TowerDebias: A Novel Unfairness Removal Method Based on the Tower Property

TL;DR

TowerDebias (tDB) is a post-processing technique that reduces bias from sensitive attributes in black-box model predictions using the Tower Property, enhancing fairness without retraining the original model.

Contribution

Introduces tDB, a novel post-processing method leveraging the Tower Property to mitigate unfairness in black-box models without needing internal model details.

Findings

Effective in reducing bias in both regression and classification tasks

Applicable to diverse real-world datasets

Does not require retraining or internal model access

Abstract

Decision-making processes have increasingly come to rely on sophisticated machine learning tools, raising critical concerns about the fairness of their predictions with respect to sensitive groups. The widespread adoption of commercial "black-box" models necessitates careful consideration of their legal and ethical implications for consumers. When users interact with such black-box models, a key challenge arises: how can the influence of sensitive attributes, such as race or gender, be mitigated or removed from its predictions? We propose towerDebias (tDB), a novel post-processing method designed to reduce the influence of sensitive attributes in predictions made by black-box models. Our tDB approach leverages the Tower Property from probability theory to improve prediction fairness without requiring retraining of the original model. This method is highly versatile, as it requires no prior knowledge of the original algorithm's internal structure and is adaptable to a diverse range of applications. We present a formal fairness improvement theorem for tDB and showcase its effectiveness in both regression and classification tasks using multiple real-world datasets.