Happiness as a Measure of Fairness
By: Georg Pichler, Marco Romanelli, Pablo Piantanida
Potential Business Impact:
Makes computer decisions fairer and happier for everyone.
In this paper, we propose a novel fairness framework grounded in the concept of happiness, a measure of the utility each group gains fromdecisionoutcomes. Bycapturingfairness through this intuitive lens, we not only offer a more human-centered approach, but also one that is mathematically rigorous: In order to compute the optimal, fair post-processing strategy, only a linear program needs to be solved. This makes our method both efficient and scalable with existing optimization tools. Furthermore, it unifies and extends several well-known fairness definitions, and our empirical results highlight its practical strengths across diverse scenarios.
Similar Papers
A Unifying Human-Centered AI Fairness Framework
Machine Learning (CS)
Helps AI treat everyone fairly, no matter what.
Toward Unifying Group Fairness Evaluation from a Sparsity Perspective
Machine Learning (CS)
Makes computer decisions fairer for everyone.
Learning Time-Varying Convexifications of Multiple Fairness Measures
Machine Learning (CS)
Teaches computers to be fair in different ways.