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

TL;DR

This paper introduces an age-aware, edge-blind federated learning method over wireless channels that uses multiple antennas and selective parameter updates to improve convergence and reduce latency without requiring channel state information at devices.

Contribution

It proposes a novel over-the-air FL approach that employs AgeTop-k for parameter selection, balancing latency and accuracy, and provides convergence analysis highlighting the benefits of multiple antennas.

Findings

More antennas improve accuracy and convergence speed.

AgeTop-k outperforms random selection in good channel conditions.

Optimal k depends on channel noise, with smaller k better in noisy environments.

Abstract

We study federated learning (FL) over wireless fading channels where multiple devices simultaneously send their model updates. We propose an efficient 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 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.