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...
Saved in:
| Main Authors: | , , , , , |
|---|---|
| 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 |