arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2102.01203cs.CYcs.AIcs.LG
收藏

算法公平性中的突发性不公平--准确性权衡研究

Emergent Unfairness in Algorithmic Fairness-Accuracy Trade-Off Research

Cornell University(康奈尔大学)

A. Feder Cooper, Ellen Abrams

摘要:

在机器学习(ML)的子学科中,研究人员做出明确的数学假设,以便于证明写作。我们注意到,特别是在公平性-准确性权衡优化奖学金领域,类似的注意力并没有支付给这种方法的基础规范性假设。这些假设假定:1)准确性和公平性是内在对立的; 2)严格的数学等式概念可以充分模拟公平性; 3)可以独立于历史背景来衡量决策的准确性和公平性; 4)收集更多关于边缘化个体的数据是减轻权衡影响的合理解决方案。我们认为,这些假设,这往往是隐含的和未经检验的,导致不一致的结论:虽然这项工作的预期目标可能是提高机器学习模型的公平性,这些未经检验的,隐含的假设实际上可能导致紧急不公平。最后,我们提出了实现潜在解决方案的具体途径。

英文摘要:

Across machine learning (ML) sub-disciplines, researchers make explicit mathematical assumptions in order to facilitate proof-writing. We note that, specifically in the area of fairness-accuracy trade-off optimization scholarship, similar attention is not paid to the normative assumptions that ground this approach. Such assumptions presume that 1) accuracy and fairness are in inherent opposition to one another, 2) strict notions of mathematical equality can adequately model fairness, 3) it is possible to measure the accuracy and fairness of decisions independent from historical context, and 4) collecting more data on marginalized individuals is a reasonable solution to mitigate the effects of the trade-off. We argue that such assumptions, which are often left implicit and unexamined, lead to inconsistent conclusions: While the intended goal of this work may be to improve the fairness of machine learning models, these unexamined, implicit assumptions can in fact result in emergent unfairness. We conclude by suggesting a concrete path forward toward a potential resolution.

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。

↑