Path-Specific Counterfactual Fairness

Path-Specific Counterfactual Fairness
复制标题

路径特定的反事实公平性

DOI:
--
复制
发表时间:
2018
期刊:
AAAI Conference on Artificial Intelligence
影响因子:
--
通讯作者:
S. Chiappa
S. Chiappa
中科院分区:
--
文献类型:
--
作者:
S. Chiappa

文献摘要

参考文献

被引文献

相似文献

我们考虑从数据中学习公平决策系统的问题,其中敏感属性可能会影响公平和不公平路径上的决策。我们引入了一种反事实方法来忽视不公平路径的影响,这种方法不会像以前的方法那样导致个人特定信息的丢失。我们的方法纠正受敏感属性不利影响的观察结果,并使用这些结果来形成决策。我们利用深度学习和近似推理的最新发展,开发了一种广泛适用于复杂非线性模型的 VAE 型方法。
We consider the problem of learning fair decision systems from data in which a sensitive attribute might affect the decision along both fair and unfair pathways. We introduce a counterfactual approach to disregard effects along unfair pathways that does not incur in the same loss of individual-specific information as previous approaches. Our method corrects observations adversely affected by the sensitive attribute, and uses these to form a decision. We leverage recent developments in deep learning and approximate inference to develop a VAE-type method that is widely applicable to complex nonlinear models.
反歧视学习:基于因果建模的框架
DOI: 10.1007/s41060-017-0058-x
发表时间: 2017
影响因子: 2.4
作者:
Zhang, Lu;Wu, Xintao
通讯作者: Wu, Xintao
DOI: 10.24963/ijcai.2017/549
发表时间: 2017
期刊: Proceedings of the Twenty-Sixth International Joint Conference on Artificial Intelligence
影响因子: --
作者:
Zhang, Lu;Wu, Yongkai;Wu, Xintao
通讯作者: Wu, Xintao