Fairness in machine learning has attained significant focus due to the widespread application in high-stake decision-making tasks. Unregulated machine learning classifiers can exhibit bias towards certain demographic groups in data, thus the quantification and mitigation of classifier bias is a central concern in fairness in machine learning. In this paper, we aim to quantify the influence of different features in a dataset on the bias of a classifier. To do this, we introduce the Fairness Influence Function (FIF). This function breaks down bias into its components among individual features and the intersection of multiple features. The key idea is to represent existing group fairness metrics as the difference of the scaled conditional variances in the classifier's prediction and apply a decomposition of variance according to global sensitivity analysis. To estimate FIFs, we instantiate an algorithm FairXplainer that applies variance decomposition of classifier's prediction following local regression. Experiments demonstrate that FairXplainer captures FIFs of individual feature and intersectional features, provides a better approximation of bias based on FIFs, demonstrates higher correlation of FIFs with fairness interventions, and detects changes in bias due to fairness affirmative/punitive actions in the classifier.

翻译：机器学习中的公平性因在高风险决策任务中的广泛应用而备受关注。未受约束的机器学习分类器可能对数据中的某些人口统计群体表现出偏见，因此分类器偏见的量化与缓解成为机器学习公平性研究的核心问题。本文旨在量化数据集中不同特征对分类器偏见的影响程度。为此，我们提出了公平性影响函数（FIF）。该函数将偏见分解为单个特征及多特征交互作用对偏见的贡献。其核心思想是将现有多组公平性度量指标表示为分类器预测中条件方差缩放后的差值，并通过全局敏感性分析实现方差分解。为估计FIF，我们实例化了一个名为FairXplainer的算法，该算法通过局部回归对分类器预测进行方差分解。实验表明，FairXplainer能捕获单个特征与交叉特征的FIF，基于FIF实现更优的偏见近似，展示出FIF与公平性干预措施间更高的相关性，并能检测到分类器中因公平性肯定/惩罚措施导致的偏见变化。