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 2402.09326cs.LG
收藏

具有不确定预测的排序中的稳定性与多组公平性

Stability and Multigroup Fairness in Ranking with Uncertain Predictions

University of Southern California(南加州大学);Princeton University(普林斯顿大学)

Siddartha Devic, Aleksandra Korolova, David Kempe, Vatsal Sharan

AI总结:

本文研究了具有不确定预测的排序问题,提出了感知不确定性(UA)排序函数,证明其能同时满足稳定性、个体公平性和多组公平性,并自然地在群体与个体层面的公平性保证之间进行插值。

摘要:

排序在从搜索引擎到招聘委员会的许多应用中无处不在。在实践中,许多排序是从预测器的输出中得出的。然而,当为分类任务训练的预测器具有内在不确定性时,如何将这种不确定性表示在导出的排序中并不明显。我们的工作考虑了排序函数:从分类任务的单个预测到排序分布的映射。我们关注排序函数的两个方面:对预测扰动的稳定性以及对个体和子群的公平性。稳定性本身不仅是一个重要的要求,而且——正如我们所展示的——它与Dwork等人(2012)意义上的个体公平性和谐地组合。虽然确定性排序函数在平凡场景之外无法保持稳定,但我们展示了Singh等人(2021)最近提出的感知不确定性(UA)排序函数是稳定的。我们的主要结果是,UA排序通过与多准确或多校准预测器的成功组合,也实现了多组公平性。我们的工作表明,UA排序自然地在群体和个体层面的公平性保证之间进行插值,同时满足在使用机器学习预测时重要的稳定性保证。

英文摘要:

Rankings are ubiquitous across many applications, from search engines to hiring committees. In practice, many rankings are derived from the output of predictors. However, when predictors trained for classification tasks have intrinsic uncertainty, it is not obvious how this uncertainty should be represented in the derived rankings. Our work considers ranking functions: maps from individual predictions for a classification task to distributions over rankings. We focus on two aspects of ranking functions: stability to perturbations in predictions and fairness towards both individuals and subgroups. Not only is stability an important requirement for its own sake, but -- as we show -- it composes harmoniously with individual fairness in the sense of Dwork et al. (2012). While deterministic ranking functions cannot be stable aside from trivial scenarios, we show that the recently proposed uncertainty aware (UA) ranking functions of Singh et al. (2021) are stable. Our main result is that UA rankings also achieve multigroup fairness through successful composition with multiaccurate or multicalibrated predictors. Our work demonstrates that UA rankings naturally interpolate between group and individual level fairness guarantees, while simultaneously satisfying stability guarantees important whenever machine-learned predictions are used.

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。

↑