Jian-Qing Zhang

FedAD: An Adaptive Block Dropping Approach for Federated Learning on Resource-Constrained Devices

—In a federated learning environment with heterogeneous, limited and time-varying computational resource capabilities, it is challenging to update deep neural network in real-time. To address this challenge, we propose FedAD, an adaptive block-dropping approach for federated learning on resource-constrained devices. Fe...