FedTorch

Distributed learning framework

A software framework for benchmarking and implementing various algorithms in federated learning and distributed optimization using PyTorch Distributed API.

FedTorch is a generic repository for benchmarking different federated and distributed learning algorithms using PyTorch Distributed API.

GitHub

188 stars
7 watching
35 forks
Language: Python
last commit: over 2 years ago
distributeddistributed-optimizationfederated-learningmpipytorch

Related projects:

RepositoryDescriptionStars
omarfoq/fedemDevelops and evaluates federated learning algorithms for personalizing machine learning models across heterogeneous client data distributions.157
smilelab-fl/fedlabA flexible framework for distributed machine learning where participants train local models and collaboratively optimize them without sharing data743
litian96/fedproxAn optimization framework designed to address heterogeneity in federated learning across distributed networks655
aiot-mlsys-lab/fedrolexAn approach to heterogeneous federated learning allowing for model training on diverse devices with varying resources.61
yuetan031/fedprotoAn implementation of federated learning with prototype-based methods across heterogeneous clients134
charliedinh/pfedmeAn implementation of Personalized Federated Learning with Moreau Envelopes and related algorithms using PyTorch for research and experimentation.291
shenzebang/federated-learning-pytorchA PyTorch-based framework for Federated Learning experiments40
raymin0223/logoAn implementation of federated active learning with a novel sampling strategy to improve performance on decentralized machine learning tasks31
xtra-computing/fedsimA framework that enables federated learning across multiple datasets while optimizing model performance with record similarities.25
codepothunter/fednpA framework for non-IID federated learning via neural propagation6
lxcnju/fedrepoAn open-source repository implementing various federated learning algorithms with source code for multiple deep learning applications.175
scaleoutsystems/fednAn open source federated learning framework designed to be secure, scalable and easy-to-use for enterprise environments145
ibm/federated-learning-libA framework for collaborative distributed machine learning in enterprise environments.500
gingsmith/fmtlA framework for collaborative learning across multiple tasks and datasets in a distributed manner130
alshedivat/fedpaA modular JAX implementation of federated learning via posterior averaging for decentralized optimization50