Fairness Interventions: A Study in AI Explainability

TL;DR

This paper explores fairness interventions in AI, emphasizing the importance of explainability and transparency in corrective methods, and introduces FairDream, a tool that reveals biases and trade-offs in fairness criteria.

Contribution

It provides a philosophical and experimental analysis of fairness corrections, introduces the FairDream package, and clarifies the relationship between fairness criteria with a focus on transparency.

Findings

FairDream tends towards Equalized Odds despite user intent for Demographic Parity.

Transparency in fairness interventions reveals inherent biases and trade-offs.

The study links fairness criteria with epistemological insights, including Simpson's paradox.

Abstract

This paper presents a philosophical and experimental study of fairness interventions in AI classification, centered on the explainability of corrective methods. We argue that ensuring fairness requires not only satisfying a target criterion, but also explaining which variables constrain its realization. When corrections are used to mitigate advantage transparently, they must remain sensitive to the distribution of true labels. To illustrate this approach, we built FairDream, a fairness package whose mechanism is made transparent for lay users, increasing the model's weights of errors on disadvantaged groups. While a user may intend to achieve Demographic Parity by the correction method, experiments show that FairDream tends towards Equalized Odds, revealing a conservative bias inherent to the data environment. We clarify the relationship between these fairness criteria, analyze FairDream's reweighting process, and compare its trade-offs with closely related GridSearch models. Finally, we justify the normative preference for Equalized Odds via an epistemological interpretation of the results, using their proximity with Simpson's paradox. The paper thus unites normative, epistemological, and empirical explanations of fairness interventions, to ensure transparency for the users.