通过特征遮蔽和排列实现公平的特征重要性评分
Fair Feature Importance Scores via Feature Occlusion and Permutation
AI总结：
本文提出两种模型无关方法，通过特征遮蔽和排列评估特征对公平性的贡献，为公平性评估提供新的可解释工具。
摘要：
随着机器学习模型日益影响社会，其不透明性对信任和问责提出了挑战，尤其是在公平性背景下。理解单个特征如何影响模型结果对于构建可解释和公平的模型至关重要。虽然用于准确性的特征重要性指标已得到充分发展，但评估特征对公平性的贡献的方法仍显不足。我们提出了两种模型无关的方法来测量公平的特征重要性。首先，我们提出比较模型公平性在排列特征值前后的情况。这种基于干预的方法将特征与模型预测分离，以衡量其对训练的贡献。其次，我们评估使用和不使用给定特征训练的模型公平性。这种遮蔽评分通过minipatch学习实现了显著的计算简化。我们的实证结果反映了我们提出指标在多种预测任务中的简单性和有效性。两种方法都提供了简单、可扩展且可解释的解决方案，以量化特征对公平性的影响，为负责任的机器学习发展提供了新工具。
英文摘要：
As machine learning models increasingly impact society, their opaque nature poses challenges to trust and accountability, particularly in fairness contexts. Understanding how individual features influence model outcomes is crucial for building interpretable and equitable models. While feature importance metrics for accuracy are well-established, methods for assessing feature contributions to fairness remain underexplored. We propose two model-agnostic approaches to measure fair feature importance. First, we propose to compare model fairness before and after permuting feature values. This simple intervention-based approach decouples a feature and model predictions to measure its contribution to training. Second, we evaluate the fairness of models trained with and without a given feature. This occlusion-based score enjoys dramatic computational simplification via minipatch learning. Our empirical results reflect the simplicity and effectiveness of our proposed metrics for multiple predictive tasks. Both methods offer simple, scalable, and interpretable solutions to quantify the influence of features on fairness, providing new tools for responsible machine learning development.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
