Code accompanying the paper "Decentralized Federated Learning through Proxy Model Sharing" published in Nature Communications.

Authors: Shivam Kalra*, Junfeng Wen*, Jesse C. Cresswell*, Maksims Volkovs, Hamid R. Tizhoosh†

• * Denotes equal contribution
• † University of Waterloo / Vector Institute

• Python 3.9

conda create -n ProxyFL python=3.9 conda activate ProxyFL

• PyTorch 1.9.0

conda install pytorch=1.9.0 torchvision=0.10.0 numpy=1.21.2 -c pytorch

• mpi4py 3.1.2

conda install -c conda-forge mpi4py=3.1.2

• opacus 0.14.0

pip install 'opacus==0.14.0'

• matplotlib 3.4.3

conda install -c conda-forge matplotlib=3.4.3

Download data via

bash download_data.sh

Then run the script

bash run_exp.sh

If you find this code useful in your research, please cite the following paper:

@article{kalra2021proxyfl, author={Kalra, Shivam and Wen, Junfeng and Cresswell, Jesse C. and Volkovs, Maksims and Tizhoosh, H. R.}, title={Decentralized federated learning through proxy model sharing}, journal={Nature Communications}, year={2023}, month={May}, day={22}, volume={14}, number={1}, pages={2899}, issn={2041-1723}, doi={10.1038/s41467-023-38569-4} }