Sumon Biswas
Sumon Biswas
Home
Experience
Publication
Service
Accomplishments
Project
Teaching
News
Blogs
Contact
Light
Dark
Automatic
preprocessing
Fair Preprocessing: Towards Understanding Compositional Fairness of Data Transformers in Machine Learning Pipeline
We introduced the causal method of fairness to reason about the fairness impact of data preprocessing stages in ML pipeline. We leveraged existing metrics to define the fairness measures of the stages. Then we conducted a detailed fairness evaluation of the preprocessing stages in 37 pipelines collected from three different sources.
Sumon Biswas
,
Hridesh Rajan
Cite
Code
DOI
PDF
arXiv
Cite
×