

主要发现

  • 所提算法通过利用多个RIS重配置无线信道,显著降低了聚合误差。
  • 与传统和基线AirFL方案相比,模型收敛速度加快,训练损失降低。
  • 通过优化资源分配和设备选择,联邦学习的预测精度得到提升。
  • 通过联合优化功率、相位偏移和设备参与,该算法在模型聚合中实现了更低的均方误差(MSE)。
  • 通过选择更少设备并降低能耗,网络寿命得以延长,且性能随设备数量增加和所选参与者减少而提升。
  • 交替优化算法表现出良好的收敛性与低复杂度,适用于RIS辅助AirFL系统的实际部署。

更好的研究,从现在开始

从阅读论文到最终审阅,大幅缩短您的研究时间。

无需绑定信用卡

本解读由 AI 生成,并经人工编辑审核。