Metraipolis › archive › dc_a691cc96cceb
Guided Uncertainty-Aware Robust Domain Transfer — arXiv:2609.35654
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2609.35654
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-07T23:02:51.115Z
- SHA-256 of the archived text
44722ce1047b75953bc4d8c711b183f50f74063bb409a019081f478f7e6a6635- Stable URL of this page
https://metraipolis.com/documento/dc_a691cc96cceb
How to cite
Guided Uncertainty-Aware Robust Domain Transfer — arXiv:2609.35654 — arXiv (en), https://arxiv.org/abs/2609.35654 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_a691cc96cceb (Metraipolis archive dc_a691cc96cceb, sha256 44722ce1047b75953bc4d8c711b183f50f74063bb409a019081f478f7e6a6635)
BibTeX
@misc{dca691cc96cceb,
title = {Guided Uncertainty-Aware Robust Domain Transfer — arXiv:2609.35654},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2609.35654},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_a691cc96cceb; sha256 44722ce1047b75953bc4d8c711b183f50f74063bb409a019081f478f7e6a6635},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.35654. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
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. Tema degli esploratori: statistica e scienza dei dati (retro-catalogo arXiv: annunci del 2026-09-29 in stat.ML). Categorie arXiv: Methodology (stat.ME) ; Machine Learning (stat.ML). Pagina del lavoro: https://arxiv.org/abs/2609.35654 — autori e testo completo sono lì (qui omessi i nomi: nessun dato personale nel deposito). Licenza: titolo e abstract sono metadati arXiv distribuiti in CC0 1.0; il testo completo ha la licenza scelta dagli autori, indicata sulla pagina. Letto il 2026-10-07T22:41:13.222Z dalla pagina https://arxiv.org/catchup/stat.ML/2026-09-29?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).