Model-assisted and Knowledge-guided Transfer Regression for the Underrepresented Population

TL;DR

This paper introduces MAKEUP, a transfer learning method for high-dimensional regression that addresses covariate shift and model heterogeneity in underrepresented populations, improving risk modeling with theoretical guarantees and real-world validation.

Contribution

The paper proposes a novel transfer learning approach called MAKEUP that combines model-assisted debiasing and knowledge-guided sparsification to enhance minority group risk modeling.

Findings

MAKEUP achieves efficient estimation of minority risk models.

It maintains robustness against model misspecification.

Numerical studies show advantages over existing methods.

Abstract

Covariate shift and outcome model heterogeneity are two prominent challenges in leveraging external sources to improve risk modeling for underrepresented cohorts in paucity of accurate labels. We consider the transfer learning problem targeting some unlabeled minority sample encountering (i) covariate shift to the labeled source sample collected on a different cohort; and (ii) outcome model heterogeneity with some majority sample informative to the targeted minority model. In this scenario, we develop a novel model-assisted and knowledge-guided transfer learning targeting underrepresented population (MAKEUP) approach for high-dimensional regression models. Our MAKEUP approach includes a model-assisted debiasing step in response to the covariate shift, accompanied by a knowledge-guided sparsifying procedure leveraging the majority data to enhance learning on the minority group. We also develop a model selection method to avoid negative knowledge transfer that can work in the absence of gold standard labels on the target sample. Theoretical analyses show that MAKEUP provides efficient estimation for the target model on the minority group. It maintains robustness to the high complexity and misspecification of the nuisance models used for covariate shift correction, as well as adaptivity to the model heterogeneity and potential negative transfer between the majority and minority groups. Numerical studies demonstrate similar advantages in finite sample settings over existing approaches. We also illustrate our approach through a real-world application about the transfer learning of Type II diabetes genetic risk models on some underrepresented ancestry group.