no code implementations • 26 Oct 2022 • Zhengjie Yang, Sen Fu, Wei Bao, Dong Yuan, Albert Y. Zomaya
In this paper, we propose Hierarchical Federated Learning with Momentum Acceleration (HierMo), a three-tier worker-edge-cloud federated learning algorithm that applies momentum for training acceleration.
no code implementations • 18 Sep 2020 • Zhengjie Yang, Wei Bao, Dong Yuan, Nguyen H. Tran, Albert Y. Zomaya
It is well-known that Nesterov Accelerated Gradient (NAG) is a more advantageous form of momentum, but it is not clear how to quantify the benefits of NAG in FL so far.