Skip to content

ChanglongShi/FedAWA

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

10 Commits
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 

Repository files navigation

arXiv

This is the official implementation of the CVPR 2025 paper "FedAWA: Adaptive Optimization of Aggregation Weights in Federated Learning Using Client Vectors".

FedAWA

Our code is based on Python version 3.7 and PyTorch version 1.13.1. You can run FedAWA with the following command:

python main.py --dataset cifar100 --local_model ResNet20 --server_method fedawa --client_method local_train #FedAWA on CIFAR-100 dataset with ResNet20 model

Citing This Repository

Please cite our paper if you find this repo useful in your work:

@misc{shi2025fedawaadaptiveoptimizationaggregation,
      title={FedAWA: Adaptive Optimization of Aggregation Weights in Federated Learning Using Client Vectors}, 
      author={Changlong Shi and He Zhao and Bingjie Zhang and Mingyuan Zhou and Dandan Guo and Yi Chang},
      year={2025},
      eprint={2503.15842},
      archivePrefix={arXiv},
      primaryClass={cs.LG},
      url={https://arxiv.org/abs/2503.15842}, 
}

Acknowledgement

We would like to thank the authors for releasing the public repository: ICML-2023-FedLAW

Contact

Please feel free to contact via email ([email protected]) if you have any questions.

About

No description, website, or topics provided.

Resources

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published

Languages