Algorithmic Fairness Applied to the Multi-Label Classification Problem

Ana Paula S. Dantas, Gabriel Bianchin de Oliveira, Daiane Mendes de Oliveira, Helio Pedrini, Cid C. de Souza, Zanoni Dias

2023

Abstract

In recent years, a concern for algorithmic fairness has been increasing. Given that decision making algorithms are intrinsically embedded in our lives, their biases become more harmful. To prevent a model from displaying bias, we consider the coverage of the training to be an important factor. We define a problem called Fairer Coverage (FC) that aims to select the fairest training subset. We present a mathematical formulation for this problem and a protocol to translate a dataset into an instance of FC. We also present a case study by applying our method to the Single Cell Classification Problem. Experiments showed that our method improves the overall quality of the qualification while also increasing the quality of the classification for smaller individual underrepresented classes in the dataset.

Paper Citation

in Harvard Style

Dantas A., Bianchin de Oliveira G., Mendes de Oliveira D., Pedrini H., de Souza C. and Dias Z. (2023). Algorithmic Fairness Applied to the Multi-Label Classification Problem. In Proceedings of the 18th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications (VISIGRAPP 2023) - Volume 5: VISAPP; ISBN 978-989-758-634-7, SciTePress, pages 737-744. DOI: 10.5220/0011746400003417

in Bibtex Style

@conference{visapp23,
author={Ana Paula S. Dantas and Gabriel Bianchin de Oliveira and Daiane Mendes de Oliveira and Helio Pedrini and Cid C. de Souza and Zanoni Dias},
title={Algorithmic Fairness Applied to the Multi-Label Classification Problem},
booktitle={Proceedings of the 18th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications (VISIGRAPP 2023) - Volume 5: VISAPP},
year={2023},
pages={737-744},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0011746400003417},
isbn={978-989-758-634-7},
}

in EndNote Style

TY - CONF

JO - Proceedings of the 18th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications (VISIGRAPP 2023) - Volume 5: VISAPP
TI - Algorithmic Fairness Applied to the Multi-Label Classification Problem
SN - 978-989-758-634-7
AU - Dantas A.
AU - Bianchin de Oliveira G.
AU - Mendes de Oliveira D.
AU - Pedrini H.
AU - de Souza C.
AU - Dias Z.
PY - 2023
SP - 737
EP - 744
DO - 10.5220/0011746400003417
PB - SciTePress