PyTorch implementation of Federated Learning algorithms FedSGD, FedAvg, FedAvgM, FedIR, FedVC, FedProx and standard SGD, applied to visual classification. Client distributions are synthesized with arbitrary non-identicalness and imbalance (Dirichlet priors). Client systems can be arbitrarily heterogeneous. Several mobile-friendly models are prov…
pytorch
sgd
classification
heterogeneity
federated-learning
imbalance
non-iid
fedavg
fedprox
fedsgd
fedavgm
fedir
fedvc
-
Updated
Feb 27, 2022 - Python