Thinking Outside the Box: Orthogonal Approach to Equalizing Protected Attributes

2023/11/21 by Jiahui Liu, Liu, Jiahui, Xiaohao Cai +3
Health Professions · Mathematics · #Advanced Causal Inference Techniques #Artificial Intelligence in Healthcare #Computer Vision and Pattern Recognition (cs.CV) #Computers and Society (cs.CY) #FOS: Computer and information sciences #Machine Learning (cs.LG) #Statistical Methods and Inference

paper · pdf · doi:10.48550/arxiv.2311.14733

openalex publication_date 2023/11/21 · openalex created_date 2023/11/29 · openalex updated_date 2026/07/28

Abstract

There is growing concern that the potential of black box AI may exacerbate health-related disparities and biases such as gender and ethnicity in clinical decision-making. Biased decisions can arise from data availability and collection processes, as well as from the underlying confounding effects of the protected attributes themselves. This work proposes a machine learning-based orthogonal approach aiming to analyze and suppress the effect of the confounder through discriminant dimensionality reduction and orthogonalization of the protected attributes against the primary attribute information. By doing so, the impact of the protected attributes on disease diagnosis can be realized, undesirable feature correlations can be mitigated, and the model prediction performance can be enhanced.

Related

• SPARC: Scalable Path-Specific Counterfactual Fairness via Causal Conditional Independence
• Iterative Orthogonal Feature Projection for Diagnosing Bias in Black-Box Models
• M³Fair: Mitigating Bias in Healthcare Data through Multi-Level and Multi-Sensitive-Attribute Reweighting Method
• Ensuring Fairness in Machine Learning to Advance Health Equity
• Achieving Fairness Without Harm via Selective Demographic Experts