RIS-Assisted Over-the-Air Adaptive Federated Learning with Noisy Downlink

TL;DR

This paper introduces a RIS-assisted over-the-air federated learning framework that optimizes communication and computation in noisy, resource-constrained wireless environments, improving convergence under realistic conditions.

Contribution

It proposes a novel cross-layer algorithm that jointly optimizes RIS configuration, power, and local updates for robust federated learning in noisy, heterogeneous wireless networks.

Findings

Outperforms existing methods in convergence speed and accuracy.

Effectively mitigates downlink noise and CSI imperfections.

Enhances federated learning robustness in practical wireless scenarios.

Abstract

Over-the-air federated learning (OTA-FL) exploits the inherent superposition property of wireless channels to integrate the communication and model aggregation. Though a naturally promising framework for wireless federated learning, it requires care to mitigate physical layer impairments. In this work, we consider a heterogeneous edge-intelligent network with different edge device resources and non-i.i.d. user dataset distributions, under a general non-convex learning objective. We leverage the Reconfigurable Intelligent Surface (RIS) technology to augment OTA-FL system over simultaneous time varying uplink and downlink noisy communication channels under imperfect CSI scenario. We propose a cross-layer algorithm that jointly optimizes RIS configuration, communication and computation resources in this general realistic setting. Specifically, we design dynamic local update steps in conjunction with RIS phase shifts and transmission power to boost learning performance. We present a convergence analysis of the proposed algorithm, and show that it outperforms the existing unified approach under heterogeneous system and imperfect CSI in numerical results.