JME-Fairness

This repository contains the implementation for paper: Joint Multisided Exposure Fairness for Recommendation (SIGIR 2022).

Code Overview

Folder

The data contains the datasets we used from here.

The saved_model contains the pre-trained model from here.

File

The read_data.py contains the data reading and preprocessing. The Disparity_Metrics.py contains the implementation of our proposed JME-Fairness metrics. The run_metric.py outputs the output values for different JME-Fairness metrics.

Run code

python run_metric.py

Citation

If you find this code or idea useful, please cite our work:

@inproceedings{wu2022joint,
  title={Joint Multisided Exposure Fairness for Recommendation},
  author={Wu, Haolun and Mitra, Bhaskar and Ma, Chen and Diaz, Fernando and Liu, Xue},
  booktitle={SIGIR},
  publisher = {{ACM}},
  year={2022}
}

Contact

If you have any questions, feel free to contact us through email ([email protected]) or Github issues. Enjoy!