Joint Channel Estimation and Dynamics-Aware Grouping for Time-Varying RIS-Assisted OTA Federated Learning
Information Theory
Summary
The authors address problems in using special surfaces (RIS) to help devices learn together wirelessly (OTA-FL), which struggle when signals change fast and users are very different. They created a system that better predicts changing signal conditions using a type of neural network (GRU) and groups users smartly based on how their signals vary, improving the learning process. Their method also combines signal estimation, group management, and hardware settings in a loop to make learning more accurate and faster. Simulations show their approach works especially well when signal measurements are scarce and users move a lot.
Authors
Ziqi Li, Shuangzhi Li, Uchechukwu Awada, Jiankang Zhang
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.