FedAlign

Data heterogeneity solver

A federated learning framework designed to mitigate data heterogeneity in distributed learning settings.

Official repository for Local Learning Matters: Rethinking Data Heterogeneity in Federated Learning [CVPR 2022 Oral, Best Paper Finalist]

GitHub

55 stars
2 watching
13 forks
Language: Python
last commit: about 2 years ago

Related projects:

Repository Description Stars
zfancy/sfat Combating heterogeneity in federated learning by combining adversarial training with client-wise slack during aggregation 28
lyn1874/fedpvr An implementation of a federated learning algorithm for handling heterogeneous data 6
omarfoq/fedem Develops and evaluates federated learning algorithms for personalizing machine learning models across heterogeneous client data distributions. 154
mingruiliu-ml-lab/episode An algorithm for Federated Learning with heterogeneous data, designed to optimize deep neural networks and improve performance 2
litian96/fedprox An optimization framework designed to address heterogeneity in federated learning across distributed networks 643
maxencenoble/differential-privacy-for-heterogeneous-federated-learning An algorithm for balancing utility and privacy in federated learning on heterogeneous data 59
pengyang7881187/fedrl Enabling multiple agents to learn from heterogeneous environments without sharing their knowledge or data 54
aiot-mlsys-lab/fedrolex An approach to heterogeneous federated learning allowing for model training on diverse devices with varying resources. 61
yutong-dai/fednh An implementation of a federated learning framework for handling data heterogeneity in decentralized settings 38
litian96/ditto A framework for personalized federated learning to balance fairness and robustness in decentralized machine learning systems. 137
bytedance/feddecorr Provides an implementation of various heterogeneous federated learning methods and datasets to mitigate dimensional collapse in distributed machine learning 63
alshedivat/fedpa A modular JAX implementation of federated learning via posterior averaging for decentralized optimization 49
jiayunz/fedalign Develops an alignment framework for federated learning with non-identical client class sets 4
tmlr-group/fedfed An approach to mitigating data heterogeneity in federated learning by sharing partial features of the data. 15
diogenes0319/fedmd_clean An implementation of a heterogenous federated learning framework using model distillation. 149