This code repo is for our work "FairNN Conjoint Learning of Fair Representations for Fair Decisions" that has been accepted by Discovery Science 2020. This project is in the cooperation between Institut für Informationsverarbeitung (TNT), Leibniz University Hannover, Germany, and L3S research center Hannover, Germany. The work is supported by BIAS (Bias and Discrimination in Big Data and Algorithmic Processing. Philosophical Assessments, Legal Dimensions, and Technical Solutions) a project funded by the Volkswagen Foundation within the initiative AI and the Society of the Future for which the last authors are Principal Investigators.
Before running the code, please download the adult and bank dataset and put them under dictinoary.
the Pretrained model can be downloaded here
For convenience, we save the code into adult and bank folder for the utilization on the corresponding dataset seperately. Besides parameter settings, the codes are identical.
If our work has inspired you, or our code is useful for your work, please cite our work with:
@article{hu2020fairnn, title={FairNN-Conjoint Learning of Fair Representations for Fair Decisions}, author={Hu, Hongxin and Iosifidis, Vasileios and Liao, Wentong and Zhang, Hang and YingYang, Michael and Ntoutsi, Eirini and Rosenhahn, Bodo}, journal={arXiv preprint arXiv:2004.02173}, year={2020} }
This code repo is only available for research or education purpose. For commecial purpose, please contact us.