Can We Trust Fair-AI?
Salvatore Ruggieri, Jose M. Alvarez, Andrea Pugnana, Laura State, Franco Turini
Abstract
There is a fast-growing literature in addressing the fairness of AI models (fair-AI), with a continuous stream of new conceptual frameworks, methods, and tools. How much can we trust them? How much do they actually impact society? We take a critical focus on fair-AI and survey issues, simplifications, and mistakes that researchers and practitioners often underestimate, which in turn can undermine the trust on fair-AI and limit its contribution to society. In particular, we discuss the hyper-focus on fairness metrics and on optimizing their average performances. We instantiate this observation by discussing the Yule's effect of fair-AI tools: being fair on average does not imply being fair in contexts that matter. We conclude that the use of fair-AI methods should be complemented with the design, development, and verification practices that are commonly summarized under the umbrella of trustworthy AI.
BibTeX
@article{Ruggieri_Alvarez_Pugnana_State_Turini_2024, title={Can We Trust Fair-AI?}, volume={37}, url={https://ojs.aaai.org/index.php/AAAI/article/view/26798}, DOI={10.1609/aaai.v37i13.26798}, abstractNote={There is a fast-growing literature in addressing the fairness of AI models (fair-AI), with a continuous stream of new conceptual frameworks, methods, and tools. How much can we trust them? How much do they actually impact society? We take a critical focus on fair-AI and survey issues, simplifications, and mistakes that researchers and practitioners often underestimate, which in turn can undermine the trust on fair-AI and limit its contribution to society. In particular, we discuss the hyper-focus on fairness metrics and on optimizing their average performances. We instantiate this observation by discussing the Yule’s effect of fair-AI tools: being fair on average does not imply being fair in contexts that matter. We conclude that the use of fair-AI methods should be complemented with the design, development, and verification practices that are commonly summarized under the umbrella of trustworthy AI.}, number={13}, journal={Proceedings of the AAAI Conference on Artificial Intelligence}, author={Ruggieri, Salvatore and Alvarez, Jose M. and Pugnana, Andrea and State, Laura and Turini, Franco}, year={2024}, month={Jul.}, pages={15421-15430} }