Active Fairness Auditing
This work addresses the regulatory challenge of scalable fairness auditing for companies using ML, providing foundational theoretical insights for AI governance.
The paper tackles the problem of efficiently auditing machine learning models for fairness, proposing query-based algorithms to estimate demographic parity with optimal deterministic and practical randomized methods, achieving comparable guarantees and exploring optimal query complexity.
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 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.