A Dynamic Decision-Making Framework Promoting Long-Term Fairness

A Dynamic Decision-Making Framework Promoting Long-Term Fairness
复制标题

促进长期公平的动态决策框架

DOI:
10.1145/3514094.3534127
复制
发表时间:
2022
期刊:
AIES 2022
影响因子:
--
通讯作者:
Pedarsani, Ramtin
Pedarsani, Ramtin
中科院分区:
--
文献类型:
--
作者:
Puranik, Bhagyashree;Madhow, Upamanyu;Pedarsani, Ramtin

文献摘要

参考文献

被引文献

相似文献

随着基于人工智能的决策在我们的社会中发挥越来越重要的作用,例如在我们的金融和刑事司法系统中,人们对设计符合特定应用的公平概念的算法非常感兴趣。在这项工作中,我们提出了一个补充性的问题:基于人工智能的决策是否可以被设计为动态地影响我们社会长期公平的演变?为了探讨这个问题,我们提出了一个框架,顺序决策的目的是动态影响长期的社会公平,说明通过选择申请人从两个群体组成的池,其中一个是代表性不足的问题。我们考虑一个申请人库组成的动态模型,在这个模型中,在一轮甄选中,一个群体中有更多的申请人被录取,这将积极地加强该群体中更多的候选人参加未来的甄选。在这样一个模型下,我们展示了拟议的公平贪婪选择政策的有效性,该政策系统地将所选申请人的分数之和(“贪婪”)与属于给定组的所选申请人的比例与目标比例(“公平”)的偏差进行交易。除了对合成数据进行实验外,我们还采用了关于法学院候选人和信贷的静态真实数据集来模拟申请人群体组成的动态。我们证明了申请人池组成收敛到一个目标比例由决策者设置时,得分分布在各组是相同的。
With AI-based decisions playing an increasingly consequential role in our society, for example, in our financial and criminal justice systems, there is a great deal of interest in designing algorithms conforming to application-specific notions of fairness. In this work, we ask a complementary question: can AI-based decisions be designed to dynamically influence the evolution of fairness in our society over the long term? To explore this question, we propose a framework for sequential decision-making aimed at dynamically influencing long-term societal fairness, illustrated via the problem of selecting applicants from a pool consisting of two groups, one of which is under-represented. We consider a dynamic model for the composition of the applicant pool, in which admission of more applicants from a group in a given selection round positively reinforces more candidates from the group to participate in future selection rounds. Under such a model, we show the efficacy of the proposed Fair-Greedy selection policy which systematically trades the sum of the scores of the selected applicants ("greedy'') against the deviation of the proportion of selected applicants belonging to a given group from a target proportion ("fair''). In addition to experimenting on synthetic data, we adapt static real-world datasets on law school candidates and credit lending to simulate the dynamics of the composition of the applicant pool. We prove that the applicant pool composition converges to a target proportion set by the decision-maker when score distributions across the groups are identical.
在顺序决策中使用机器学习时的群体保留:用户动态与公平性之间的相互作用
DOI: --
发表时间: 2019
期刊: 33rd Conference on Neural Information Processing Systems
影响因子: --
作者:
Zhang, Xueru;Khalili, Mohammad Mahdi;Tekin, Cem;Liu, Mingyan
通讯作者: Liu, Mingyan
DOI: 10.1145/3351095.3372861
发表时间: 2019
期刊: Proceedings of the 2020 Conference on Fairness, Accountability, and Transparency
影响因子: --
作者:
Lydia T. Liu;Ashia C. Wilson;Nika Haghtalab;A. Kalai;C. Borgs;J. Chayes
通讯作者: J. Chayes
预测警务中失控的反馈循环
DOI: --
发表时间: 2018
期刊: and Transparency
影响因子: --
作者:
Ensign, Danielle;Friedler, Sorelle A.;Neville, Scott;Scheidegger, Carlos;Venkatasubramanian, Suresh
通讯作者: Venkatasubramanian, Suresh
从公平决策到社会平等
DOI: 10.1145/3287560.3287599
发表时间: 2018
期刊: Proceedings of the Conference on Fairness, Accountability, and Transparency
影响因子: --
作者:
Hussein Mozannar;Mesrob I. Ohannessian;N. Srebro
通讯作者: N. Srebro
DOI: --
发表时间: 2019
期刊: Neural Information Processing Systems
影响因子: --
作者:
Yahav Bechavod;Katrina Ligett;Aaron Roth;Bo Waggoner;Zhiwei Steven Wu
通讯作者: Zhiwei Steven Wu