Publication Type

Journal Article

Version

acceptedVersion

Publication Date

2-2021

Abstract

The growing use of automated decision-making in critical applications, such as crime prediction and college admission, has raised questions about fairness in machine learning. How can we decide whether different treatments are reasonable or discriminatory? In this paper, we investigate discrimination in machine learning from a visual analytics perspective and propose an interactive visualization tool, DiscriLens, to support a more comprehensive analysis. To reveal detailed information on algorithmic discrimination, DiscriLens identifies a collection of potentially discriminatory itemsets based on causal modeling and classification rules mining. By combining an extended Euler diagram with a matrix-based visualization, we develop a novel set visualization to facilitate the exploration and interpretation of discriminatory itemsets. A user study shows that users can interpret the visually encoded information in DiscriLens quickly and accurately. Use cases demonstrate that DiscriLens provides informative guidance in understanding and reducing algorithmic discrimination.

Keywords

Machine Learning, Discrimination, Data Visualization

Discipline

Databases and Information Systems | Software Engineering | Theory and Algorithms

Research Areas

Software and Cyber-Physical Systems

Publication

IEEE Transactions on Visualization and Computer Graphics

Volume

27

Issue

2

First Page

1470

Last Page

1480

ISSN

1077-2626

Identifier

10.1109/TVCG.2020.3030471

Publisher

Institute of Electrical and Electronics Engineers

Copyright Owner and License

Authors

Additional URL

https://doi.org/10.1109/TVCG.2020.3030471

Share

COinS