FedAvgM算法的目标是在保持FedAvg算法简单性的同时,提高模型的性能和收敛速度。 在传统的FedAvg算法中,每个参与方(如移动设备或终端用户)会将本地的模型参数上传至中央服务器进行聚合。然而,由于参与方之间的异构性(包括计算能力、带宽等差异),以及数据分布不均匀等问题,FedAvg算法在某些情况下可能无法取得令人满意的...
Add a description, image, and links to the fedavgm topic page so that developers can more easily learn about it. Curate this topic Add this topic to your repo To associate your repository with the fedavgm topic, visit your repo's landing page and select "manage topics." Learn more...
This branch is5 commits ahead ofc-gabri/Federated-Learning-PyTorch:master. README License Federated Visual Classification (PyTorch): SGD, FedSGD, FedAvg, FedAvgM, FedIR, FedVC, FedProx PyTorch implementation of Federated Learning algorithms FedSGD, FedAvg, FedAvgM, FedIR, FedVC, FedProx and standard...