From Implicit to Explicit Assumptions: Why There is No Fairness Without Bias-Awareness

Marco Favier, Toon Calders
Proceedings of Fourth European Workshop on Algorithmic Fairness, PMLR 294:335-338, 2025.

Abstract

This extended abstract is a follow-up to our previous work –“Patriarchy Hurts Men Too.” Does Your Model Agree? A Discussion on Fairness Assumptions.– We discuss why implicit assumptions for fairness are tied to specific properties of the bias present in the data and why, without explicit assumptions, the choice of the correct model might be difficult. Moreover, we state a new result on one of these possible assumptions, proving the validity of the approach.

Cite this Paper

BibTeX
@InProceedings{pmlr-v294-favier25a, title = {From Implicit to Explicit Assumptions: Why There is No Fairness Without Bias-Awareness}, author = {Favier, Marco and Calders, Toon}, booktitle = {Proceedings of Fourth European Workshop on Algorithmic Fairness}, pages = {335--338}, year = {2025}, editor = {Weerts, Hilde and Pechenizkiy, Mykola and Allhutter, Doris and Corrêa, Ana Maria and Grote, Thomas and Liem, Cynthia}, volume = {294}, series = {Proceedings of Machine Learning Research}, month = {30 Jun--02 Jul}, publisher = {PMLR}, pdf = {https://raw.githubusercontent.com/mlresearch/v294/main/assets/favier25a/favier25a.pdf}, url = {https://proceedings.mlr.press/v294/favier25a.html}, abstract = {This extended abstract is a follow-up to our previous work –“Patriarchy Hurts Men Too.” Does Your Model Agree? A Discussion on Fairness Assumptions.– We discuss why implicit assumptions for fairness are tied to specific properties of the bias present in the data and why, without explicit assumptions, the choice of the correct model might be difficult. Moreover, we state a new result on one of these possible assumptions, proving the validity of the approach.} }
Endnote
%0 Conference Paper %T From Implicit to Explicit Assumptions: Why There is No Fairness Without Bias-Awareness %A Marco Favier %A Toon Calders %B Proceedings of Fourth European Workshop on Algorithmic Fairness %C Proceedings of Machine Learning Research %D 2025 %E Hilde Weerts %E Mykola Pechenizkiy %E Doris Allhutter %E Ana Maria Corrêa %E Thomas Grote %E Cynthia Liem %F pmlr-v294-favier25a %I PMLR %P 335--338 %U https://proceedings.mlr.press/v294/favier25a.html %V 294 %X This extended abstract is a follow-up to our previous work –“Patriarchy Hurts Men Too.” Does Your Model Agree? A Discussion on Fairness Assumptions.– We discuss why implicit assumptions for fairness are tied to specific properties of the bias present in the data and why, without explicit assumptions, the choice of the correct model might be difficult. Moreover, we state a new result on one of these possible assumptions, proving the validity of the approach.
APA
Favier, M. & Calders, T.. (2025). From Implicit to Explicit Assumptions: Why There is No Fairness Without Bias-Awareness. Proceedings of Fourth European Workshop on Algorithmic Fairness, in Proceedings of Machine Learning Research 294:335-338 Available from https://proceedings.mlr.press/v294/favier25a.html.

Related Material