Age-Aware Edge-Blind Federated Learning via Over-the-Air Aggregation

2026-02-02

AI Summary

This work addresses the challenges of federated learning over wireless fading channels, where limited channel state information (CSI) at devices and constrained orthogonal subcarriers lead to significant transmission delays. To overcome these issues, the authors propose an edge-based blind federated learning framework that eliminates the need for device-side CSI by leveraging a multi-antenna parameter server with maximal ratio combining (MRC) and over-the-air aggregation within a single OFDM symbol, thereby drastically reducing communication latency. The key innovation lies in the AgeTop-k coordinate selection mechanism, which adaptively balances compression and noise robustness by integrating age-awareness of model updates with magnitude-based thresholding. Experimental results demonstrate that increasing the number of server antennas enhances convergence speed and accuracy; furthermore, AgeTop-k outperforms random selection under favorable channel conditions, with the optimal sparsity level k dynamically decreasing in high-noise environments.

Technology Category

• Machine Learning: Learning on the Edge & Model Compression
• Multiagent Systems: Multiagent Learning
• Search and Optimization: Learning to Search

Application Category

• User Modeling, Personalization and Recommendation: Federated recommendation systems and personalization
• 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

Abstract

We study federated learning (FL) over wireless fading channels where multiple devices simultaneously send their model updates. We propose an efficient \emph{age-aware edge-blind over-the-air FL} approach that does not require channel state information (CSI) at the devices. Instead, the parameter server (PS) uses multiple antennas and applies maximum-ratio combining (MRC) based on its estimated sum of the channel gains to detect the parameter updates. A key challenge is that the number of orthogonal subcarriers is limited; thus, transmitting many parameters requires multiple Orthogonal Frequency Division Multiplexing (OFDM) symbols, which increases latency. To address this, the PS selects only a small subset of model coordinates each round using \emph{AgeTop-\(k\)}, which first picks the largest-magnitude entries and then chooses the \(k\) coordinates with the longest waiting times since they were last selected. This ensures that all selected parameters fit into a single OFDM symbol, reducing latency. We provide a convergence bound that highlights the advantages of using a higher number of antenna array elements and demonstrates a key trade-off: increasing \(k\) decreases compression error at the cost of increasing the effect of channel noise. Experimental results show that (i) more PS antennas greatly improve accuracy and convergence speed; (ii) AgeTop-\(k\) outperforms random selection under relatively good channel conditions; and (iii) the optimum \(k\) depends on the channel, with smaller \(k\) being better in noisy settings.

Problem

• federated learning
• wireless fading channels
• over-the-air aggregation
• latency
• channel noise

Innovation

• over-the-air aggregation
• age-aware selection
• edge-blind federated learning
• maximum-ratio combining
• AgeTop-k