Skip to content

Official implementation of SCARLET from the paper "Soft-Label Caching and Sharpening for Communication-Efficient Federated Distillation".

License

Notifications You must be signed in to change notification settings

kitsuyaazuma/SCARLET

Repository files navigation

SCARLET

uv Python Version from PEP 621 TOML GitHub License

Official implementation of SCARLET from the paper "Soft-Label Caching and Sharpening for Communication-Efficient Federated Distillation".

Important

The main branch contains a simplified implementation for better understanding of SCARLET’s core algorithms, using BlazeFL. For the exact experiment code and hyperparameter settings used in our paper, switch to the reproducibility branch.

Getting Started

uv

git clone https://github.com/kitsuyaazuma/SCARLET.git
cd SCARLET
uv sync

# NOTE: PYTHON_GIL=0 is required due to a triton issue (https://github.com/triton-lang/triton/issues/8491)
PYTHON_GIL=0 uv run python main.py

Docker

docker run -it --rm --gpus=all --name scarlet ghcr.io/kitsuyaazuma/scarlet:main --algorithm-name SCARLET

# or

git clone https://github.com/kitsuyaazuma/SCARLET.git
cd SCARLET
docker build -t scarlet .
docker run -it --rm --gpus=all --name scarlet scarlet:latest --algorithm-name SCARLET

Configuration

All hyperparameters are managed with Typer. You can see all available options by running:

uv run python main.py --help

Citation

If you use this code in your research, please cite our preprint:

@misc{azuma2025softlabelcachingsharpeningcommunicationefficient,
      title={Soft-Label Caching and Sharpening for Communication-Efficient Federated Distillation}, 
      author={Kitsuya Azuma and Takayuki Nishio and Yuichi Kitagawa and Wakako Nakano and Takahito Tanimura},
      year={2025},
      eprint={2504.19602},
      archivePrefix={arXiv},
      primaryClass={cs.LG},
      url={https://arxiv.org/abs/2504.19602}, 
}

About

Official implementation of SCARLET from the paper "Soft-Label Caching and Sharpening for Communication-Efficient Federated Distillation".

Topics

Resources

License

Stars

Watchers

Forks

Releases

No releases published

Packages

 
 
 

Languages