Skip to content

jangsoohyuk/Robust-Federated-Learning-with-Noisy-Labels

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

18 Commits
 
 
 
 
 
 
 
 
 
 
 
 
 
 

Repository files navigation

Robust Federated Learning with Noisy Labels

This is an unofficial PyTorch implementation of Robust Federated Learning with Noisy Labels.

Requirements

  • python 3.8.8
  • pytorch 1.8.0
  • torchvision 0.9.0

Usage

Results can be reproduced running the following:

MNIST

python3 main.py --gpu 0 --iid --dataset mnist --epochs 1000 --noise_type symmetric --noise_rate 0.2 
python3 main.py --gpu 0 --iid --dataset mnist --epochs 1000 --noise_type pairflip --noise_rate 0.2 

CIFAR10

python3 main.py --gpu 0 --iid --dataset cifar --epochs 1000 --noise_type symmetric --noise_rate 0.2 
python3 main.py --gpu 0 --iid --dataset cifar --epochs 1000 --noise_type pairflip --noise_rate 0.2 

References

  • Yang, S., Park, H., Byun, J., & Kim, C. (2020). Robust Federated Learning with Noisy Labels. arXiv preprint arXiv:2012.01700.

Acknowledgements

This codebase was adapted from https://github.com/shaoxiongji/federated-learning and https://github.com/bhanML/Co-teaching

About

Code for 'Robust Federated Learning with Noisy Labels'

Resources

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published

Languages