Uncertainty-Aware mRMR for Transferable Feature Selection in High-Dimensional, Low-Sample-Size Biomedical Data

Xuehan Chen, Brian D. Davison
Proceedings of the 11th Machine Learning for Healthcare Conference, PMLR 340:314-335, 2026.

Abstract

In biomedical and clinical research, high-dimensional data are often collected from multiple heterogeneous source groups, such as different hospitals, patient populations, cancer types, or experimental conditions. Researchers often seek a compact set of features, such as genes, that is informative across source groups and remains useful in newly collected, unseen target groups. Despite its practical importance, this transferable feature selection problem in the high-dimensional, low-sample-size (HDLSS) setting remains underexplored. In this work, we propose Uncertainty-Aware mRMR (UA-mRMR), a training-free filter method that extends the minimum Redundancy Maximum Relevance (mRMR) feature selection method by accounting for sample-size-dependent statistical uncertainty across heterogeneous source groups. Specifically, UA-mRMR uses Fisher z-transformed confidence bounds to stabilize correlation-based relevance and redundancy estimates under unequal sample sizes. Experiments on real-world multi-source biomedical datasets show that features selected by UA-mRMR transfer effectively to unseen target groups and achieve strong downstream predictive performance.

Cite this Paper

BibTeX
@InProceedings{pmlr-v340-chen26a, title = {Uncertainty-Aware mRMR for Transferable Feature Selection in High-Dimensional, Low-Sample-Size Biomedical Data}, author = {Chen, Xuehan and Davison, Brian D.}, booktitle = {Proceedings of the 11th Machine Learning for Healthcare Conference}, pages = {314--335}, year = {2026}, editor = {Krishnan, Rahul G. and van Amsterdam, Wouter A. C. and Chopra, Sumit and Overgaard, Shauna and Hughes, Michael and Ötleş, Erkin and Shen, Yiqiu and Shanmugam, Divya and Nayan, Madhur and Engelhard, Matthew and Fackler, Jim and Oberst, Michael}, volume = {340}, series = {Proceedings of Machine Learning Research}, month = {12--14 Aug}, publisher = {PMLR}, pdf = {https://raw.githubusercontent.com/mlresearch/v340/main/assets/chen26a/chen26a.pdf}, url = {https://proceedings.mlr.press/v340/chen26a.html}, abstract = {In biomedical and clinical research, high-dimensional data are often collected from multiple heterogeneous source groups, such as different hospitals, patient populations, cancer types, or experimental conditions. Researchers often seek a compact set of features, such as genes, that is informative across source groups and remains useful in newly collected, unseen target groups. Despite its practical importance, this transferable feature selection problem in the high-dimensional, low-sample-size (HDLSS) setting remains underexplored. In this work, we propose Uncertainty-Aware mRMR (UA-mRMR), a training-free filter method that extends the minimum Redundancy Maximum Relevance (mRMR) feature selection method by accounting for sample-size-dependent statistical uncertainty across heterogeneous source groups. Specifically, UA-mRMR uses Fisher z-transformed confidence bounds to stabilize correlation-based relevance and redundancy estimates under unequal sample sizes. Experiments on real-world multi-source biomedical datasets show that features selected by UA-mRMR transfer effectively to unseen target groups and achieve strong downstream predictive performance.} }
Endnote
%0 Conference Paper %T Uncertainty-Aware mRMR for Transferable Feature Selection in High-Dimensional, Low-Sample-Size Biomedical Data %A Xuehan Chen %A Brian D. Davison %B Proceedings of the 11th Machine Learning for Healthcare Conference %C Proceedings of Machine Learning Research %D 2026 %E Rahul G. Krishnan %E Wouter A. C. van Amsterdam %E Sumit Chopra %E Shauna Overgaard %E Michael Hughes %E Erkin Ötleş %E Yiqiu Shen %E Divya Shanmugam %E Madhur Nayan %E Matthew Engelhard %E Jim Fackler %E Michael Oberst %F pmlr-v340-chen26a %I PMLR %P 314--335 %U https://proceedings.mlr.press/v340/chen26a.html %V 340 %X In biomedical and clinical research, high-dimensional data are often collected from multiple heterogeneous source groups, such as different hospitals, patient populations, cancer types, or experimental conditions. Researchers often seek a compact set of features, such as genes, that is informative across source groups and remains useful in newly collected, unseen target groups. Despite its practical importance, this transferable feature selection problem in the high-dimensional, low-sample-size (HDLSS) setting remains underexplored. In this work, we propose Uncertainty-Aware mRMR (UA-mRMR), a training-free filter method that extends the minimum Redundancy Maximum Relevance (mRMR) feature selection method by accounting for sample-size-dependent statistical uncertainty across heterogeneous source groups. Specifically, UA-mRMR uses Fisher z-transformed confidence bounds to stabilize correlation-based relevance and redundancy estimates under unequal sample sizes. Experiments on real-world multi-source biomedical datasets show that features selected by UA-mRMR transfer effectively to unseen target groups and achieve strong downstream predictive performance.
APA
Chen, X. & Davison, B.D.. (2026). Uncertainty-Aware mRMR for Transferable Feature Selection in High-Dimensional, Low-Sample-Size Biomedical Data. Proceedings of the 11th Machine Learning for Healthcare Conference, in Proceedings of Machine Learning Research 340:314-335 Available from https://proceedings.mlr.press/v340/chen26a.html.

Related Material