This is a simulator for distributed Graph Federated Learning on a single host. It implements our works and some graph learning methods as benchmarks.
This is a Python project. The third party dependencies are listed in requirements.txt. If you use pip, it should be easy to install:
python3 -m pip install . --user
To run the experiments of Historical Embedding-Guided Efficient Large-Scale Federated Graph Learning, use this command
bash fed_aas.shIf you find this work useful, feel free to cite it:
@article{li2024historical,
title={Historical Embedding-Guided Efficient Large-Scale Federated Graph Learning},
author={Li, Anran and Chen, Yuanyuan and Zhang, Jian and Cheng, Mingfei and Huang, Yihao and Wu, Yueming and Luu, Anh Tuan and Yu, Han},
journal={Proceedings of the ACM on Management of Data},
volume={2},
number={3},
pages={1--24},
year={2024},
publisher={ACM New York, NY, USA}
}