Combating Interference for Over-the-Air Federated Learning: A Statistical Approach via RIS

2025-01-27

AI Summary

To address gradient estimation bias in AirFL caused by both unintentional and malicious interference, this paper proposes, for the first time, a Reconfigurable Intelligent Surface (RIS)-aided framework leveraging “phase-controlled favorable propagation” and “channel hardening.” The approach jointly optimizes RIS phase shifts, device transmit powers, and statistical channel modeling to achieve unbiased over-the-air computation (AirComp) aggregation. Theoretically, we prove that both the gradient estimation mean squared error (MSE) and the overall AirComp error converge at rate O(1/N), where N denotes the number of RIS elements; moreover, the FL convergence rate asymptotically approaches that of the ideal interference-free case. Numerical experiments demonstrate that the proposed method significantly outperforms existing baselines across diverse interference scenarios—including additive noise, jamming, and adversarial perturbations—while maintaining robustness and scalability.

Technology Category

• Machine Learning: Hardware-aware ML
• Search and Optimization: Learning to Search
• Intelligent Robots: Learning & Optimization for ROB

Application Category

• Security and Privacy: Large-scale security measurements
• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking
• Systems and Infrastructure for Web, Mobile and WoT: Applied ML and AI for Web-based mobile applications

Abstract

Over-the-air computation (AirComp) integrates analog communication with task-oriented computation, serving as a key enabling technique for communication-efficient federated learning (FL) over wireless networks. However, owing to its analog characteristics, AirComp-enabled FL (AirFL) is vulnerable to both unintentional and intentional interference. In this paper, we aim to attain robustness in AirComp aggregation against interference via reconfigurable intelligent surface (RIS) technology to artificially reconstruct wireless environments. Concretely, we establish performance objectives tailored for interference suppression in wireless FL systems, aiming to achieve unbiased gradient estimation and reduce its mean square error (MSE). Oriented at these objectives, we introduce the concept of phase-manipulated favorable propagation and channel hardening for AirFL, which relies on the adjustment of RIS phase shifts to realize statistical interference elimination and reduce the error variance of gradient estimation. Building upon this concept, we propose two robust aggregation schemes of power control and RIS phase shifts design, both ensuring unbiased gradient estimation in the presence of interference. Theoretical analysis of the MSE and FL convergence affirms the anti-interference capability of the proposed schemes. It is observed that computation and interference errors diminish by an order of $mathcal{O}left(frac{1}{N} ight)$ where $N$ is the number of RIS elements, and the ideal convergence rate without interference can be asymptotically achieved by increasing $N$. Numerical results confirm the analytical results and validate the superior performance of the proposed schemes over existing baselines.

Problem

• AirComp
• interference
• computational accuracy

Innovation

• Reconfigurable Intelligent Surface (RIS)
• AirComp Optimization
• Interference Reduction