Bayesian Modeling of Intersectional Fairness: The Variance of Bias
This work addresses the problem of intersectional fairness measurement for AI practitioners and policymakers, offering a data-efficient method to handle statistical challenges in multi-dimensional settings, though it is incremental as it applies Bayesian methods to existing fairness metrics.
The paper tackles the challenge of measuring fairness in AI systems with multi-dimensional protected attributes, such as race and gender, by proposing a Bayesian probabilistic modeling approach that reliably estimates fairness metrics despite data sparsity, demonstrating its utility on census and COMPAS datasets.
Intersectionality is a framework that analyzes how interlocking systems of power and oppression affect individuals along overlapping dimensions including race, gender, sexual orientation, class, and disability. Intersectionality theory therefore implies it is important that fairness in artificial intelligence systems be protected with regard to multi-dimensional protected attributes. However, the measurement of fairness becomes statistically challenging in the multi-dimensional setting due to data sparsity, which increases rapidly in the number of dimensions, and in the values per dimension. We present a Bayesian probabilistic modeling approach for the reliable, data-efficient estimation of fairness with multi-dimensional protected attributes, which we apply to two existing intersectional fairness metrics. Experimental results on census data and the COMPAS criminal justice recidivism dataset demonstrate the utility of our methodology, and show that Bayesian methods are valuable for the modeling and measurement of fairness in an intersectional context.