Skip to content

MediaBrain-SJTU/pFedGraph

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

3 Commits
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 

Repository files navigation

Personalized Federated Learning with Inferred Collaboration Graphs, ICML2023

Note: This repo is still in progress.

Dependencies

  • PyTorch = 1.12.0

Quick Start

  • Run FedAvg algorithm on CIFAR-10, skew partition, 10 clients, local iteration number is 200:
python fedavg.py --gpu "7" --dataset 'cifar10' --partition 'noniid-skew' --n_parties 10 --num_local_iterations 200
  • For fair comparisons on CIFAR-10, you can run the bash file. (Same to CIFAR-100 and Yahoo! Answers)
sh run_cifar10.sh
  • pfedgraph_approx.py runs the experiment that we regularize the local model with the unnormalized aggregated model.
  • pfedgraph_cosine.py runs the experiment that we regularize the local model with the normalized aggregated model.

Others

Cite

To cite, please use:

@inproceedings{ye2023personalized,
  title={Personalized Federated Learning with Inferred Collaboration Graphs},
  author={Ye, Rui and Ni, Zhenyang and Wu, Fangzhao and Chen, Siheng and Wang, Yanfeng},
  booktitle={International Conference on Machine Learning},
  pages={39801--39817},
  year={2023},
  organization={PMLR}
}

About

No description, website, or topics provided.

Resources

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published