Blind Asynchronous Over-the-Air Federated Edge Learning

TL;DR

This paper introduces a synchronization-free over-the-air federated learning method that accurately recovers the global model without prior timing information, improving robustness and performance in asynchronous wireless environments.

Contribution

It proposes a novel convex optimization approach for asynchronous over-the-air federated learning that does not require prior synchronization, enhancing model recovery accuracy.

Findings

Achieves 10% accuracy close to ideal synchronized scenarios.

Performs 4 times better than no recovery method.

Effective in asynchronous wireless settings.

Abstract

Federated Edge Learning (FEEL) is a distributed machine learning technique where each device contributes to training a global inference model by independently performing local computations with their data. More recently, FEEL has been merged with over-the-air computation (OAC), where the global model is calculated over the air by leveraging the superposition of analog signals. However, when implementing FEEL with OAC, there is the challenge on how to precode the analog signals to overcome any time misalignment at the receiver. In this work, we propose a novel synchronization-free method to recover the parameters of the global model over the air without requiring any prior information about the time misalignments. For that, we construct a convex optimization based on the norm minimization problem to directly recover the global model by solving a convex semi-definite program. The performance of the proposed method is evaluated in terms of accuracy and convergence via numerical experiments. We show that our proposed algorithm is close to the ideal synchronized scenario by $10\%$, and performs $4\times$ better than the simple case where no recovering method is used.