arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 1905.00147cs.LGcs.AIstat.ML
收藏

公平分类与社会福利

Fair Classification and Social Welfare

Lily Hu, Yiling Chen

摘要:

既然机器学习算法处于许多资源分配管道的中心,计算机科学家已经不知不觉地被塑造成部分社会规划者。鉴于这种情况,重要的问题随之而来。计算机科学家定义的公平与社会福利概念之间有什么关系?在本文中,我们提出了一个基于福利的分类和公平制度的分析。我们将损失最小化程序转化为一个社会福利最大化问题,其中包含一组个人和群体的隐含福利权重--这些权重可以从分配正义的角度进行分析。在相反的方向上,我们问一个给定的数据集和假设类的可能标签的空间是什么。我们提供了一个算法,回答这个问题,相对于线性超平面在$\mathbb{R}^d$,运行在$O(n^dd)$。我们对公平标准和福利之间关系的主要发现集中在公平约束的经验风险最小化方案的敏感性分析上。我们描述了$Δε$扰动对公平参数$ε$的范围,这些参数对个人以及扩展到群体的效用产生更好、更差和中性的结果。我们表明,应用更严格的公平标准,被编纂为平等的约束,可以恶化两组的福利结果。更一般地说,总是倾向于“更公平”的分类不遵守帕累托原则-社会选择理论和福利经济学的基本公理。机器学习领域最近的工作围绕着这些公平的概念展开,这些概念对于确保算法系统不会对弱势社会群体产生不同的负面影响至关重要。通过表明这些限制往往不能转化为改善这些群体的结果,我们对它们作为确保正义的手段的有效性表示怀疑。

英文摘要:

Now that machine learning algorithms lie at the center of many resource allocation pipelines, computer scientists have been unwittingly cast as partial social planners. Given this state of affairs, important questions follow. What is the relationship between fairness as defined by computer scientists and notions of social welfare? In this paper, we present a welfare-based analysis of classification and fairness regimes. We translate a loss minimization program into a social welfare maximization problem with a set of implied welfare weights on individuals and groups--weights that can be analyzed from a distribution justice lens. In the converse direction, we ask what the space of possible labelings is for a given dataset and hypothesis class. We provide an algorithm that answers this question with respect to linear hyperplanes in $\mathbb{R}^d$ that runs in $O(n^dd)$. Our main findings on the relationship between fairness criteria and welfare center on sensitivity analyses of fairness-constrained empirical risk minimization programs. We characterize the ranges of $Δε$ perturbations to a fairness parameter $ε$ that yield better, worse, and neutral outcomes in utility for individuals and by extension, groups. We show that applying more strict fairness criteria that are codified as parity constraints, can worsen welfare outcomes for both groups. More generally, always preferring "more fair" classifiers does not abide by the Pareto Principle---a fundamental axiom of social choice theory and welfare economics. Recent work in machine learning has rallied around these notions of fairness as critical to ensuring that algorithmic systems do not have disparate negative impact on disadvantaged social groups. By showing that these constraints often fail to translate into improved outcomes for these groups, we cast doubt on their effectiveness as a means to ensure justice.

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。

↑