Silva: Interactively Assessing Machine Learning Fairness Using Causality
Silva: Interactively Assessing Machine Learning Fairness Using Causality
复制标题
Silva:利用因果关系交互式评估机器学习的公平性
DOI:
10.1145/3313831.3376447
复制
发表时间:
2020
期刊:
影响因子:
--
通讯作者:
Rzeszotarski, Jeffrey M.
中科院分区:
文献类型:
--
作者:
Yan, Jing Nathan;Gu, Ziwei;Lin, Hubert;Rzeszotarski, Jeffrey M.
Machine learning models risk encoding unfairness on the part of their developers or data sources. However, assessing fairness is challenging as analysts might misidentify sources of bias, fail to notice them, or misapply metrics. In this paper we introduce Silva, a system for exploring potential sources of unfairness in datasets or machine learning models interactively. Silva directs user attention to relationships between attributes through a global causal view, provides interactive recommendations, presents intermediate results, and visualizes metrics. We describe the implementation of Silva, identify salient design and technical challenges, and provide an evaluation of the tool in comparison to an existing fairness optimization tool.
登录
查看更多内容
DOI:
--
发表时间:
2018
期刊:
International Conference on Human Factors in Computing Systems
影响因子:
--
作者:
Allison Woodruff;Sarah E. Fox;Steven Rousso;J. Warshaw
通讯作者:
J. Warshaw
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
影响因子:
64.8
作者:
Esteva A;Kuprel B;Novoa RA;Ko J;Swetter SM;Blau HM;Thrun S
通讯作者:
Thrun S
DOI:
10.7551/mitpress/9780262525374.001.0001
发表时间:
2014
期刊:
The Journal of emergency medicine
影响因子:
--
作者:
Tarleton Gillespie;P. Boczkowski;K. Foot
通讯作者:
K. Foot
DOI:
--
发表时间:
2016
期刊:
影响因子:
--
作者:
K. Crawford
通讯作者:
K. Crawford