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 2003.05048stat.MLcs.LG
收藏

个体偏差和不公平性的ML模型审计

Auditing ML Models for Individual Bias and Unfairness

Department of Statistics University of Michigan(密歇根大学统计系);IBM Research(IBM研究);MIT-IBM Watson AI lab(麻省理工学院-IBM沃森人工智能实验室)

Songkai Xue, Mikhail Yurochkin, Yuekai Sun

摘要:

我们考虑审计ML模型的个人偏见/不公平性的任务。我们正式的任务在一个优化问题,并开发了一套推理工具的最佳值。我们的工具使我们能够获得渐近置信区间和假设检验,覆盖目标/控制第一类错误率。为了证明我们的工具的实用性,我们用它们来揭示性别和种族偏见在Northpointe的COMPAS累犯预测工具。

英文摘要:

We consider the task of auditing ML models for individual bias/unfairness. We formalize the task in an optimization problem and develop a suite of inferential tools for the optimal value. Our tools permit us to obtain asymptotic confidence intervals and hypothesis tests that cover the target/control the Type I error rate exactly. To demonstrate the utility of our tools, we use them to reveal the gender and racial biases in Northpointe's COMPAS recidivism prediction instrument.

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。

↑