Computational Methods for Multi-View Representation Learning

Dear Colleagues,

Multi-view representation learning aims to learn unified, complementary, and discriminative representations from multiple sources, modalities, sensors, or feature spaces. It has become an important research direction in machine learning, data mining, and artificial intelligence. With the rapid growth of multi-modal data, heterogeneous graph data, cross-platform user behavior data, remote sensing and medical imaging data, and scientific computing data, effectively modeling the consistency, complementarity, redundancy, and uncertainty among different views has become a key challenge in intelligent information processing.

This Special Issue focuses on ‘Computational Methods for Multi-View Representation Learning’ and aims to present recent advances in theoretical models, algorithm design, optimization methods, and practical applications in this field. We welcome original research articles, review articles, and methodological papers on topics including multi-view feature fusion, multi-modal representation learning, cross-view alignment, contrastive learning, graph representation learning, deep clustering, semi-supervised and self-supervised learning, incomplete-view learning, robust representation learning, interpretable multi-view learning, and large-scale efficient optimization methods.

Specific methods and fields of applications include, but are not limited to, the following:

• Multi-view representation learning.
• Multi-modal representation learning.
• Cross-view alignment, matching, and fusion.
• Multi-view contrastive learning.
• Multi-view clustering, classification, and regression.
• Deep multi-view learning and neural representation models.
• Graph-based and hypergraph-based multi-view learning.
• Self-supervised, semi-supervised, and weakly supervised multi-view learning.
• Incomplete, partial, and missing-view learning.
• Robust multi-view learning under noisy, inconsistent, or heterogeneous views.
• Scalable optimization and efficient computation for large-scale multi-view data.
• Applications in multi-modal retrieval and cross-modal understanding.
• Applications in biomedical data analysis and healthcare informatics.
• Applications in remote sensing and geospatial intelligence.

Dr. Zhenqiu Shu
Dr. Zhe Chen
Dr. Guoqing Zhang
Guest Editors

Manuscript Submission Information

Manuscripts should be submitted online at www.mdpi.com by registering and logging in to this website. Once you are registered, click here to go to the submission form. Manuscripts can be submitted until the deadline. All submissions that pass pre-check are peer-reviewed. Accepted papers will be published continuously in the journal (as soon as accepted) and will be listed together on the special issue website. Research articles, review articles as well as short communications are invited. For planned papers, a title and short abstract (about 250 words) can be sent to the Editorial Office for assessment.

Submitted manuscripts should not have been published previously, nor be under consideration for publication elsewhere (except conference proceedings papers). All manuscripts are thoroughly refereed through a single-blind peer-review process. A guide for authors and other relevant information for submission of manuscripts is available on the Instructions for Authors page. Computation is an international peer-reviewed open access monthly journal published by MDPI.

Please visit the Instructions for Authors page before submitting a manuscript. The Article Processing Charge (APC) for publication in this open access journal is 1800 CHF (Swiss Francs). Submitted papers should be well formatted and use good English. Authors may use MDPI's English editing service prior to publication or during author revisions.

• multi-view representation learning
• multi-modal representation learning
• cross-view alignment
• feature fusion
• contrastive learning
• graph representation learning
• incomplete multi-view learning
• robust representation learning
• self-supervised learning