Happiness as a Measure of Fairness
It addresses fairness in AI for decision-making scenarios, offering a human-centered and mathematically rigorous approach, but appears incremental as it builds on known definitions.
The paper tackles the problem of fairness in decision-making by proposing a novel framework based on happiness, a measure of utility for each group, and shows that it unifies and extends existing fairness definitions with efficient computation via a linear program.
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.