Welcome to the official code repository for the ICLR 2024 paper "Aligning Relational Learning with Lipschitz Fairness"! This repository is dedicated to providing a comprehensive and easy-to-use implementation of the methodologies discussed in our paper.
Our work introduces a novel approach to align relational learning with Lipschitz fairness principles. This repository offers a hands-on experience to understand and implement our methods.
- Python 3.x
- Pip package manager
To set up the environment and install necessary dependencies, follow these steps:
git clone https://github.com/chunhuizng/lipschitz-fairness.git
cd lipschitz-fairness
pip install -r requirements.txt
Our implementation supports various tasks, including node classification and link prediction. Below are the instructions to run each task:
Navigate to the node classification directory and run the corresponding script:
cd node/
python jacolip_node.py
For link prediction tasks, use the following commands:
cd link/
python jacolip_link.py
We welcome contributions and suggestions to improve the code and methodologies. Please feel free to submit issues and pull requests.
If you find our work useful in your research, please consider citing:
@inproceedings{jia2024aligning,
title={Aligning Relational Learning with Lipschitz Fairness},
author={Yaning Jia and Chunhui Zhang and Soroush Vosoughi},
booktitle={International Conference on Learning Representations},
year={2024},
url={https://openreview.net/forum?id=ODSgo2m8aE}
}
For any queries regarding the code or research, please contact us at [email protected].
We would like to thank all the contributors and reviewers who helped in reviewing this research.
This project is licensed under the MIT License - see the LICENSE file for details.