Guided Uncertainty-Aware Robust Domain Transfer
Abstract
Artificial intelligence models deployed as clinical decision support tools often suffer substantial performance degradation over time and across institutions due to covariate shift, concept drift, and cross-system heterogeneity. Fully retraining complex models is frequently infeasible, particularly in EHR settings where labeled outcome data are scarce and regulatory constraints limit model modification. We propose GUARD (Guided and Uncertainty-Aware Robustness to Domain shift), a unified statistical framework for updating an existing deployed model using limited labeled target data and multiple heterogeneous source populations while guarding against future distributional shifts. GUARD formulates robust multi-source transfer learning as a semi-supervised, adversarial optimization problem anchored at the current model, and employs double machine learning with cross-fitting to obtain debiased, efficient estimates that leverage abundant unlabeled target covariates. It then constructs an uncertainty-aware, guided group DRO estimator that combines source and target information while accounting for sampling variability in the source models. Our framework jointly provides principled robustness to domain shift, efficient semi-supervised estimation, and valid statistical inference for multi-source transfer of clinical prediction models. We demonstrate the utility of GUARD via extensive simulation experiments and a real world application to predicting future disease activity in rheumatoid arthritis from EHR data spanning more than a decade. GUARD recalibrates a pretrained model with only a small number of labeled records per year and remains accurate over multi-year horizons where target-only and standard transfer estimators degrade sharply.
Related
- An Uncertainty-Aware Hybrid Symbolic-Lexicon Framework for Multi-Domain Sentiment Classification
- Adjustable Robust Optimization with Discrete Uncertainty
- Sparsity Regularized and Robust Mean Variance Portfolio Selection Under Ellipsoidal Uncertainty
- Generalized Semi-Infinite Programming for Robust Optimal Control with Decision-Dependent Uncertainty
- Constructing Data-Driven Budgeted Uncertainty Sets for Robust Optimization
BibTeX
@misc{xiong2026guided,
title = {{Guided Uncertainty-Aware Robust Domain Transfer}},
author = {Xin Xiong and Zijian Guo and Tianxi Cai},
howpublished = {arXiv},
year = {2026},
month = sep,
doi = {10.48550/arxiv.2609.35654},
eprint = {2609.35654},
archivePrefix = {arXiv},
url = {https://arxiv.org/abs/2609.35654},
}
RIS
TY - UNPB
TI - Guided Uncertainty-Aware Robust Domain Transfer
AU - Xin Xiong
AU - Zijian Guo
AU - Tianxi Cai
PY - 2026
DA - 2026/09/28
PB - arXiv
DO - 10.48550/arxiv.2609.35654
UR - https://arxiv.org/abs/2609.35654
AB - Artificial intelligence models deployed as clinical decision support tools often suffer substantial performance degradation over time and across institutions due to covariate shift, concept drift, and cross-system heterogeneity. Fully retraining complex models is frequently infeasible, particularly in EHR settings where labeled outcome data are scarce and regulatory constraints limit model modification. We propose GUARD (Guided and Uncertainty-Aware Robustness to Domain shift), a unified statistical framework for updating an existing deployed model using limited labeled target data and multiple heterogeneous source populations while guarding against future distributional shifts. GUARD formulates robust multi-source transfer learning as a semi-supervised, adversarial optimization problem anchored at the current model, and employs double machine learning with cross-fitting to obtain debiased, efficient estimates that leverage abundant unlabeled target covariates. It then constructs an uncertainty-aware, guided group DRO estimator that combines source and target information while accounting for sampling variability in the source models. Our framework jointly provides principled robustness to domain shift, efficient semi-supervised estimation, and valid statistical inference for multi-source transfer of clinical prediction models. We demonstrate the utility of GUARD via extensive simulation experiments and a real world application to predicting future disease activity in rheumatoid arthritis from EHR data spanning more than a decade. GUARD recalibrates a pretrained model with only a small number of labeled records per year and remains accurate over multi-year horizons where target-only and standard transfer estimators degrade sharply.
ER -