Interactive Human-Centric Bias Mitigation
Abstract
Bias mitigation algorithms differ in their definition of bias and how they go about achieving that objective. Bias mitigation algorithms impact different cohorts differently and allowing end users and data scientists to understand the impact of these differences in order to make informed choices is a relatively unexplored domain. This demonstration presents an interactive bias mitigation pipeline that allows users to understand the cohorts impacted by their algorithm choice and provide feedback in order to provide a bias mitigated pipeline that most aligns with their goals.
Cite
Text
Vejsbjerg et al. "Interactive Human-Centric Bias Mitigation." AAAI Conference on Artificial Intelligence, 2024. doi:10.1609/AAAI.V38I21.30582Markdown
[Vejsbjerg et al. "Interactive Human-Centric Bias Mitigation." AAAI Conference on Artificial Intelligence, 2024.](https://mlanthology.org/aaai/2024/vejsbjerg2024aaai-interactive/) doi:10.1609/AAAI.V38I21.30582BibTeX
@inproceedings{vejsbjerg2024aaai-interactive,
title = {{Interactive Human-Centric Bias Mitigation}},
author = {Vejsbjerg, Inge and Daly, Elizabeth M. and Nair, Rahul and Nizhnichenkov, Svetoslav},
booktitle = {AAAI Conference on Artificial Intelligence},
year = {2024},
pages = {23838-23840},
doi = {10.1609/AAAI.V38I21.30582},
url = {https://mlanthology.org/aaai/2024/vejsbjerg2024aaai-interactive/}
}