Haofeng Sun

On the Convergence of Hierarchical Federated Learning with Gradient Quantization and Imperfect Transmission

To enhance the robustness and convergence of hierarchical federated learning (HFL) in wireless networks with imperfect channel state information (CSI), a quantized HFL (QHFL) framework is proposed. Considering the local training and communication latency, the outage probability of quantized gradient…