Skip to content

This is the code for Addressing Class Imbalance in Federated Learning (AAAI-2021).

Notifications You must be signed in to change notification settings

balanced-fl/Addressing-Class-Imbalance-FL

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

13 Commits
 
 
 
 
 
 
 
 
 
 

Repository files navigation

Addressing Class Imbalance in Federated Learning

This is the code for our AAAI-2021 paper: Addressing Class Imbalance in Federated Learning.

Run the code

To run the monitoring scheme, you can

cd ./FEMNIST-monitor/
python3 main_nn.py

To load different loss functions on federated learning, you can

cd ./FEMNIST-4-Losses/
python3 main_nn.py --loss ce/focal/ratio/ghm

Citation

If you find our work is helpful for your research, please cite our paper.

@inproceedings{wang2021addressing,
  title={Addressing Class Imbalance in Federated Learning},
  author={Wang, Lixu and Xu, Shichao and Wang, Xiao and Zhu, Qi},
  booktitle={Proceedings of the AAAI Conference on Artificial Intelligence},
  volume={35},
  number={11},
  pages={10165--10173},
  year={2021}
}