… tion approach for on-device federated learning via over-the-air computation. To improve
the performance and the convergence rate for federated learning, we propose a joint device …

… To allow centralized training without data sharing, federated learning (FL) was proposed
in [4] as a method combining distributed training with central aggregation, and is the focus of …

… Federated learning (FL) tackles the aforementioned concerns by collaboratively training
a … As a typical FL algorithm, the federated averaging (FedAvg) proposed in [12] iteratively …

… In this section, we study the effect of analog aggregation transmission on FL over the air, by
… over the instantaneous SNRs, we derive the expected convergence rate of FL over the air, …

… Section II presents the federated learning model and our FL algorithm. Section III
provides the convergence analysis of our proposed algorithm. Section IV analyzes the system …

… In this work, we propose two schemes of federated learning with statistical channel state
information (FL-SCSI-A and FLSCSI-B) to reduce the communication overheads resulting from …

… To further improve the communication efficiency for distributed federated learning, in this
paper, we shall focus on developing the fast aggregation approach for local updates in the …

… 1, we consider a federated learning system supported by a … no central PS exists to coordinate
training process of all edge … to collaboratively learn a common machine learning model by …

… This work studied the power control optimization problem for the over-the-air federated
learning over fading channels by taking the gradient statistics into account. The optimal power …

… Abstract—Federated Learning (FL) is a distributed machine learning technique designed to
utilize the distributed datasets collected by our mobile and internet-of-things devices. As such…