An Autoencoder-Based Constellation Design for AirComp in Wireless Federated Learning

arXiv:2404.09392v1 Announce Type: cross
Abstract: Wireless federated learning (FL) relies on efficient uplink communications to aggregate model updates across distributed edge devices. Over-the-air computation (a.k.a. AirComp) has emerged as a promising approach for addressing the scalability challenge of FL over wireless links with limited communication resources. Unlike conventional methods, AirComp allows multiple edge devices to transmit uplink signals simultaneously, enabling the parameter server to directly decode the average global model. However, existing AirComp solutions are intrinsically analog, while modern wireless …

abstract arxiv autoencoder challenge communication communications computation constellation cs.it cs.lg cs.ni design devices distributed edge edge devices eess.sp federated learning math.it resources scalability type updates wireless