Fairness Evaluation of Neural Networks Through Computational Profile Likelihood
Sign Up to like & getrecommendations! Published in 2025 at "Computational Intelligence"
DOI: 10.1111/coin.70124
Abstract: Despite high predictive performance, machine learning models can be unfair towards specific demographic subgroups characterized by sensitive attributes such as gender or race. This paper presents a novel approach using Computational Profile Likelihood (CPL) to… read more here.
Keywords: sensitive attribute; computational profile; profile likelihood; sensitive attributes ... See more keywords