RMFRASL: Robust Matrix Factorization with Robust Adaptive Structure Learning for Feature Selection
In this paper, we present a novel unsupervised feature selection method termed robust matrix factorization with robust adaptive structure learning (RMFRASL), which can select discriminative features from a large amount of multimedia data to improve the performance of classification and clustering ta...
Main Authors: | , , , , , |
---|---|
Format: | Article |
Language: | English |
Published: |
MDPI AG
2022-12-01
|
Series: | Algorithms |
Subjects: | |
Online Access: | https://www.mdpi.com/1999-4893/16/1/14 |
_version_ | 1797447124085899264 |
---|---|
author | Shumin Lai Longjun Huang Ping Li Zhenzhen Luo Jianzhong Wang Yugen Yi |
author_facet | Shumin Lai Longjun Huang Ping Li Zhenzhen Luo Jianzhong Wang Yugen Yi |
author_sort | Shumin Lai |
collection | DOAJ |
description | In this paper, we present a novel unsupervised feature selection method termed robust matrix factorization with robust adaptive structure learning (RMFRASL), which can select discriminative features from a large amount of multimedia data to improve the performance of classification and clustering tasks. RMFRASL integrates three models (robust matrix factorization, adaptive structure learning, and structure regularization) into a unified framework. More specifically, a robust matrix factorization-based feature selection (RMFFS) model is proposed by introducing an indicator matrix to measure the importance of features, and the <i>L</i><sub>21</sub>-norm is adopted as a metric to enhance the robustness of feature selection. Furthermore, a robust adaptive structure learning (RASL) model based on the self-representation capability of the samples is designed to discover the geometric structure relationships of original data. Lastly, a structure regularization (SR) term is designed on the learned graph structure, which constrains the selected features to preserve the structure information in the selected feature space. To solve the objective function of our proposed RMFRASL, an iterative optimization algorithm is proposed. By comparing our method with some state-of-the-art unsupervised feature selection approaches on several publicly available databases, the advantage of the proposed RMFRASL is demonstrated. |
first_indexed | 2024-03-09T13:50:18Z |
format | Article |
id | doaj.art-9932abe89db14fc5bfd8fe4000c4f8f4 |
institution | Directory Open Access Journal |
issn | 1999-4893 |
language | English |
last_indexed | 2024-03-09T13:50:18Z |
publishDate | 2022-12-01 |
publisher | MDPI AG |
record_format | Article |
series | Algorithms |
spelling | doaj.art-9932abe89db14fc5bfd8fe4000c4f8f42023-11-30T20:51:12ZengMDPI AGAlgorithms1999-48932022-12-011611410.3390/a16010014RMFRASL: Robust Matrix Factorization with Robust Adaptive Structure Learning for Feature SelectionShumin Lai0Longjun Huang1Ping Li2Zhenzhen Luo3Jianzhong Wang4Yugen Yi5School of Software, Jiangxi Normal University, Nanchang 330022, ChinaSchool of Software, Jiangxi Normal University, Nanchang 330022, ChinaSchool of Software, Jiangxi Normal University, Nanchang 330022, ChinaSchool of Software, Jiangxi Normal University, Nanchang 330022, ChinaCollege of Information Science and Technology, Northeast Normal University, Changchun 130117, ChinaSchool of Software, Jiangxi Normal University, Nanchang 330022, ChinaIn this paper, we present a novel unsupervised feature selection method termed robust matrix factorization with robust adaptive structure learning (RMFRASL), which can select discriminative features from a large amount of multimedia data to improve the performance of classification and clustering tasks. RMFRASL integrates three models (robust matrix factorization, adaptive structure learning, and structure regularization) into a unified framework. More specifically, a robust matrix factorization-based feature selection (RMFFS) model is proposed by introducing an indicator matrix to measure the importance of features, and the <i>L</i><sub>21</sub>-norm is adopted as a metric to enhance the robustness of feature selection. Furthermore, a robust adaptive structure learning (RASL) model based on the self-representation capability of the samples is designed to discover the geometric structure relationships of original data. Lastly, a structure regularization (SR) term is designed on the learned graph structure, which constrains the selected features to preserve the structure information in the selected feature space. To solve the objective function of our proposed RMFRASL, an iterative optimization algorithm is proposed. By comparing our method with some state-of-the-art unsupervised feature selection approaches on several publicly available databases, the advantage of the proposed RMFRASL is demonstrated.https://www.mdpi.com/1999-4893/16/1/14feature selectionmatrix factorizationadaptive structure learningstructure regularization |
spellingShingle | Shumin Lai Longjun Huang Ping Li Zhenzhen Luo Jianzhong Wang Yugen Yi RMFRASL: Robust Matrix Factorization with Robust Adaptive Structure Learning for Feature Selection Algorithms feature selection matrix factorization adaptive structure learning structure regularization |
title | RMFRASL: Robust Matrix Factorization with Robust Adaptive Structure Learning for Feature Selection |
title_full | RMFRASL: Robust Matrix Factorization with Robust Adaptive Structure Learning for Feature Selection |
title_fullStr | RMFRASL: Robust Matrix Factorization with Robust Adaptive Structure Learning for Feature Selection |
title_full_unstemmed | RMFRASL: Robust Matrix Factorization with Robust Adaptive Structure Learning for Feature Selection |
title_short | RMFRASL: Robust Matrix Factorization with Robust Adaptive Structure Learning for Feature Selection |
title_sort | rmfrasl robust matrix factorization with robust adaptive structure learning for feature selection |
topic | feature selection matrix factorization adaptive structure learning structure regularization |
url | https://www.mdpi.com/1999-4893/16/1/14 |
work_keys_str_mv | AT shuminlai rmfraslrobustmatrixfactorizationwithrobustadaptivestructurelearningforfeatureselection AT longjunhuang rmfraslrobustmatrixfactorizationwithrobustadaptivestructurelearningforfeatureselection AT pingli rmfraslrobustmatrixfactorizationwithrobustadaptivestructurelearningforfeatureselection AT zhenzhenluo rmfraslrobustmatrixfactorizationwithrobustadaptivestructurelearningforfeatureselection AT jianzhongwang rmfraslrobustmatrixfactorizationwithrobustadaptivestructurelearningforfeatureselection AT yugenyi rmfraslrobustmatrixfactorizationwithrobustadaptivestructurelearningforfeatureselection |