Fair Representation Learning with Maximum Mean Discrepancy Distance Constraint (Student Abstract)
Abstract
Unsupervised learning methods such as principal component analysis (PCA), t-distributed stochastic neighbor embedding (t-SNE), and autoencoding are regularly used in dimensionality reduction within the statistical learning scene. However, despite a pivot toward fairness and explainability in machine learning over the past few years, there have been few rigorous attempts toward a generalized framework of fair and explainable representation learning. Our paper explores the possibility of such a framework that leverages maximum mean discrepancy to remove information derived from a protected class from generated representations. For the optimization, we introduce a binary search component to optimize the Lagrangian coefficients. We present rigorous mathematical analysis and experimental results of our framework applied to t-SNE.
Cite
Text
Lopotenco et al. "Fair Representation Learning with Maximum Mean Discrepancy Distance Constraint (Student Abstract)." AAAI Conference on Artificial Intelligence, 2024. doi:10.1609/AAAI.V38I21.30476Markdown
[Lopotenco et al. "Fair Representation Learning with Maximum Mean Discrepancy Distance Constraint (Student Abstract)." AAAI Conference on Artificial Intelligence, 2024.](https://mlanthology.org/aaai/2024/lopotenco2024aaai-fair/) doi:10.1609/AAAI.V38I21.30476BibTeX
@inproceedings{lopotenco2024aaai-fair,
title = {{Fair Representation Learning with Maximum Mean Discrepancy Distance Constraint (Student Abstract)}},
author = {Lopotenco, Alexandru and Pan, Ian Tong and Zhang, Jack and Qiao, Guan Xiong},
booktitle = {AAAI Conference on Artificial Intelligence},
year = {2024},
pages = {23567-23568},
doi = {10.1609/AAAI.V38I21.30476},
url = {https://mlanthology.org/aaai/2024/lopotenco2024aaai-fair/}
}