Name
Title | ||
|---|---|---|
MithraCoverage: A System for Investigating Population Bias for Intersectional Fairness |
Abstract | ||
|---|---|---|
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.
|
Year | DOI | Venue |
|---|---|---|
2020 | 10.1145/3318464.3384689 | SIGMOD/PODS '20: International Conference on Management of Data
Portland
OR
USA
June, 2020 |
Keywords | DocType | ISBN |
Fairness, Data Ethics, Responsible Data Science | Conference | 978-1-4503-6735-6 |
Citations | PageRank | References |
1 | 0.35 | 3 |
Authors | ||
5 | ||
Name | Order | Citations | PageRank |
|---|---|---|---|
| Zhongjun Jin | 1 | 24 | 5.12 |
| Mengjing Xu | 2 | 1 | 0.35 |
| Chenkai Sun | 3 | 3 | 0.71 |
| Abolfazl Asudeh | 4 | 60 | 19.05 |
| H. V. Jagadish | 5 | 11141 | 2495.67 |