English

Federated Learning via Active RIS Assisted Over-the-Air Computation

Information Theory 2023-11-08 v1 Signal Processing math.IT

Abstract

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.

Keywords

Cite

@article{arxiv.2311.03982,
  title  = {Federated Learning via Active RIS Assisted Over-the-Air Computation},
  author = {Deyou Zhang and Ming Xiao and Mikael Skoglund and H. Vincent Poor},
  journal= {arXiv preprint arXiv:2311.03982},
  year   = {2023}
}

Comments

This paper was submitted to the IEEE International Conference on Machine Learning for Communication and Networking (ICMLCN), Stockholm, Sweden, 2024

R2 v1 2026-06-28T13:14:01.670Z