Skip to yearly menu bar Skip to main content


Active fairness auditing

Tom Yan · Chicheng Zhang

Hall E #1222

Keywords: [ SA: Everything Else ] [ T: Active Learning and Interactive Learning ] [ T: Social Aspects ]

award Outstanding Paper Runner Up
[ ]
[ Slides [ Poster [ Paper PDF


The fast spreading adoption of machine learning (ML) by companies across industries poses significant regulatory challenges. One such challenge is scalability: how can regulatory bodies efficiently \emph{audit} these ML models, ensuring that they are fair? In this paper, we initiate the study of query-based auditing algorithms that can estimate the demographic parity of ML models in a query-efficient manner. We propose an optimal deterministic algorithm, as well as a practical randomized, oracle-efficient algorithm with comparable guarantees. Furthermore, we make inroads into understanding the optimal query complexity of randomized active fairness estimation algorithms. Our first exploration of active fairness estimation aims to put AI governance on firmer theoretical foundations.

Chat is not available.