FAiRDAS

This repository provides the code for reproducing the results obtained in the paper FAiRDAS: Fairness-Aware Ranking as Dynamic Abstract System.

If you use this codebase, please cite:

@inproceedings{DBLP:conf/aequitas/MisinoC0M23,
  author       = {Eleonora Misino and
                  Roberta Calegari and
                  Michele Lombardi and
                  Michela Milano},
  editor       = {Roberta Calegari and
                  Andrea Aler Tubella and
                  Gabriel Gonz{\'{a}}lez{-}Casta{\~{n}}{\'{e}} and
                  Virginia Dignum and
                  Michela Milano},
  title        = {FAiRDAS: Fairness-Aware Ranking as Dynamic Abstract System},
  booktitle    = {Proceedings of the 1st Workshop on Fairness and Bias in {AI} co-located
                  with 26th European Conference on Artificial Intelligence {(ECAI} 2023),
                  Krak{\'{o}}w, Poland, October 1st, 2023},
  series       = {{CEUR} Workshop Proceedings},
  volume       = {3523},
  publisher    = {CEUR-WS.org},
  year         = {2023},
  url          = {https://ceur-ws.org/Vol-3523/paper5.pdf},
  timestamp    = {Tue, 19 Dec 2023 17:15:12 +0100},
  biburl       = {https://dblp.org/rec/conf/aequitas/MisinoC0M23.bib},
  bibsource    = {dblp computer science bibliography, https://dblp.org}
}

Prerequisites

• Python >=3.9
• Dependencies:

  pip install -r requirements.txt

Content

• demo.ipynb contains the steps to reproduce the paper experiments.
• utils folder contains the source code.

Corresponding Author

• Eleonora Misino - [email protected]