Over-The-Air Federated Learning Over Scalable Cell-free Massive MIMO

Cell-free massive MIMO is emerging as a promising technology for future wireless communication systems, which is expected to offer uniform coverage and high spectral efficiency compared to classical cellular systems. We study in this paper how cell-free massive MIMO can support federated edge learning. Taking advantage of the additive nature of the wireless multiple access channel, over-the-air computation is exploited, where the clients send their local updates simultaneously over the same communication resource. Such an approach, known as over-the-air federated learning (OT A-FL), is proven to alleviate the communication overhead of federated learning over wireless networks. Considering channel correlation and only imperfect channel state information available at the central server, we propose a practical implementation of OT A-FL over cell-free massive MIMO. The convergence of the proposed implementation is studied analytically and experimentally, confirming the benefits of cell-free massive MIMO for OT A-FL. With the exponential growth in data collection from distributed devices and remarkable advancements in AI applications, there is a growing interest in distributed learning, which leverages the computing capabilities of these devices. Distributed learning offers two primary benefits. Firstly, it eliminates the need to transfer massive volumes of high-dimensional data from the collecting devices to central servers (CSs) for further processing. Secondly, it inherently ensures privacy since local data is not shared. This work specifically focuses on federated learning (FL), a popular technique in distributed learning, where a CS coordinates global model training by communicating with multiple distributed clients [1]-[3].