In this work, we investigate federated edge learning over a fading multiple access channel. To alleviate the communication burden between the edge devices and the access point, we introduce a pioneering digital over-the-air computation strategy employing q-ary quadrature amplitude modulation, culminating in a low latency communication scheme. Indeed, we propose a new federated edge learning framework in which edge devices use digital modulation for over-the-air uplink transmission to the edge server while they have no access to the channel state information. Furthermore, we incorporate multiple antennas at the edge server to overcome the fading inherent in wireless communication. We analyze the number of antennas required to mitigate the fading impact effectively. We prove a nonasymptotic upper bound for the mean squared error for the proposed federated learning with digital over-the-air uplink transmissions under both noisy and fading conditions. Leveraging the derived upper bound, we characterize the convergence rate of the learning process of a non-convex loss function in terms of the mean square error of gradients due to the fading channel. Furthermore, we substantiate the theoretical assurances through numerical experiments concerning mean square error and the convergence efficacy of the digital federated edge learning framework. Notably, the results demonstrate that augmenting the number of antennas at the edge server and adopting higher-order modulations improve the model accuracy up to 60%.Index Terms-blind federated learning, digital modulation, federated edge learning, over-the-air computation[15]-[17], they studied FEEL problem over wireless fading multiple access channel (MAC).In parallel, the FEEL domain has observed substantial advancements in digital aggregation methods for wireless communication in federated learning applications. The onebit broadband digital aggregation (OBDA) method, outlined in [18], aims at reducing data communication, thereby conserving bandwidth and energy. Another significant development is adopting majority vote frequency-shift keying (FSK) techniques [17], which aims at harnessing modulation techniques for efficient and reliable data aggregation in wireless networks. Moreover, a phase asynchronous orthogonal frequency division multiplexing (OFDM)-based variant of OBDA has been introduced [19], characterized by the integration of joint channel decoding and aggregation decoders, specifically designed for digital OAC applications, enhancing privacy and efficiency by eliminating the necessity for raw data sharing.Nevertheless, these OBDA-centric methods exhibit certain limitations, predominantly confined to specific functions such as sign detection and particular machine learning training procedures, such as the signSGD problem [20]. To widen the class of functions for digital OAC, authors in [21] use balanced number systems for computing summation functions. Despite its potential, this approach requires the allocation of unique frequencies for each quantized level, thus rais...
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 4ˆbetter than the simple case where no recovering method is used.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.
hi@scite.ai
10624 S. Eastern Ave., Ste. A-614
Henderson, NV 89052, USA
Copyright © 2024 scite LLC. All rights reserved.
Made with 💙 for researchers
Part of the Research Solutions Family.