AAAI 2025technical0 citations
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.
BibTeX
@article{Khalili_2025, title={Mitigating Bias in Machine Learning: A Comprehensive Review and Novel Approaches}, volume={39}, url={https://ojs.aaai.org/index.php/AAAI/article/view/35107}, DOI={10.1609/aaai.v39i27.35107}, abstractNote={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.}, number={27}, journal={Proceedings of the AAAI Conference on Artificial Intelligence}, author={Khalili, Mahdi}, year={2025}, month={Apr.}, pages={28712-28712} }