Causal Multi-level Fairness
Causal Multi-level Fairness
复制标题
因果多层次公平性
DOI：
10.1145/3461702.3462587
复制
发表时间：
2021
期刊：
影响因子：
--
通讯作者：
Chunara, Rumi
中科院分区：
文献类型：
--
作者：
Mhasawade, Vishwali;Chunara, Rumi
众所周知，算法系统会严重影响边缘化群体，如果不考虑所有偏见来源，情况更是如此。虽然迄今为止算法公平性方面的工作主要集中在解决由于个体相关属性而导致的歧视，但社会科学研究阐明了我们与个体相关的一些属性如何被概念化为在宏观（例如结构）层面上有原因，并且在多个层面上公平对待属性可能很重要。例如，不是简单地将种族视为个人的因果关系和受保护的属性，而是可以将原因提炼为个人经历的感知种族歧视，而这反过来又会受到邻里因素的影响。这种多层次的概念化与公平问题有关，因为不仅要考虑到个人是否属于另一个人口群体，而且要考虑到个人是否在宏观一级受到歧视待遇。在本文中，我们正式的问题，多层次的公平性，使用工具，从因果推理的方式，允许一个评估和解释敏感属性的影响，在多个层次。我们通过说明剩余的不公平性，如果宏观层面的敏感属性不占，或包括不占其多层次的性质，说明问题的重要性。此外，在现实世界的任务的背景下，预测收入的基础上，宏观和个人层面的属性，我们展示了一种方法来减轻不公平，多层次的敏感属性的结果。
Algorithmic systems are known to impact marginalized groups severely, and more so, if all sources of bias are not considered. While work in algorithmic fairness to-date has primarily focused on addressing discrimination due to individually linked attributes, social science research elucidates how some properties we link to individuals can be conceptualized as having causes at macro (e.g. structural) levels, and it may be important to be fair to attributes at multiple levels. For example, instead of simply considering race as a causal, protected attribute of an individual, the cause may be distilled as perceived racial discrimination an individual experiences, which in turn can be affected by neighborhood-level factors. This multi-level conceptualization is relevant to questions of fairness, as it may not only be important to take into account if the individual belonged to another demographic group, but also if the individual received advantaged treatment at the macro-level. In this paper, we formalize the problem of multi-level fairness using tools from causal inference in a manner that allows one to assess and account for effects of sensitive attributes at multiple levels. We show importance of the problem by illustrating residual unfairness if macro-level sensitive attributes are not accounted for, or included without accounting for their multi-level nature. Further, in the context of a real-world task of predicting income based on macro and individual-level attributes, we demonstrate an approach for mitigating unfairness, a result of multi-level sensitive attributes.
登录
查看更多内容
DOI：
10.1177/000271620056800113
发表时间：
1985
期刊：
The American Economic Review
影响因子：
--
作者：
C. Reimers
通讯作者：
C. Reimers
DOI：
--
发表时间：
2017
期刊：
Neural Information Processing Systems
影响因子：
--
作者：
Niki Kilbertus;Mateo Rojas;Giambattista Parascandolo;Moritz Hardt;D. Janzing;B. Scholkopf
通讯作者：
B. Scholkopf
DOI：
--
发表时间：
2018
期刊：
arXiv.org
影响因子：
--
作者：
Matt J. Kusner;Chris Russell;Joshua R. Loftus;Ricardo Silva
通讯作者：
Ricardo Silva
影响因子：
2.5
作者：
Ross, Catherine E.;Mirowsky, John
通讯作者：
Mirowsky, John
用未衡量的混杂因素的代理变量识别因果效应。
影响因子：
2.7
作者：
Miao W;Geng Z;Tchetgen Tchetgen E
通讯作者：
Tchetgen Tchetgen E