Designing machine learning algorithms that are accurate yet fair, not discriminating based on any sensitive attribute, is of paramount importance for society to accept AI for critical applications. In this article, we propose a novel fair representation learning method termed the R\'enyi Fair Information Bottleneck Method (RFIB) which incorporates constraints for utility, fairness, and compactness (compression) of representation, and apply it to image and tabular data classification. A key attribute of our approach is that we consider - in contrast to most prior work - both demographic parity and equalized odds as fairness constraints, allowing for a more nuanced satisfaction of both criteria. Leveraging a variational approach, we show that our objectives yield a loss function involving classical Information Bottleneck (IB) measures and establish an upper bound in terms of two R\'enyi measures of order $\alpha$ on the mutual information IB term measuring compactness between the input and its encoded embedding. We study the influence of the $\alpha$ parameter as well as two other tunable IB parameters on achieving utility/fairness trade-off goals, and show that the $\alpha$ parameter gives an additional degree of freedom that can be used to control the compactness of the representation. Experimenting on three different image datasets (EyePACS, CelebA, and FairFace) and two tabular datasets (Adult and COMPAS), using both binary and categorical sensitive attributes, we show that on various utility, fairness, and compound utility/fairness metrics RFIB outperforms current state-of-the-art approaches.

翻译：设计既准确又公平、不基于任何敏感属性进行歧视的机器学习算法，对于社会接受人工智能应用于关键领域至关重要。本文提出一种新颖的公平表征学习方法——Rényi公平信息瓶颈方法（RFIB），该方法整合了表征的效用、公平性和紧凑性（压缩）约束，并将其应用于图像与表格数据分类。与大多数现有研究不同，本方法的关键特性在于同时将人口统计均等和均等几率作为公平性约束，从而更精细地满足这两个标准。借助变分方法，我们证明了优化目标可导出涉及经典信息瓶颈（IB）度量的损失函数，并建立了基于两个α阶Rényi度量的上界以约束表征输入与编码嵌入间紧凑性的互信息IB项。我们研究了α参数及其他两个可调IB参数对实现效用/公平性权衡目标的影响，结果表明α参数可作为额外自由度用于控制表征的紧凑性。在三个不同图像数据集（EyePACS、CelebA、FairFace）和两个表格数据集（Adult、COMPAS）上，采用二值化与分类敏感属性进行的实验表明，在多种效用、公平性以及效用/公平性复合指标上，RFIB均优于现有最先进方法。