On the Fairness of Causal Algorithmic Recourse

On the Fairness of Causal Algorithmic Recourse
复制标题

论因果算法追索的公平性

DOI:
--
复制
发表时间:
2020
期刊:
AAAI Conference on Artificial Intelligence
影响因子:
--
通讯作者:
B. Scholkopf
B. Scholkopf
中科院分区:
--
文献类型:
--
作者:
Julius von Kügelgen;Umang Bhatt;Amir;Isabel Valera;Adrian Weller;B. Scholkopf

文献摘要

参考文献

被引文献

相似文献

数学公平性通常从预测的角度来研究。相反,在这里,我们调查的公平性的角度,追索权行动建议个人补救不利的分类。我们提出了两个新的公平性标准,在组和个人的水平,这与以往的工作均衡平均组明智的距离从决策边界明确占功能之间的因果关系,从而捕捉下游的影响,在物理世界中进行追索行动。我们探讨了我们的标准如何与其他人,如反事实的公平,并表明,公平的追索权是补充公平的预测。我们从理论上和经验上研究如何通过改变分类器来执行公平的因果追索权,并在Adult数据集上进行案例研究。最后,我们讨论了我们的标准所揭示的数据生成过程中的公平违规行为是否可以通过社会干预而不是对分类器的限制来更好地解决。
Algorithmic fairness is typically studied from the perspective of predictions. Instead, here we investigate fairness from the perspective of recourse actions suggested to individuals to remedy an unfavourable classification. We propose two new fair-ness criteria at the group and individual level, which—unlike prior work on equalising the average group-wise distance from the decision boundary—explicitly account for causal relationships between features, thereby capturing downstream effects of recourse actions performed in the physical world. We explore how our criteria relate to others, such as counterfactual fairness, and show that fairness of recourse is complementary to fairness of prediction. We study theoretically and empirically how to enforce fair causal recourse by altering the classifier and perform a case study on the Adult dataset. Finally, we discuss whether fairness violations in the data generating process revealed by our criteria may be better addressed by societal interventions as opposed to constraints on the classifier.
DOI: 10.24963/ijcai.2019/199
发表时间: 2019-08
期刊: --
影响因子: --
作者:
Yongkai Wu;Lu Zhang;Xintao Wu
通讯作者: Yongkai Wu;Lu Zhang;Xintao Wu
DOI: 10.1145/3351095.3372876
发表时间: 2020-01
期刊: Proceedings of the 2020 Conference on Fairness, Accountability, and Transparency
影响因子: --
作者:
S. Venkatasubramanian;M. Alfano
通讯作者: S. Venkatasubramanian;M. Alfano
PC-Fairness:衡量基于因果关系的公平性的统一框架
DOI: --
发表时间: 2019
期刊: NeurIPS 2019
影响因子: --
作者:
Wu, Yongkai;Zhang, Lu;Wu, Xintao;Tong, Hanghang
通讯作者: Tong, Hanghang
学习最佳公平政策。
DOI: --
发表时间: 2019
期刊: Proceedings of machine learning research
影响因子: --
作者:
Nabi,Razieh;Malinsky,Daniel;Shpitser,Ilya
通讯作者: Shpitser,Ilya