Handy PyTorch implementation of Federated Learning (for your painless research)

PyTorch implementation of FedProx (Federated Optimization for Heterogeneous Networks, MLSys 2020).

(NeurIPS 2022) Official Implementation of "Preservation of the Global Knowledge by Not-True Distillation in Federated Learning"

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…

An implementation of federated learning research baseline methods based on FedML-core, which can be deployed on real distributed cluster and help researchers to explore more problems existing in real FL systems.

(CVPR 2024) Official Implementation of "FedSOL: Stabilized Orthogonal Learning with Proximal Restrictions in Federated Learning"

We utilize the Adversarial Model Perturbations (AMP) regularizer to regularize clients’ models. The AMP regulzaizer is based on perturbing the model parameters so as to get a more generalized model. The claim of AMP regularizer is to reach flat minima and therefore is expected to reach flat minima in FL settings as well.