Mitigating Bias in Machine Learning: A Comprehensive Review and Novel Approaches
Abstract
Machine Learning (ML) algorithms are increasingly used in our daily lives, yet often exhibit discrimination against protected groups. In this talk, I discuss the growing concern of bias in ML and overview existing approaches to address fairness issues. Then, I present three novel approaches developed by my research group. The first leverages generative AI to eliminate biases in training datasets, the second tackles non-convex problems arise in fair learning, and the third introduces a matrix decomposition-based post-processing approach to identify and eliminate unfair model components.
Cite
Text
Khalili. "Mitigating Bias in Machine Learning: A Comprehensive Review and Novel Approaches." AAAI Conference on Artificial Intelligence, 2025. doi:10.1609/AAAI.V39I27.35107Markdown
[Khalili. "Mitigating Bias in Machine Learning: A Comprehensive Review and Novel Approaches." AAAI Conference on Artificial Intelligence, 2025.](https://mlanthology.org/aaai/2025/khalili2025aaai-mitigating/) doi:10.1609/AAAI.V39I27.35107BibTeX
@inproceedings{khalili2025aaai-mitigating,
title = {{Mitigating Bias in Machine Learning: A Comprehensive Review and Novel Approaches}},
author = {Khalili, Mahdi},
booktitle = {AAAI Conference on Artificial Intelligence},
year = {2025},
pages = {28712},
doi = {10.1609/AAAI.V39I27.35107},
url = {https://mlanthology.org/aaai/2025/khalili2025aaai-mitigating/}
}