Demographic Parity-aware Individualized Treatment Rules

2025-04-28

AI Summary

This paper addresses discrimination in individualized treatment rules (ITRs) arising from sensitive attributes—such as age, sex, and race—by formalizing demographic parity as a fairness criterion within the ITR learning framework for the first time. Method: We propose a convex surrogate objective that reformulates non-convex fairness constraints as tractable convex quadratic programs, enabling efficient optimization. Our approach integrates fair machine learning, constrained optimization, and individualized causal inference. Contribution/Results: We establish theoretical guarantees on estimation consistency and risk upper bounds for the learned fair ITRs. Extensive experiments on multiple synthetic and real-world healthcare datasets demonstrate that our method significantly improves cross-group fairness—measured by demographic parity—while preserving treatment efficacy. Moreover, the proposed estimator exhibits statistical consistency and robust generalization across heterogeneous subpopulations.

Technology Category

• Machine Learning: Causal Learning
• Constraint Satisfaction and Optimization: Constraint Learning and Acquisition
• Search and Optimization: Mixed Discrete/Continuous Search

Application Category

• User Modeling, Personalization and Recommendation: Fairness-aware retrieval and ranking
• Economics, Online Markets and Human Computation: Fairness, privacy, and diversity in economic environments
• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking

Abstract

There has been growing interest in developing optimal individualized treatment rules (ITRs) in various fields, such as precision medicine, business decision-making, and social welfare distribution. The application of ITRs within a societal context raises substantial concerns regarding potential discrimination over sensitive attributes such as age, gender, or race. To address this concern directly, we introduce the concept of demographic parity in ITRs. However, estimating an optimal ITR that satisfies the demographic parity requires solving a non-convex constrained optimization problem. To overcome these computational challenges, we employ tailored fairness proxies inspired by demographic parity and transform it into a convex quadratic programming problem. Additionally, we establish the consistency of the proposed estimator and the risk bound. The performance of the proposed method is demonstrated through extensive simulation studies and real data analysis.

Problem

• Developing optimal individualized treatment rules (ITRs) with demographic parity
• Addressing discrimination concerns in ITRs over sensitive attributes
• Solving non-convex optimization for fair ITRs using convex proxies

Innovation

• Introduces demographic parity in treatment rules
• Uses fairness proxies for convex optimization
• Ensures estimator consistency and risk bound