Recent research has shown that seemingly fair machine learning models, when used to inform decisions that have an impact on peoples' lives or well-being (e.g., applications involving education, employment, and lending), can inadvertently increase social inequality in the long term. This is because prior fairness-aware algorithms only consider static fairness constraints, such as equal opportunity or demographic parity. However, enforcing constraints of this type may result in models that have negative long-term impact on disadvantaged individuals and communities. We introduce ELF (Enforcing Long-term Fairness), the first classification algorithm that provides high-confidence fairness guarantees in terms of long-term, or delayed, impact. We prove that the probability that ELF returns an unfair solution is less than a user-specified tolerance and that (under mild assumptions), given sufficient training data, ELF is able to find and return a fair solution if one exists. We show experimentally that our algorithm can successfully mitigate long-term unfairness.
翻译:最近的研究显示,当用来为影响人民生活或福祉的决定(例如涉及教育、就业和贷款的应用)提供参考时,看似公平的机器学习模式,从长远来看,可能无意中增加社会不平等,这是因为事先的公平认知算法只考虑静态的公平制约,例如平等机会或人口均等;然而,执行这种类型的制约可能导致对处境不利的个人和社区产生长期消极影响的模式。我们引入了ELF(实现长期公平),这是第一个在长期或延迟影响方面提供高度信任公平保障的分类算法。我们证明,ELF返回不公平解决办法的可能性比用户指定的容忍程度要小,而且(在温和的假设下),如果有足够的培训数据,ELF能够找到公平的解决办法,如果存在的话,则可以返回公平的解决办法。我们实验性地表明,我们的算法能够成功地减轻长期的不公平。