Improving Fairness and Privacy in Selection Problems
This work is significant for organizations and institutions using supervised learning for high-stakes selection processes (e.g., hiring, admissions) who need to mitigate bias and protect individual privacy.
This paper addresses the challenge of ensuring fairness and privacy in selection problems where supervised learning models are used to pick a limited number of applicants. The authors propose using a differentially private exponential mechanism as a post-processing step, demonstrating that it can achieve perfect fairness (equal opportunity) and improve privacy, with only a slight decrease in accuracy on real-world datasets.
Supervised learning models have been increasingly used for making decisions about individuals in applications such as hiring, lending, and college admission. These models may inherit pre-existing biases from training datasets and discriminate against protected attributes (e.g., race or gender). In addition to unfairness, privacy concerns also arise when the use of models reveals sensitive personal information. Among various privacy notions, differential privacy has become popular in recent years. In this work, we study the possibility of using a differentially private exponential mechanism as a post-processing step to improve both fairness and privacy of supervised learning models. Unlike many existing works, we consider a scenario where a supervised model is used to select a limited number of applicants as the number of available positions is limited. This assumption is well-suited for various scenarios, such as job application and college admission. We use ``equal opportunity'' as the fairness notion and show that the exponential mechanisms can make the decision-making process perfectly fair. Moreover, the experiments on real-world datasets show that the exponential mechanism can improve both privacy and fairness, with a slight decrease in accuracy compared to the model without post-processing.