MithraCoverage: A System for Investigating Population Bias for Intersectional Fairness
MithraCoverage: A System for Investigating Population Bias for Intersectional Fairness
复制标题
MithraCoverage：用于调查群体偏差以实现交叉公平的系统
DOI：
10.1145/3318464.3384689
复制
发表时间：
2020
期刊：
影响因子：
--
通讯作者：
Jagadish, H. V.
中科院分区：
文献类型：
--
作者：
Jin, Zhongjun;Xu, Mengjing;Sun, Chenkai;Asudeh, Abolfazl;Jagadish, H. V.
数据驱动技术的好坏取决于它们所使用的数据。另一方面，数据科学家通常对数据收集方式的控制有限。未能包含足够数量的来自少数（子）群体的实例，称为人口偏见，是模型不公平和不同群体之间表现不一的主要原因。我们展示了MithraCoverage，一个用于调查多个属性交叉点的人口偏见的系统。我们使用覆盖率的概念来识别数据集中代表性不足的交叉亚组。MithraCoverage是一个具有交互式可视化界面的Web应用程序，允许数据科学家探索数据集并识别覆盖率低的子组。
Data-driven technologies are only as good as the data they work with. On the other hand, data scientists have often limited control on how the data is collected. Failing to contain adequate number of instances from minority (sub)groups, known as population bias, is a major reason for model unfairness and disparate performance across different groups. We demonstrate MithraCoverage, a system for investigating population bias over the intersection of multiple attributes. We use the concept of coverage for identifying intersectional subgroups with inadequate representation in the dataset. MithraCoverage is a web application with an interactive visual interface that allows data scientists to explore the dataset and identify subgroups with poor coverage.
组合下的群体公平性
DOI：
--
发表时间：
2018
期刊：
影响因子：
--
作者：
C. Dwork;Christina Ilvento
通讯作者：
Christina Ilvento