FedBN

Feature normalization method

An approach to federated learning that addresses feature shift non-iid by normalizing local batch features before averaging models.

[ICLR'21] FedBN: Federated Learning on Non-IID Features via Local Batch Normalization

GitHub

231 stars
3 watching
36 forks
Language: Python
last commit: almost 2 years ago

Related projects:

Repository Description Stars
lins-lab/fedbr An implementation of federated learning algorithm to reduce local learning bias and improve convergence on heterogeneous data 25
gaoliang13/feddc Federated learning algorithm that adapts to non-IID data by decoupling and correcting for local drift 81
debcaldarola/fedsam Improving generalization in federated learning by seeking flat minima through optimization techniques 82
lunanbit/fedul This project presents an approach to federated learning that leverages unsupervised techniques to adapt models to unlabeled data without requiring labels. 33
mediabrain-sjtu/feddg-ga This project presents a method for federated domain generalization with adjustment, allowing multiple models to learn from each other across different domains. 43
ignavierng/notears-admm An implementation of Bayesian network structure learning with continuous optimization for federated learning. 10
mediabrain-sjtu/pfedgraph This project enables personalized federated learning with inferred collaboration graphs to improve the performance of machine learning models on non-IID (non-independent and identically distributed) datasets. 26
liuquande/feddg-elcfs This project presents a framework for federated domain generalization in medical image segmentation using continuous frequency space and episodic learning. 246
tmlr-group/fedfed An approach to mitigating data heterogeneity in federated learning by sharing partial features of the data. 17
med-air/harmofl A framework to harmonize local and global drifts in federated learning on heterogeneous medical images 86
allenbeau/pfedbayes An implementation of personalized federated learning using variational Bayesian inference on the MNIST dataset 52
atuannguyen/fedsr An implementation of a domain generalization method for federated learning using Python and PyTorch 26
mediabrain-sjtu/fedgela This project enables federated learning across partially class-disjoint data with curated bilateral curation. 11
mingruiliu-ml-lab/episode An algorithm for Federated Learning with heterogeneous data, designed to optimize deep neural networks and improve performance 2
chunmeifeng/fedpr An algorithm for learning federated visual prompts in null space to improve MRI reconstruction performance on limited local data and reduced communication costs 45