REMIND: Rethinking Medical High-Modality Learning under Missingness--A Long-Tailed Distribution Perspective

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Wu, Chenwei, Shuai, Zitao, Shen, Liyue
Format: Preprint
Published: 2026
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866911474381750272
author Wu, Chenwei
Shuai, Zitao
Shen, Liyue
author_facet Wu, Chenwei
Shuai, Zitao
Shen, Liyue
contents Medical multi-modal learning is critical for integrating information from a large set of diverse modalities. However, when leveraging a high number of modalities in real clinical applications, it is often impractical to obtain full-modality observations for every patient due to data collection constraints, a problem we refer to as 'High-Modality Learning under Missingness'. In this study, we identify that such missingness inherently induces an exponential growth in possible modality combinations, followed by long-tail distributions of modality combinations due to varying modality availability. While prior work overlooked this critical phenomenon, we find this long-tailed distribution leads to significant underperformance on tail modality combination groups. Our empirical analysis attributes this problem to two fundamental issues: 1) gradient inconsistency, where tail groups' gradient updates diverge from the overall optimization direction; 2) concept shifts, where each modality combination requires distinct fusion functions. To address these challenges, we propose REMIND, a unified framework that REthinks MultImodal learNing under high-moDality missingness from a long-tail perspective. Our core idea is to propose a novel group-specialized Mixture-of-Experts architecture that scalably learns group-specific multi-modal fusion functions for arbitrary modality combinations, while simultaneously leveraging a group distributionally robust optimization strategy to upweight underrepresented modality combinations. Extensive experiments on real-world medical datasets show that our framework consistently outperforms state-of-the-art methods, and robustly generalizes across various medical multi-modal learning applications under high-modality missingness.
format Preprint
id arxiv_https___arxiv_org_abs_2603_00046
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle REMIND: Rethinking Medical High-Modality Learning under Missingness--A Long-Tailed Distribution Perspective
Wu, Chenwei
Shuai, Zitao
Shen, Liyue
Machine Learning
Artificial Intelligence
Medical multi-modal learning is critical for integrating information from a large set of diverse modalities. However, when leveraging a high number of modalities in real clinical applications, it is often impractical to obtain full-modality observations for every patient due to data collection constraints, a problem we refer to as 'High-Modality Learning under Missingness'. In this study, we identify that such missingness inherently induces an exponential growth in possible modality combinations, followed by long-tail distributions of modality combinations due to varying modality availability. While prior work overlooked this critical phenomenon, we find this long-tailed distribution leads to significant underperformance on tail modality combination groups. Our empirical analysis attributes this problem to two fundamental issues: 1) gradient inconsistency, where tail groups' gradient updates diverge from the overall optimization direction; 2) concept shifts, where each modality combination requires distinct fusion functions. To address these challenges, we propose REMIND, a unified framework that REthinks MultImodal learNing under high-moDality missingness from a long-tail perspective. Our core idea is to propose a novel group-specialized Mixture-of-Experts architecture that scalably learns group-specific multi-modal fusion functions for arbitrary modality combinations, while simultaneously leveraging a group distributionally robust optimization strategy to upweight underrepresented modality combinations. Extensive experiments on real-world medical datasets show that our framework consistently outperforms state-of-the-art methods, and robustly generalizes across various medical multi-modal learning applications under high-modality missingness.
title REMIND: Rethinking Medical High-Modality Learning under Missingness--A Long-Tailed Distribution Perspective
topic Machine Learning
Artificial Intelligence
url https://arxiv.org/abs/2603.00046