Back to Search
Start Over
Silva: Interactively Assessing Machine Learning Fairness Using Causality
- Source :
- CHI
- Publication Year :
- 2020
- Publisher :
- ACM, 2020.
-
Abstract
- 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.
- Subjects :
- Computer science
business.industry
05 social sciences
020207 software engineering
02 engineering and technology
Machine learning
computer.software_genre
Causality
0202 electrical engineering, electronic engineering, information engineering
0501 psychology and cognitive sciences
Artificial intelligence
business
computer
050107 human factors
Subjects
Details
- Database :
- OpenAIRE
- Journal :
- Proceedings of the 2020 CHI Conference on Human Factors in Computing Systems
- Accession number :
- edsair.doi...........8e6b59dad60149e7391d8bdb5066b82f