arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2305.06994cs.LGcs.CY
收藏

一种在群体公平设置中检测敏感特征的统计方法

A statistical approach to detect sensitive features in a group fairness setting

School of Applied Sciences (FCA)(应用科学学院(FCA));University of Campinas (UNICAMP)(坎皮纳斯大学(UNICAMP));Université de Lorraine(洛林大学);CNRS(法国国家科学研究中心);LORIA(洛林计算机科学及其应用实验室)

Guilherme Dean Pelegrina, Miguel Couceiro, Leonardo Tomazeli Duarte

AI总结:

本文提出一种基于希尔伯特-施密特独立性准则的预处理方法,自动识别群体公平设置中的敏感特征,无需训练模型,实证表明文献中的敏感特征未必导致不公平结果。

摘要:

机器学习模型在具有高社会影响的决策支持系统中的使用,引发了对不同人群不公平(差异)结果的担忧。在评估此类不公平决策时,通常依赖于由一组被视为敏感的特征所确定的预定义群体。然而,这种方法具有主观性,并且不能保证这些特征是唯一需要被视为敏感的特征,也不能保证它们会导致不公平(差异)的结果。在本文中,我们提出一个预处理步骤,以解决自动识别敏感特征的任务,该步骤不需要训练好的模型来验证不公平结果。我们的提议基于希尔伯特-施密特独立性准则,该准则衡量变量分布的统计依赖性。我们假设,如果标签向量与候选特征之间的依赖性对于敏感特征而言很高,则该特征提供的信息将导致群体之间的差异性能指标。我们的实证结果证实了我们的假设,并表明文献中被视为敏感的若干特征并不必然导致差异(不公平)的结果。

英文摘要:

The use of machine learning models in decision support systems with high societal impact raised concerns about unfair (disparate) results for different groups of people. When evaluating such unfair decisions, one generally relies on predefined groups that are determined by a set of features that are considered sensitive. However, such an approach is subjective and does not guarantee that these features are the only ones to be considered as sensitive nor that they entail unfair (disparate) outcomes. In this paper, we propose a preprocessing step to address the task of automatically recognizing sensitive features that does not require a trained model to verify unfair results. Our proposal is based on the Hilber-Schmidt independence criterion, which measures the statistical dependence of variable distributions. We hypothesize that if the dependence between the label vector and a candidate is high for a sensitive feature, then the information provided by this feature will entail disparate performance measures between groups. Our empirical results attest our hypothesis and show that several features considered as sensitive in the literature do not necessarily entail disparate (unfair) results.

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。

↑