A systematic literature review on incomplete multimodal learning: techniques and challenges

Recently, machine learning technologies have been successfully applied across various fields. However, most existing machine learning models rely on unimodal data for information inference, which hinders their ability to generalize to complex application scenarios. This limitation has resulted in th...

Full description

Saved in:
Bibliographic Details
Main Authors: Yifan Zhan, Rui Yang, Junxian You, Mengjie Huang, Weibo Liu, Xiaohui Liu
Format: Article
Language:English
Published: Taylor & Francis Group 2025-12-01
Series:Systems Science & Control Engineering
Subjects:
Online Access:https://www.tandfonline.com/doi/10.1080/21642583.2025.2467083
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1850139978889166848
author Yifan Zhan
Rui Yang
Junxian You
Mengjie Huang
Weibo Liu
Xiaohui Liu
author_facet Yifan Zhan
Rui Yang
Junxian You
Mengjie Huang
Weibo Liu
Xiaohui Liu
author_sort Yifan Zhan
collection DOAJ
description Recently, machine learning technologies have been successfully applied across various fields. However, most existing machine learning models rely on unimodal data for information inference, which hinders their ability to generalize to complex application scenarios. This limitation has resulted in the development of multimodal learning, a field that integrates information from different modalities to enhance models' capabilities. However, data often suffers from missing or incomplete modalities in practical applications. This necessitates that models maintain robustness and effectively infer complete information in the presence of missing modalities. The emerging research direction of incomplete multimodal learning (IML) aims to facilitate effective learning from incomplete multimodal training sets, ensuring that models can dynamically and robustly address new instances with arbitrary missing modalities during the testing phase. This paper offers a comprehensive review of methods based on IML. It categorizes existing approaches based on their information sources into two main types: based on internal information and external information methods. These categories are further subdivided into data-based, feature-based, knowledge transfer-based, graph knowledge enhancement-based, and human-in-the-loop-based methods. The paper conducts comparative analyses from two perspectives: comparisons among similar methods and comparisons among different types of methods. Finally, it offers insights into the research trends in IML.
format Article
id doaj-art-db27f15f9d88468d9ea86150dbeadb67
institution OA Journals
issn 2164-2583
language English
publishDate 2025-12-01
publisher Taylor & Francis Group
record_format Article
series Systems Science & Control Engineering
spelling doaj-art-db27f15f9d88468d9ea86150dbeadb672025-08-20T02:30:01ZengTaylor & Francis GroupSystems Science & Control Engineering2164-25832025-12-0113110.1080/21642583.2025.2467083A systematic literature review on incomplete multimodal learning: techniques and challengesYifan Zhan0Rui Yang1Junxian You2Mengjie Huang3Weibo Liu4Xiaohui Liu5School of Advanced Technology, Xi'an Jiaotong-Liverpool University, Suzhou, People's Republic of ChinaSchool of Advanced Technology, Xi'an Jiaotong-Liverpool University, Suzhou, People's Republic of ChinaSchool of Advanced Technology, Xi'an Jiaotong-Liverpool University, Suzhou, People's Republic of ChinaDesign School, Xi'an Jiaotong-Liverpool University, Suzhou, People's Republic of ChinaDepartment of Computer Science, Brunel University London, Uxbridge, UKDepartment of Computer Science, Brunel University London, Uxbridge, UKRecently, machine learning technologies have been successfully applied across various fields. However, most existing machine learning models rely on unimodal data for information inference, which hinders their ability to generalize to complex application scenarios. This limitation has resulted in the development of multimodal learning, a field that integrates information from different modalities to enhance models' capabilities. However, data often suffers from missing or incomplete modalities in practical applications. This necessitates that models maintain robustness and effectively infer complete information in the presence of missing modalities. The emerging research direction of incomplete multimodal learning (IML) aims to facilitate effective learning from incomplete multimodal training sets, ensuring that models can dynamically and robustly address new instances with arbitrary missing modalities during the testing phase. This paper offers a comprehensive review of methods based on IML. It categorizes existing approaches based on their information sources into two main types: based on internal information and external information methods. These categories are further subdivided into data-based, feature-based, knowledge transfer-based, graph knowledge enhancement-based, and human-in-the-loop-based methods. The paper conducts comparative analyses from two perspectives: comparisons among similar methods and comparisons among different types of methods. Finally, it offers insights into the research trends in IML.https://www.tandfonline.com/doi/10.1080/21642583.2025.2467083Incomplete multimodal learningmultimodal learningmodality missing
spellingShingle Yifan Zhan
Rui Yang
Junxian You
Mengjie Huang
Weibo Liu
Xiaohui Liu
A systematic literature review on incomplete multimodal learning: techniques and challenges
Systems Science & Control Engineering
Incomplete multimodal learning
multimodal learning
modality missing
title A systematic literature review on incomplete multimodal learning: techniques and challenges
title_full A systematic literature review on incomplete multimodal learning: techniques and challenges
title_fullStr A systematic literature review on incomplete multimodal learning: techniques and challenges
title_full_unstemmed A systematic literature review on incomplete multimodal learning: techniques and challenges
title_short A systematic literature review on incomplete multimodal learning: techniques and challenges
title_sort systematic literature review on incomplete multimodal learning techniques and challenges
topic Incomplete multimodal learning
multimodal learning
modality missing
url https://www.tandfonline.com/doi/10.1080/21642583.2025.2467083
work_keys_str_mv AT yifanzhan asystematicliteraturereviewonincompletemultimodallearningtechniquesandchallenges
AT ruiyang asystematicliteraturereviewonincompletemultimodallearningtechniquesandchallenges
AT junxianyou asystematicliteraturereviewonincompletemultimodallearningtechniquesandchallenges
AT mengjiehuang asystematicliteraturereviewonincompletemultimodallearningtechniquesandchallenges
AT weiboliu asystematicliteraturereviewonincompletemultimodallearningtechniquesandchallenges
AT xiaohuiliu asystematicliteraturereviewonincompletemultimodallearningtechniquesandchallenges
AT yifanzhan systematicliteraturereviewonincompletemultimodallearningtechniquesandchallenges
AT ruiyang systematicliteraturereviewonincompletemultimodallearningtechniquesandchallenges
AT junxianyou systematicliteraturereviewonincompletemultimodallearningtechniquesandchallenges
AT mengjiehuang systematicliteraturereviewonincompletemultimodallearningtechniquesandchallenges
AT weiboliu systematicliteraturereviewonincompletemultimodallearningtechniquesandchallenges
AT xiaohuiliu systematicliteraturereviewonincompletemultimodallearningtechniquesandchallenges