Low‐rank constrained weighted discriminative regression for multi‐view feature learning

Abstract In recent years, multi‐view learning has attracted much attention in the fields of data mining, knowledge discovery and machine learning, and been widely used in classification, clustering and information retrieval, and so forth. A new supervised feature learning method for multi‐view data,...

Descripción completa

Guardado en:

Detalles Bibliográficos
Autores principales:	Chao Zhang, Huaxiong Li
Formato:	article
Lenguaje:	EN
Publicado:	Wiley 2021
Materias:	Computational linguistics. Natural language processing P98-98.5 Computer software QA76.75-76.765
Acceso en línea:	https://doaj.org/article/e9ee40f0c3d748d09829c315af2ffe59
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

id	oai:doaj.org-article:e9ee40f0c3d748d09829c315af2ffe59
record_format	dspace
spelling	oai:doaj.org-article:e9ee40f0c3d748d09829c315af2ffe592021-11-17T03:12:43ZLow‐rank constrained weighted discriminative regression for multi‐view feature learning2468-232210.1049/cit2.12018https://doaj.org/article/e9ee40f0c3d748d09829c315af2ffe592021-12-01T00:00:00Zhttps://doi.org/10.1049/cit2.12018https://doaj.org/toc/2468-2322Abstract In recent years, multi‐view learning has attracted much attention in the fields of data mining, knowledge discovery and machine learning, and been widely used in classification, clustering and information retrieval, and so forth. A new supervised feature learning method for multi‐view data, called low‐rank constrained weighted discriminative regression (LWDR), is proposed. Different from previous methods handling each view separately, LWDR learns a discriminative projection matrix by fully exploiting the complementary information among all views from a unified perspective. Based on least squares regression model, the high‐dimensional multi‐view data is mapped into a common subspace, in which different views have different weights in projection. The weights are adaptively updated to estimate the roles of all views. To improve the intra‐class similarity of learned features, a low‐rank constraint is designed and imposed on the multi‐view features of each class, which improves the feature discrimination. An iterative optimization algorithm is designed to solve the LWDR model efficiently. Experiments on four popular datasets, including Handwritten, Caltech101, PIE and AwA, demonstrate the effectiveness of the proposed method.Chao ZhangHuaxiong LiWileyarticleComputational linguistics. Natural language processingP98-98.5Computer softwareQA76.75-76.765ENCAAI Transactions on Intelligence Technology, Vol 6, Iss 4, Pp 471-479 (2021)
institution	DOAJ
collection	DOAJ
language	EN
topic	Computational linguistics. Natural language processing P98-98.5 Computer software QA76.75-76.765
spellingShingle	Computational linguistics. Natural language processing P98-98.5 Computer software QA76.75-76.765 Chao Zhang Huaxiong Li Low‐rank constrained weighted discriminative regression for multi‐view feature learning
description	Abstract In recent years, multi‐view learning has attracted much attention in the fields of data mining, knowledge discovery and machine learning, and been widely used in classification, clustering and information retrieval, and so forth. A new supervised feature learning method for multi‐view data, called low‐rank constrained weighted discriminative regression (LWDR), is proposed. Different from previous methods handling each view separately, LWDR learns a discriminative projection matrix by fully exploiting the complementary information among all views from a unified perspective. Based on least squares regression model, the high‐dimensional multi‐view data is mapped into a common subspace, in which different views have different weights in projection. The weights are adaptively updated to estimate the roles of all views. To improve the intra‐class similarity of learned features, a low‐rank constraint is designed and imposed on the multi‐view features of each class, which improves the feature discrimination. An iterative optimization algorithm is designed to solve the LWDR model efficiently. Experiments on four popular datasets, including Handwritten, Caltech101, PIE and AwA, demonstrate the effectiveness of the proposed method.
format	article
author	Chao Zhang Huaxiong Li
author_facet	Chao Zhang Huaxiong Li
author_sort	Chao Zhang
title	Low‐rank constrained weighted discriminative regression for multi‐view feature learning
title_short	Low‐rank constrained weighted discriminative regression for multi‐view feature learning
title_full	Low‐rank constrained weighted discriminative regression for multi‐view feature learning
title_fullStr	Low‐rank constrained weighted discriminative regression for multi‐view feature learning
title_full_unstemmed	Low‐rank constrained weighted discriminative regression for multi‐view feature learning
title_sort	low‐rank constrained weighted discriminative regression for multi‐view feature learning
publisher	Wiley
publishDate	2021
url	https://doaj.org/article/e9ee40f0c3d748d09829c315af2ffe59
work_keys_str_mv	AT chaozhang lowrankconstrainedweighteddiscriminativeregressionformultiviewfeaturelearning AT huaxiongli lowrankconstrainedweighteddiscriminativeregressionformultiviewfeaturelearning
_version_	1718426023151796224

Low‐rank constrained weighted discriminative regression for multi‐view feature learning

Ejemplares similares