Diversity and Inclusion Metrics in Subset Selection

被引：46

作者：

Mitchell, Margaret ^{[1
]}

Baker, Dylan ^{[1
]}

Moorosi, Nyalleng ^{[1
]}

Denton, Emily ^{[1
]}

Hutchinson, Ben ^{[1
]}

Hanna, Alex ^{[1
]}

Gebru, Timnit ^{[1
]}

Morgenstern, Jamie ^{[1
,2
]}

机构：

[1] Google Res, Mountain View, CA 94043 USA

[2] Univ Washington, Seattle, WA 98195 USA

来源：

PROCEEDINGS OF THE 3RD AAAI/ACM CONFERENCE ON AI, ETHICS, AND SOCIETY AIES 2020 | 2020年

关键词：

machine learning fairness; subset selection; diversity and inclusion;

D O I：

10.1145/3375627.3375832

中图分类号：

TP18 [人工智能理论];

学科分类号：

081104 ; 0812 ; 0835 ; 1405 ;

摘要：

The ethical concept of fairness has recently been applied in machine learning (ML) settings to describe a wide range of constraints and objectives. When considering the relevance of ethical concepts to subset selection problems, the concepts of diversity and inclusion are additionally applicable in order to create outputs that account for social power and access differentials. We introduce metrics based on these concepts, which can be applied together, separately, and in tandem with additional fairness constraints. Results from human subject experiments lend support to the proposed criteria. Social choice methods can additionally be leveraged to aggregate and choose preferable sets, and we detail how these may be applied.

引用

页码：117 / 123

页数：7

共 37 条

[1]

Anari N, 2016, C LEARNING THEORY, V49, P103

[2]

[Anonymous], 2009, Ecol. Econ, DOI DOI 10.1016/J.ECOLECON.2008.10.015

[3] Assessing and Remedying Coverage for a Given Dataset [J].