DASFAA2023 - FedGR :Federated Learning with Gravitation Regulation for Double Imbalance Distribution

Federated learning for double unbalance settings (sample quantities imbalance for different classes in client and label or class imbalance for different client cross-client)

Framework of FedGR

Part of Experiment Results (full results are listed in our paper)

python main_fed.py -algo fedgr/fednova/fedavg/fedopt/moon -dataset cifar10/cifar100/fashion-mnist

Citation

This is the code for the 2023 DASFAA paper: FedGR: Federated Learning with Gravitation Regulation for Double Imbalance Distribution. Please cite our paper if you use the code:

@inproceedings{Guo2023FedGR
  author    = {Songyue Guo and
               Xu Yang and
               Jiyuan Feng and
               Ye Ding and 
               Wei Wang and
               Yunqing Feng and
               Qing Liao},
  title     = {FedGR: Federated Learning with Gravitation Regulation for Double Imbalance Distribution
},
  booktitle = {Database Systems for Advanced Applications - 28th International Conference,
               {DASFAA} 2023, Tianjin, China, April 17-20, 2023},
  publisher = {Springer},
  year      = {2023}
}