Stein-Encoder: A White-Box Supervised Encoder via Stein Identities in Multi-Modal Studies

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Zhang, Jiarui, Xu, Shuoxun, Shi, Jiasheng, Guo, Xinzhou
Format: Preprint
Published: 2026
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866910254929805312
author Zhang, Jiarui
Xu, Shuoxun
Shi, Jiasheng
Guo, Xinzhou
author_facet Zhang, Jiarui
Xu, Shuoxun
Shi, Jiasheng
Guo, Xinzhou
contents In multi-modal biomedical research, integrating high-dimensional genomic data with clinical baselines is essential for precision medicine. However, standard deep neural network approaches often entangle these modalities, obscuring the specific predictive impact of genetic features and leading to possibly suboptimal predictive performance. Motivated by the landmark METABRIC cohort primary breast tumors study, we propose the Stein-Encoder, a white-box supervised framework designed to isolate the genetic signal driving clinical outcomes conditional on nuisance covariates. By leveraging Stein's method and residualization techniques, our approach constructs an interpretable single index that summarizes relevant biological heterogeneity while flexibly incorporating clinical factors and can be used to improve downstream prediction. We establish theoretical guarantees for identification, consistency and efficiency improvement. Applied to the METABRIC cohort, the Stein-Encoder outperforms unsupervised benchmarks in predictive accuracy. Crucially, it achieves structural disentanglement by revealing response-specific biological mechanisms: we find that tumor size is driven primarily by mitotic networks, whereas prognostic indices rely on a distinct proliferation-versus-immune axis. This work contributes a unified, computationally efficient framework that bridges statistical rigor with the representational power of neural networks, enabling interpretable, task-specific and efficient compression of multi-modal health data for a wide range of precision medicine applications, beyond biomarker discovery.
format Preprint
id arxiv_https___arxiv_org_abs_2605_25734
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle Stein-Encoder: A White-Box Supervised Encoder via Stein Identities in Multi-Modal Studies
Zhang, Jiarui
Xu, Shuoxun
Shi, Jiasheng
Guo, Xinzhou
Applications
Methodology
Machine Learning
In multi-modal biomedical research, integrating high-dimensional genomic data with clinical baselines is essential for precision medicine. However, standard deep neural network approaches often entangle these modalities, obscuring the specific predictive impact of genetic features and leading to possibly suboptimal predictive performance. Motivated by the landmark METABRIC cohort primary breast tumors study, we propose the Stein-Encoder, a white-box supervised framework designed to isolate the genetic signal driving clinical outcomes conditional on nuisance covariates. By leveraging Stein's method and residualization techniques, our approach constructs an interpretable single index that summarizes relevant biological heterogeneity while flexibly incorporating clinical factors and can be used to improve downstream prediction. We establish theoretical guarantees for identification, consistency and efficiency improvement. Applied to the METABRIC cohort, the Stein-Encoder outperforms unsupervised benchmarks in predictive accuracy. Crucially, it achieves structural disentanglement by revealing response-specific biological mechanisms: we find that tumor size is driven primarily by mitotic networks, whereas prognostic indices rely on a distinct proliferation-versus-immune axis. This work contributes a unified, computationally efficient framework that bridges statistical rigor with the representational power of neural networks, enabling interpretable, task-specific and efficient compression of multi-modal health data for a wide range of precision medicine applications, beyond biomarker discovery.
title Stein-Encoder: A White-Box Supervised Encoder via Stein Identities in Multi-Modal Studies
topic Applications
Methodology
Machine Learning
url https://arxiv.org/abs/2605.25734