2022/06/23 by Siamak Ghodsi, Ghodsi, Siamak, Harith Alani +3 · 1 citation
Decision Sciences · Social Sciences · #Artificial Intelligence (cs.AI) #FOS: Computer and information sciences #Health disparities and outcomes #Insurance, Mortality, Demography, Risk Management #Machine Learning (cs.LG) #demographic modeling and climate adaptation
paper · pdf · doi:10.48550/arxiv.2206.11436
openalex publication_date 2022/06/23 · openalex created_date 2022/06/26 · openalex updated_date 2026/07/28
With the ever growing involvement of data-driven AI-based decision making technologies in our daily social lives, the fairness of these systems is becoming a crucial phenomenon. However, an important and often challenging aspect in utilizing such systems is to distinguish validity for the range of their application especially under distribution shifts, i.e., when a model is deployed on data with different distribution than the training set. In this paper, we present a case study on the newly released American Census datasets, a reconstruction of the popular Adult dataset, to illustrate the importance of context for fairness and show how remarkably can spatial distribution shifts affect predictive- and fairness-related performance of a model. The problem persists for fairness-aware learning models with the effects of context-specific fairness interventions differing across the states and different population groups. Our study suggests that robustness to distribution shifts is necessary before deploying a model to another context.