Parity-based Cumulative Fairness-aware Boosting

TL;DR

This paper introduces AdaFair, a boosting ensemble method that improves fairness in AI systems by adjusting data distribution during training and post-training to address class imbalance and discrimination.

Contribution

AdaFair is a novel fairness-aware boosting approach that considers cumulative fairness and class imbalance, effectively mitigating discrimination while maintaining accuracy.

Findings

Achieves parity in statistical parity, equal opportunity, and disparate mistreatment.

Maintains good predictive performance across classes.

Effectively mitigates discrimination in imbalanced datasets.

Abstract

Data-driven AI systems can lead to discrimination on the basis of protected attributes like gender or race. One reason for this behavior is the encoded societal biases in the training data (e.g., females are underrepresented), which is aggravated in the presence of unbalanced class distributions (e.g., "granted" is the minority class). State-of-the-art fairness-aware machine learning approaches focus on preserving the \emph{overall} classification accuracy while improving fairness. In the presence of class-imbalance, such methods may further aggravate the problem of discrimination by denying an already underrepresented group (e.g., \textit{females}) the fundamental rights of equal social privileges (e.g., equal credit opportunity). To this end, we propose AdaFair, a fairness-aware boosting ensemble that changes the data distribution at each round, taking into account not only the class errors but also the fairness-related performance of the model defined cumulatively based on the partial ensemble. Except for the in-training boosting of the group discriminated over each round, AdaFair directly tackles imbalance during the post-training phase by optimizing the number of ensemble learners for balanced error performance (BER). AdaFair can facilitate different parity-based fairness notions and mitigate effectively discriminatory outcomes. Our experiments show that our approach can achieve parity in terms of statistical parity, equal opportunity, and disparate mistreatment while maintaining good predictive performance for all classes.