Realistically -- and equitably -- modeling the dynamics of group-level disparities in machine learning remains an open problem. In particular, we desire models that do not suppose inherent differences between artificial groups of people -- but rather endogenize disparities by appeal to unequal initial conditions of insular subpopulations. In this paper, agents each have a real-valued feature $X$ (e.g., credit score) informed by a "true" binary label $Y$ representing qualification (e.g., for a loan). Each agent alternately (1) receives a binary classification label $\hat{Y}$ (e.g., loan approval) from a Bayes-optimal machine learning classifier observing $X$ and (2) may update their qualification $Y$ by imitating successful strategies (e.g., seek a raise) within an isolated group $G$ of agents to which they belong. We consider the disparity of qualification rates $\Pr(Y=1)$ between different groups and how this disparity changes subject to a sequence of Bayes-optimal classifiers repeatedly retrained on the global population. We model the evolving qualification rates of each subpopulation (group) using the replicator equation, which derives from a class of imitation processes. We show that differences in qualification rates between subpopulations can persist indefinitely for a set of non-trivial equilibrium states due to uniformed classifier deployments, even when groups are identical in all aspects except initial qualification densities. We next simulate the effects of commonly proposed fairness interventions on this dynamical system along with a new feedback control mechanism capable of permanently eliminating group-level qualification rate disparities. We conclude by discussing the limitations of our model and findings and by outlining potential future work.
翻译:现实地 -- 和公平地 -- 模拟机器学习中群体一级差异的动态,仍然是一个尚未解决的问题。特别是,我们希望一些模型不假定人为人群之间的内在差异,而是将差异内在化,向不均匀的岛屿亚群群中的初始条件发出呼吁。在本文中,每个代理商都有由“真”二进制标签(如信用评分)提供的以“真正”二进制美元代表资格(如贷款)的Y美元为根据的真实价值X美元(如信用评分)。每个代理商(1)从一个Bayes-最优机器学习分类师中获得一个二进制的分类标签(如贷款审批),这些分类标签并不假定人为人为的人群之间的内在差异。我们用一个不均匀的定型系统来更新其资格。我们根据Bayes-最优分级化师的顺序反复对全球人口进行重新培训。我们用一个不均匀的定型的定型系统,从每个常态的定型结构中,从每个定型的定型的定型的定型的定型的定型比率,从每个定型的定型的定型的定型的定型的定型的定型的定型的定型的定型的定型的定型的定型的定型的定型的定型的定型的定型的定型的定型的定型的定型的定型的定型流程,从的定型的定型的定型的定型的定型的定型的定型的定型的定型的定型的定型的定型的定型的定型的定型的定型的定型的定型的定型的定型流程,在的定型的定型的定型的定型的定型后的定型的定型的定型的定型的定型的定型的定型的定型的定型的定型的定型的定型的定型的定型的定型的定型的定型的定型的定型的定型的定型的定型的定型的定型的定型的定型的定型的定型的定型的定型的定型的定型的定型的定型的定型的定型的定型的定型的定型的定型