CRII: SHF: Testing Fairness in Human Decisions with Algorithmic Bias

CRII：SHF：用算法偏差测试人类决策的公平性

• 批准号: 2245796
• 负责人: Zhe Yu
• 金额: $ 17.5万
• 依托单位: Rochester Institute of Tech
• 依托单位国家: 美国
• 项目类别: Standard Grant
• 财政年份: 2023
• 资助国家: 美国
• 起止时间: 2023-06-01 至 2025-05-31
• 项目状态: 未结题
• 来源: https://www.nsf.gov/awardsearch/showAward?AWD_ID=2245796&HistoricalAwards=false
• 关键词: CRII; SHF; Testing; Fairness; Human

Unfairness in human decisions has been a long-standing issue in our society that constantly threatens the equality rights of historically underrepresented groups. This issue has been exacerbated in decision making processes where a machine learning software learns from potentially unfair human decisions and makes potentially unfair predictions to guide future human decisions. One such example is the talent hiring process where a human resource person screens a list of candidate resumes ranked by a machine learning software to decide who deserves an interview. Human decision fairness is especially important in this scenario since (1) the machine learning software will inherit the bias when trained on unfair human decisions; (2) even with unbiased machine learning software, the final decisions can still be biased as long as the human resource person is biased. This project will approach this historically challenging issue from a different direction. It learns to model the human decisions with a machine learning software and utilizes the algorithmic bias of that software to detect bias in the human decisions. This work could potentially advance the equity process in many decision making activities such as talent hiring, credit card approval, and school admission. In contrast to most of the existing research focusing on improving algorithmic fairness, this work aims to isolate the algorithmic bias inherited from the training data (with human decisions as dependent variables) as an indicator for human decision unfairness. To do this, the project will use a novel technique to test fairness in human decisions. Specifically, machine learning models are trained on the human decisions under test with re-balanced class distribution in each demographic group, then tests the learned model with a regression test suite of comparative judgements. If the model fails the regression test, the human decisions it was trained on will be considered as unfair. While it is difficult to directly test whether a human has bias, it is easier to test whether a machine learning model makes biased predictions using comparative judgements.This award reflects NSF's statutory mission and has been deemed worthy of support through evaluation using the Foundation's intellectual merit and broader impacts review criteria.

人类决策中的不公平一直是我们社会中的一个长期问题，不断威胁着历史上代表性不足的群体的平等权利。在决策过程中，机器学习软件从潜在的不公平的人类决策中学习，并做出潜在的不公平预测来指导未来的人类决策，这一问题变得更加严重。一个这样的例子是人才招聘过程，人力资源人员筛选由机器学习软件排名的候选人简历列表，以决定谁值得面试。在这种情况下，人类决策的公平性尤为重要，因为（1）机器学习软件在接受不公平的人类决策训练时会继承偏见;（2）即使使用无偏见的机器学习软件，只要人力资源人员有偏见，最终决策仍然会有偏见。这个项目将从不同的方向来处理这个具有历史挑战性的问题。它学会用机器学习软件对人类决策进行建模，并利用该软件的算法偏差来检测人类决策中的偏差。这项工作可能会在许多决策活动中推进公平过程，如人才招聘，信用卡审批和学校录取。与大多数专注于提高算法公平性的现有研究相反，这项工作旨在隔离从训练数据（以人类决策为因变量）继承的算法偏见，作为人类决策不公平性的指标。为此，该项目将使用一种新技术来测试人类决策的公平性。具体来说，机器学习模型是在每个人口统计组中重新平衡类分布的测试下根据人类决策进行训练的，然后用比较判断的回归测试套件测试学习模型。如果模型在回归测试中失败，那么它所训练的人类决策将被认为是不公平的。虽然很难直接测试人类是否有偏见，但通过比较判断来测试机器学习模型是否会做出有偏见的预测更容易。该奖项反映了NSF的法定使命，并通过使用基金会的智力价值和更广泛的影响审查标准进行评估，被认为值得支持。