Generalized Disparate Impact for Configurable Fairness Solutions in ML

Luca Giuliani, Eleonora Misino, Michele Lombardi
Proceedings of the 40th International Conference on Machine Learning, PMLR 202:11443-11458, 2023.

Abstract

We make two contributions in the field of AI fairness over continuous protected attributes. First, we show that the Hirschfeld-Gebelein-Renyi (HGR) indicator (the only one currently available for such a case) is valuable but subject to a few crucial limitations regarding semantics, interpretability, and robustness. Second, we introduce a family of indicators that are: 1) complementary to HGR in terms of semantics; 2) fully interpretable and transparent; 3) robust over finite samples; 4) configurable to suit specific applications. Our approach also allows us to define fine-grained constraints to permit certain types of dependence and forbid others selectively. By expanding the available options for continuous protected attributes, our approach represents a significant contribution to the area of fair artificial intelligence.

Cite this Paper


BibTeX
@InProceedings{pmlr-v202-giuliani23a, title = {Generalized Disparate Impact for Configurable Fairness Solutions in {ML}}, author = {Giuliani, Luca and Misino, Eleonora and Lombardi, Michele}, booktitle = {Proceedings of the 40th International Conference on Machine Learning}, pages = {11443--11458}, year = {2023}, editor = {Krause, Andreas and Brunskill, Emma and Cho, Kyunghyun and Engelhardt, Barbara and Sabato, Sivan and Scarlett, Jonathan}, volume = {202}, series = {Proceedings of Machine Learning Research}, month = {23--29 Jul}, publisher = {PMLR}, pdf = {https://proceedings.mlr.press/v202/giuliani23a/giuliani23a.pdf}, url = {https://proceedings.mlr.press/v202/giuliani23a.html}, abstract = {We make two contributions in the field of AI fairness over continuous protected attributes. First, we show that the Hirschfeld-Gebelein-Renyi (HGR) indicator (the only one currently available for such a case) is valuable but subject to a few crucial limitations regarding semantics, interpretability, and robustness. Second, we introduce a family of indicators that are: 1) complementary to HGR in terms of semantics; 2) fully interpretable and transparent; 3) robust over finite samples; 4) configurable to suit specific applications. Our approach also allows us to define fine-grained constraints to permit certain types of dependence and forbid others selectively. By expanding the available options for continuous protected attributes, our approach represents a significant contribution to the area of fair artificial intelligence.} }
Endnote
%0 Conference Paper %T Generalized Disparate Impact for Configurable Fairness Solutions in ML %A Luca Giuliani %A Eleonora Misino %A Michele Lombardi %B Proceedings of the 40th International Conference on Machine Learning %C Proceedings of Machine Learning Research %D 2023 %E Andreas Krause %E Emma Brunskill %E Kyunghyun Cho %E Barbara Engelhardt %E Sivan Sabato %E Jonathan Scarlett %F pmlr-v202-giuliani23a %I PMLR %P 11443--11458 %U https://proceedings.mlr.press/v202/giuliani23a.html %V 202 %X We make two contributions in the field of AI fairness over continuous protected attributes. First, we show that the Hirschfeld-Gebelein-Renyi (HGR) indicator (the only one currently available for such a case) is valuable but subject to a few crucial limitations regarding semantics, interpretability, and robustness. Second, we introduce a family of indicators that are: 1) complementary to HGR in terms of semantics; 2) fully interpretable and transparent; 3) robust over finite samples; 4) configurable to suit specific applications. Our approach also allows us to define fine-grained constraints to permit certain types of dependence and forbid others selectively. By expanding the available options for continuous protected attributes, our approach represents a significant contribution to the area of fair artificial intelligence.
APA
Giuliani, L., Misino, E. & Lombardi, M.. (2023). Generalized Disparate Impact for Configurable Fairness Solutions in ML. Proceedings of the 40th International Conference on Machine Learning, in Proceedings of Machine Learning Research 202:11443-11458 Available from https://proceedings.mlr.press/v202/giuliani23a.html.

Related Material