Joint Channel Estimation and Dynamics-Aware Grouping for Time-Varying RIS-Assisted OTA Federated Learning

2026-07-19

AI Summary

This work addresses the degradation in aggregation accuracy and the cancellation of model updates in RIS-assisted over-the-air federated learning under time-varying channels, imperfect channel state information (CSI), and highly heterogeneous user conditions. To tackle these challenges, the paper proposes a unified framework that jointly performs channel estimation and dynamic, RIS-aware user grouping. The framework tightly integrates gated recurrent unit (GRU)-based temporal modeling, RIS-informed physical-layer optimization, and personalized over-the-air aggregation, innovatively designing grouping strategies that leverage both long-term path loss and short-term channel dynamics. Under low pilot overhead and high-mobility scenarios, the proposed approach significantly enhances channel estimation accuracy and over-the-air aggregation performance, accelerates convergence, and improves learning robustness in strongly heterogeneous environments.

Abstract

Reconfigurable intelligent surface (RIS)-assisted over-the-air federated learning (OTA-FL) enables efficient distributed intelligence but suffers from time-varying channels, imperfect channel state information (CSI), and strong user heterogeneity, which jointly degrade aggregation accuracy and cause severe model update cancellation. To address these issues, we propose a unified framework for joint channel estimation and dynamics-aware user grouping in RIS-assisted OTA-FL systems, enabling reliable learning under imperfect CSI and heterogeneous dynamics. The framework integrates gated recurrent unit (GRU) for temporal modeling to capture time-varying CSI evolution, OTA-based federated aggregation with personalization, and RIS-aware physical-layer optimization in a closed loop. In addition, we design a dynamics-aware grouping strategy based on long-term path-loss and short-term channel dynamics to reduce inter-user conflicts under heterogeneous conditions. Simulation results show that the proposed method achieves substantial gains in CSI estimation accuracy and OTA aggregation performance in low-pilot and high-mobility regimes, while improving convergence speed and robustness under strong user heterogeneity.

Problem

• time-varying channels
• imperfect CSI
• user heterogeneity
• model update cancellation
• aggregation accuracy

Innovation

• RIS-assisted OTA-FL
• joint channel estimation
• dynamics-aware grouping
• temporal modeling with GRU
• heterogeneous user aggregation