[论文解读] Towards A Holistic View of Bias in Machine Learning: Bridging Algorithmic Fairness and Imbalanced Learning

Damien Dablain, Bartosz Krawczyk+1 more|arXiv (Cornell University)|Jul 13, 2022

Artificial Intelligence in Law被引用 9

一句话总结

本文提出了一种新颖的预处理方法 Fair Oversampling，通过生成合成样本同时保持公平性，联合解决机器学习中的类别不平衡与受保护群体不平衡问题。该方法在经由新提出的 Fair Utility 评估指标验证后，同时提升了模型的准确率与公平性，并在与公平感知算法结合时表现出稳健性。

ABSTRACT

Machine learning (ML) is playing an increasingly important role in rendering decisions that affect a broad range of groups in society. ML models inform decisions in criminal justice, the extension of credit in banking, and the hiring practices of corporations. This posits the requirement of model fairness, which holds that automated decisions should be equitable with respect to protected features (e.g., gender, race, or age) that are often under-represented in the data. We postulate that this problem of under-representation has a corollary to the problem of imbalanced data learning. This class imbalance is often reflected in both classes and protected features. For example, one class (those receiving credit) may be over-represented with respect to another class (those not receiving credit) and a particular group (females) may be under-represented with respect to another group (males). A key element in achieving algorithmic fairness with respect to protected groups is the simultaneous reduction of class and protected group imbalance in the underlying training data, which facilitates increases in both model accuracy and fairness. We discuss the importance of bridging imbalanced learning and group fairness by showing how key concepts in these fields overlap and complement each other; and propose a novel oversampling algorithm, Fair Oversampling, that addresses both skewed class distributions and protected features. Our method: (i) can be used as an efficient pre-processing algorithm for standard ML algorithms to jointly address imbalance and group equity; and (ii) can be combined with fairness-aware learning algorithms to improve their robustness to varying levels of class imbalance. Additionally, we take a step toward bridging the gap between fairness and imbalanced learning with a new metric, Fair Utility, that combines balanced accuracy with fairness.

研究动机与目标

• 解决机器学习数据集中类别不平衡与受保护群体代表性不足的双重挑战。
• 通过识别数据不平衡在算法公平性与不平衡学习中的共同根源，弥合两者之间的鸿沟。
• 开发一种预处理方法，同时减轻两类不平衡，以提升公平性与准确率。
• 提出一种新的评估指标 Fair Utility，结合平衡准确率与群体公平性度量。
• 通过集成所提出的过采样技术，增强公平感知学习算法在不同类别不平衡水平下的鲁棒性。

提出的方法

• 设计 Fair Oversampling，一种新颖的过采样算法，通过生成合成样本以平衡类别与受保护群体的分布。
• 在生成合成样本的过程中引入公平性约束，通过考虑受保护属性（如性别、种族）来实现。
• 采用基于距离的方法，在少数类样本附近生成新样本，确保多样性和代表性。
• 将 Fair Oversampling 作为预处理步骤与标准机器学习算法结合，以提升公平性与准确率。
• 将 Fair Oversampling 与公平感知学习算法集成，以增强其在不同类别不平衡水平下的鲁棒性。
• 提出 Fair Utility，一种复合指标，结合平衡准确率与群体公平性（如平等机会差异），实现模型的全面评估。

实验结果

研究问题

• RQ1 如何在一个统一的预处理框架中联合解决类别不平衡与受保护群体不平衡问题？
• RQ2 减轻数据不平衡在多大程度上能同时提升分类任务中的模型准确率与公平性？
• RQ3 一种单一的过采样方法是否能有效提升公平性而不损害模型性能？
• RQ4 Fair Oversampling 如何在不同类别不平衡水平下提升公平感知学习算法的鲁棒性？
• RQ5 像 Fair Utility 这样的统一指标能否有效捕捉不平衡、有偏数据集中准确率与公平性之间的权衡？

主要发现

• Fair Oversampling 在多个基准数据集上显著提升了平衡准确率与公平性度量。
• 所提出的 Fair Utility 指标有效捕捉了准确率与公平性之间的权衡，实现了更全面的模型评估。
• 将 Fair Oversampling 与公平感知学习算法结合，显著增强了其对类别不平衡的鲁棒性，尤其在资源有限的受保护群体中表现突出。
• 与现有预处理和事中公平性技术相比，该方法在公平性与准确率方面达到了最先进性能。
• 在 GitHub 上的开源实现确保了可复现性，并推动了公平性与不平衡学习领域的进一步研究。
• 实证结果表明，在预处理阶段减轻数据不平衡，可显著提升公平性与模型泛化能力。