In this paper, we propose leveraging the active reconfigurable intelligence surface (RIS) to support reliable gradient aggregation for over-the-air computation (AirComp) enabled federated learning (FL) systems. An analysis of the FL convergence property reveals that minimizing gradient aggregation errors in each training round is crucial for narrowing the convergence gap. As such, we formulate an optimization problem, aiming to minimize these errors by jointly optimizing the transceiver design and RIS configuration. To handle the formulated highly non-convex problem, we devise a two-layer alternative optimization framework to decompose it into several convex subproblems, each solvable optimally. Simulation results demonstrate the superiority of the active RIS in reducing gradient aggregation errors compared to its passive counterpart.

翻译：本文提出利用主动可重构智能表面（RIS）支持基于空中计算（AirComp）的联邦学习（FL）系统中可靠的梯度聚合。关于FL收敛特性的分析表明，最小化每轮训练中的梯度聚合误差对于缩小收敛差距至关重要。为此，我们构建了一个优化问题，旨在通过联合优化收发器设计与RIS配置来最小化这些误差。为处理所提出的高度非凸问题，我们设计了一种双层交替优化框架，将其分解为若干可最优求解的凸子问题。仿真结果表明，与被动RIS相比，主动RIS在降低梯度聚合误差方面具有优越性。