Noise Resilient Over-The-Air Federated Learning In Heterogeneous Wireless Networks

2025-03-25

AI Summary

To address convergence instability in over-the-air federated learning (OTA-FL) for 6G wireless networks—caused by AWGN noise, channel fading, and data/system heterogeneity across edge devices—this paper proposes NoROTA-FL, a noise-robust OTA-FL framework. Methodologically, it introduces (i) controllable inexact local optimization and (ii) client-side proximal constraints—the first to establish convergence guarantees for non-convex objectives under zeroth- and first-order inexactness. It further integrates AirComp, channel-adaptive power scaling, heterogeneous-resource-aware scheduling, and proximal gradient control. Experiments on FEMNIST, CIFAR-10, and CIFAR-100 demonstrate that NoROTA-FL significantly improves convergence stability and communication robustness over baselines such as COTAF and FedProx, maintaining over 92% test accuracy even under high noise and multi-straggler conditions.

Technology Category

• Machine Learning: Distributed Machine Learning & Federated Learning
• Search and Optimization: Non-convex Optimization
• Intelligent Robots: Learning & Optimization for ROB

Application Category

• Systems and Infrastructure for Web, Mobile and WoT: Federated Web and WoT systems, including distributed, federated and edge-based data processing
• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking
• User Modeling, Personalization and Recommendation: Federated recommendation systems and personalization

Abstract

In 6G wireless networks, Artificial Intelligence (AI)-driven applications demand the adoption of Federated Learning (FL) to enable efficient and privacy-preserving model training across distributed devices. Over-The-Air Federated Learning (OTA-FL) exploits the superposition property of multiple access channels, allowing edge users in 6G networks to efficiently share spectral resources and perform low-latency global model aggregation. However, these advantages come with challenges, as traditional OTA-FL techniques suffer due to the joint effects of Additive White Gaussian Noise (AWGN) at the server, fading, and both data and system heterogeneity at the participating edge devices. In this work, we propose the novel Noise Resilient Over-the-Air Federated Learning (NoROTA-FL) framework to jointly tackle these challenges in federated wireless networks. In NoROTA-FL, the local optimization problems find controlled inexact solutions, which manifests as an additional proximal constraint at the clients. This approach provides robustness against straggler-induced partial work, heterogeneity, noise, and fading. From a theoretical perspective, we leverage the zeroth- and first-order inexactness and establish convergence guarantees for non-convex optimization problems in the presence of heterogeneous data and varying system capabilities. Experimentally, we validate NoROTA-FL on real-world datasets, including FEMNIST, CIFAR10, and CIFAR100, demonstrating its robustness in noisy and heterogeneous environments. Compared to state-of-the-art baselines such as COTAF and FedProx, NoROTA-FL achieves significantly more stable convergence and higher accuracy, particularly in the presence of stragglers.

Problem

• Addresses noise and fading in OTA-FL for 6G networks
• Mitigates data and system heterogeneity in federated learning
• Improves convergence stability and accuracy in noisy environments

Innovation

• Noise-resilient OTA-FL framework for 6G
• Proximal constraint for robustness
• Zeroth- and first-order inexactness convergence