File Download
There are no files associated with this item.
Links for fulltext
(May Require Subscription)
- Publisher Website: 10.1109/TSP.2020.3008050
- Scopus: eid_2-s2.0-85089286716
- WOS: WOS:000554882400003
- Find via
Supplementary
- Citations:
- Appears in Collections:
Article: Learning Latent Features with Pairwise Penalties in Low-Rank Matrix Completion
Title | Learning Latent Features with Pairwise Penalties in Low-Rank Matrix Completion |
---|---|
Authors | |
Keywords | matrix factorization pairwise learning nonconvex pairwise penalty |
Issue Date | 2020 |
Publisher | IEEE. The Journal's web site is located at http://ieeexplore.ieee.org/xpl/RecentIssue.jsp?punumber=78 |
Citation | IEEE Transactions on Signal Processing, 2020, Epub 2020-07-08, p. 1-1 How to Cite? |
Abstract | Low-rank matrix completion has achieved great success in many real-world data applications. A matrix factorization model that learns latent features is usually employed and, to improve prediction performance, the similarities between latent variables can be exploited by pairwise learning using the graph regularized matrix factorization (GRMF) method. However, existing GRMF approaches often use the squared loss to measure the pairwise differences, which may be overly influenced by dissimilar pairs and lead to inferior prediction. To fully empower pairwise learning for matrix completion, we propose a general optimization framework that allows a rich class of (non-)convex pairwise penalty functions. A new and efficient algorithm is developed to solve the proposed optimization problem, with a theoretical convergence guarantee under mild assumptions. In an important situation where the latent variables form a small number of subgroups, its statistical guarantee is also fully considered. In particular, we theoretically characterize the performance of the complexity-regularized maximum likelihood estimator, as a special case of our framework, which is shown to have smaller errors when compared to the standard matrix completion framework without pairwise penalties. We conduct extensive experiments on both synthetic and real datasets to demonstrate the superior performance of this general framework. |
Persistent Identifier | http://hdl.handle.net/10722/284255 |
ISSN | 2023 Impact Factor: 4.6 2023 SCImago Journal Rankings: 2.520 |
ISI Accession Number ID |
DC Field | Value | Language |
---|---|---|
dc.contributor.author | Ji, K | - |
dc.contributor.author | Tan, J | - |
dc.contributor.author | Xu, J | - |
dc.contributor.author | Chi, Y | - |
dc.date.accessioned | 2020-07-20T05:57:17Z | - |
dc.date.available | 2020-07-20T05:57:17Z | - |
dc.date.issued | 2020 | - |
dc.identifier.citation | IEEE Transactions on Signal Processing, 2020, Epub 2020-07-08, p. 1-1 | - |
dc.identifier.issn | 1053-587X | - |
dc.identifier.uri | http://hdl.handle.net/10722/284255 | - |
dc.description.abstract | Low-rank matrix completion has achieved great success in many real-world data applications. A matrix factorization model that learns latent features is usually employed and, to improve prediction performance, the similarities between latent variables can be exploited by pairwise learning using the graph regularized matrix factorization (GRMF) method. However, existing GRMF approaches often use the squared loss to measure the pairwise differences, which may be overly influenced by dissimilar pairs and lead to inferior prediction. To fully empower pairwise learning for matrix completion, we propose a general optimization framework that allows a rich class of (non-)convex pairwise penalty functions. A new and efficient algorithm is developed to solve the proposed optimization problem, with a theoretical convergence guarantee under mild assumptions. In an important situation where the latent variables form a small number of subgroups, its statistical guarantee is also fully considered. In particular, we theoretically characterize the performance of the complexity-regularized maximum likelihood estimator, as a special case of our framework, which is shown to have smaller errors when compared to the standard matrix completion framework without pairwise penalties. We conduct extensive experiments on both synthetic and real datasets to demonstrate the superior performance of this general framework. | - |
dc.language | eng | - |
dc.publisher | IEEE. The Journal's web site is located at http://ieeexplore.ieee.org/xpl/RecentIssue.jsp?punumber=78 | - |
dc.relation.ispartof | IEEE Transactions on Signal Processing | - |
dc.rights | IEEE Transactions on Signal Processing. Copyright © IEEE. | - |
dc.rights | ©2020 IEEE. Personal use of this material is permitted. Permission from IEEE must be obtained for all other uses, in any current or future media, 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 component of this work in other works. | - |
dc.subject | matrix factorization | - |
dc.subject | pairwise learning | - |
dc.subject | nonconvex pairwise penalty | - |
dc.title | Learning Latent Features with Pairwise Penalties in Low-Rank Matrix Completion | - |
dc.type | Article | - |
dc.identifier.email | Xu, J: xujf@hku.hk | - |
dc.identifier.authority | Xu, J=rp02086 | - |
dc.description.nature | link_to_subscribed_fulltext | - |
dc.identifier.doi | 10.1109/TSP.2020.3008050 | - |
dc.identifier.scopus | eid_2-s2.0-85089286716 | - |
dc.identifier.hkuros | 311190 | - |
dc.identifier.volume | Epub 2020-07-08 | - |
dc.identifier.spage | 1 | - |
dc.identifier.epage | 1 | - |
dc.identifier.isi | WOS:000554882400003 | - |
dc.publisher.place | United States | - |
dc.identifier.issnl | 1053-587X | - |