Show simple item record

dc.contributor.authorLuo, Dixin
dc.contributor.authorXu, Hongteng
dc.contributor.authorCarin, Lawrence
dc.date.accessioned2022-11-17T05:58:23Z
dc.date.available2022-11-17T05:58:23Z
dc.date.issued2022-11-16
dc.identifier.citationLuo, D., Xu, H., & Carin, L. (2022). Differentiable Hierarchical Optimal Transport for Robust Multi-View Learning. IEEE Transactions on Pattern Analysis and Machine Intelligence, 1–14. https://doi.org/10.1109/tpami.2022.3222569
dc.identifier.issn0162-8828
dc.identifier.issn2160-9292
dc.identifier.issn1939-3539
dc.identifier.doi10.1109/tpami.2022.3222569
dc.identifier.urihttp://hdl.handle.net/10754/685827
dc.description.abstractTraditional multi-view learning methods often rely on two assumptions: ( i ) the samples in different views are well-aligned, and ( ii ) their representations obey the same distribution in a latent space. Unfortunately, these two assumptions may be questionable in practice, which limits the application of multi-view learning. In this work, we propose a differentiable hierarchical optimal transport (DHOT) method to mitigate the dependency of multi-view learning on these two assumptions. Given arbitrary two views of unaligned multi-view data, the DHOT method calculates the sliced Wasserstein distance between their latent distributions. Based on these sliced Wasserstein distances, the DHOT method further calculates the entropic optimal transport across different views and explicitly indicates the clustering structure of the views. Accordingly, the entropic optimal transport, together with the underlying sliced Wasserstein distances, leads to a hierarchical optimal transport distance defined for unaligned multi-view data, which works as the objective function of multi-view learning and leads to a bi-level optimization task. Moreover, our DHOT method treats the entropic optimal transport as a differentiable operator of model parameters. It considers the gradient of the entropic optimal transport in the backpropagation step and thus helps improve the descent direction for the model in the training phase. We demonstrate the superiority of our bi-level optimization strategy by comparing it to the traditional alternating optimization strategy. The DHOT method is applicable for both unsupervised and semi-supervised learning. Experimental results show that our DHOT method is at least comparable to state-of-the-art multi-view learning methods on both synthetic and real-world tasks, especially for challenging scenarios with unaligned multi-view data.
dc.description.sponsorshipDixin Luo was supported in part by the Beijing Institute of Technology Research Fund Program for Young Scholars (XSQD-202107001) and the project 2020YFF0305200. Hongteng Xu was supported in part by Beijing Outstanding Young Scientist Program (NO. BJJWZYJH012019100020098), National Natural Science Foundation of China (No. 61832017), the Fundamental Research Funds for the Central Universities, and the Research Funds of Renmin University of China.
dc.publisherInstitute of Electrical and Electronics Engineers (IEEE)
dc.relation.urlhttps://ieeexplore.ieee.org/document/9953569/
dc.rights(c) 2022 IEEE. Personal use of this material is permitted. Permission from IEEE must be obtained for all other users, including reprinting/ republishing this material for advertising or promotional purposes, creating new collective works for resale or redistribution to servers or lists, or reuse of any copyrighted components of this work in other works.
dc.subjectHierarchical optimal transport
dc.subjectmulti-view learning
dc.subjectunaligned multi-view data
dc.subjectsliced Wasserstein distance
dc.subjectentropic optimal transport
dc.subjectbi-level optimization
dc.titleDifferentiable Hierarchical Optimal Transport for Robust Multi-View Learning
dc.typeArticle
dc.contributor.departmentProvost at King Abdullah University of Science & Technology (KAUST), Saudi Arabia
dc.contributor.departmentElectrical and Computer Engineering Program
dc.contributor.departmentComputer, Electrical and Mathematical Science and Engineering (CEMSE) Division
dc.identifier.journalIEEE Transactions on Pattern Analysis and Machine Intelligence
dc.eprint.versionPost-print
dc.contributor.institutionSchool of Computer Science and Technology, Beijing Institute of Technology, China
dc.contributor.institutionGaoling School of Artificial Intelligence, Renmin University of China, China
dc.contributor.institutionBeijing Key Laboratory of Big Data Management and Analysis Methods
dc.identifier.pages1-14
kaust.personCarin, Lawrence
refterms.dateFOA2022-11-17T05:59:10Z


Files in this item

Thumbnail
Name:
Differentiable_Hierarchical_Optimal_Transport_for_Robust_Multi-View_Learning.pdf
Size:
2.456Mb
Format:
PDF
Description:
Accepted Manuscript

This item appears in the following Collection(s)

Show simple item record