FedRec: Federated Learning of Universal Receivers over Fading Channels
share
Wireless communications are often subject to fading conditions. Various models have been proposed to capture the inherent randomness of fading in wireless channels, and conventional model-based receiver methods rely on accurate knowledge of this underlying distribution, which in practice may be complex and intractable. In this work we propose a collaborative neural network-based symbol detection mechanism for downlink fading channels, referred to as FedRec, which is based on the maximum a-posteriori probability (MAP) detector. To facilitate training using a limited number of pilots, while capturing a diverse ensemble of fading realizations, we propose a federated training scheme in which multiple users collaborate to jointly learn a universal data-driven detector. The performance of the resulting FedRec receiver is shown to approach the MAP performance in diverse channel conditions without requiring knowledge of the fading statistics, while inducing a substantially reduced communication overhead in its training procedure compared to training in a centralized fashion.
READ FULL TEXT
