Bayesian Modeling of Intersectional Fairness: The Variance of Bias
By James R. Foulds, Rashidul Islam, Kamrun Keya, Shimei Pan. 2018
47 citations recorded by the source corpus.
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.
Subfields: Artificial Intelligence, Safety Research
How researchers see this paper
The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.
In Artificial Intelligence
- Vikram V. Ramaswamy
- Olga Russakovsky
- Angelina Wang
- Shira Mitchell
- Solon Barocas
- Eric Potash
- Kristen Grauman
- Yuta Nakashima
In Safety Research
- Vikram V. Ramaswamy
- Olga Russakovsky
- Shira Mitchell
- Eric Potash
- Solon Barocas
- Angelina Wang
- Adrian Weller
Citations in the corpus
- Prediction-Based Decisions and Fairness: A Catalogue of Choices, Assumptions, and Definitions (2018, methodology): “apply Bayesian methods to overcome data sparsity in checking statistical parities for small groups [50].”
- Towards Intersectionality in Machine Learning: Including More Identities, Handling Underrepresentation, and Performing Evaluation (2022, background): “For smaller groups where one might argue evaluations would be noisy [39], error bars could convey uncertainty, and evaluations on the larger group could also be included.”