Learning Time-Varying Convexifications of Multiple Fairness Measures

Artificial intelligence has gained widespread popularity and adoption across diverse industries due to its ability of automatic decision-making processes. In numerous contexts where artificial intelligence permeates various aspects of our lives, from business operations to societal dynamics and policy formulation, ensuring fairness is of greatest importance to meeting environmental, social, and governance standards. While for nearly any problem in the field of artificial intelligence, there can exist multiple measures of individual fairness as well as multiple measures of subgroup fairness. Often, Subgroup fairness involves multiple protected attributes (e.g., race, sex), creating numerous combinations of subgroups and corresponding subgroup fairness measures, all of which deserve consideration. Hence, it becomes essential to take into account the trade-offs among optimising for multiple fairness measures.