Search Results for author:
Found 3 papers, 0 papers with code
Practical Bias Mitigation through Proxy Sensitive Attribute Label Generation
Addressing bias in the trained machine learning system often requires access to sensitive attributes.
GroupMixNorm Layer for Learning Fair Models
Analysis on benchmark tabular and image datasets demonstrates the efficacy of the proposed method in achieving state-of-the-art performance.
Transitioning from Real to Synthetic data: Quantifying the bias in model
This study aims to establish a trade-off between bias and fairness in the models trained using synthetic data.
Cannot find the paper you are looking for? You can
Submit a new open access paper.
