Skip to content

Technique of Ordered Dropout as used in the paper "Fjord: Fair and accurate federated learning under heterogeneous targets with ordered dropout", NeurIPS'21

License

Notifications You must be signed in to change notification settings

SamsungLabs/ordered_dropout

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

2 Commits
 
 
 
 
 
 
 
 
 
 
 
 

Repository files navigation

Ordered Dropout

Implementation of Ordered Dropout (OD) for different type of NN layers in PyTorch.

The repo contains:

  • layers: Linear, CNN, LSTM,
  • simple example to showcase OD: example.ipynb.

How to run

pip install -r requirements
jupyter notebook

Reference

If you find this repo useful, please cite the paper that introduced notion of Ordered Dropout:

@article{horvath2021fjord,
  title={Fjord: Fair and accurate federated learning under heterogeneous targets with ordered dropout},
  author={Horvath, Samuel and Laskaridis, Stefanos and Almeida, Mario and Leontiadis, Ilias and Venieris, Stylianos and Lane, Nicholas},
  journal={Advances in Neural Information Processing Systems},
  volume={34},
  pages={12876--12889},
  year={2021}
}

About

Technique of Ordered Dropout as used in the paper "Fjord: Fair and accurate federated learning under heterogeneous targets with ordered dropout", NeurIPS'21

Resources

License

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published