Robust multi-view clustering algorithm based on sparse consensus graph decomposition(基于稀疏一致图分解的鲁棒多视图聚类算法)

由于数据形式日益复杂,陆续涌现了大量多视图聚类算法。但现有方法存在计算复杂度较高、需要额外的后续处理步骤、构造的相似图非最优等缺点。基于此,首先提出一种基于稀疏一致图分解的单视图聚类算法,然后将其扩展为多视图聚类算法,考虑不同视图对最终结果的贡献不同,对每个视图分配适当的权重,同时利用L2.1范数,得到性能更优的一致图,在一致图基础上学习非负表示矩阵,经交替迭代得到聚类结果。最后在多个数据集上进行比较实验,验证了该算法的有效性。...

Full description

Bibliographic Details
Main Author: 耿莉(GENG Li)
Format: Article
Language:zho
Published: Zhejiang University Press 2023-09-01
Series:Zhejiang Daxue xuebao. Lixue ban
Online Access:https://doi.org/10.3785/j.issn.1008-9497.2023.05.008
_version_ 1797232935592525824
author 耿莉(GENG Li)
耿莉(GENG Li)
author_facet 耿莉(GENG Li)
耿莉(GENG Li)
author_sort 耿莉(GENG Li)
collection DOAJ
description 由于数据形式日益复杂,陆续涌现了大量多视图聚类算法。但现有方法存在计算复杂度较高、需要额外的后续处理步骤、构造的相似图非最优等缺点。基于此,首先提出一种基于稀疏一致图分解的单视图聚类算法,然后将其扩展为多视图聚类算法,考虑不同视图对最终结果的贡献不同,对每个视图分配适当的权重,同时利用L2.1范数,得到性能更优的一致图,在一致图基础上学习非负表示矩阵,经交替迭代得到聚类结果。最后在多个数据集上进行比较实验,验证了该算法的有效性。
first_indexed 2024-04-24T16:08:11Z
format Article
id doaj.art-c74bd0d62bcc468697528b8a493124e5
institution Directory Open Access Journal
issn 1008-9497
language zho
last_indexed 2024-04-24T16:08:11Z
publishDate 2023-09-01
publisher Zhejiang University Press
record_format Article
series Zhejiang Daxue xuebao. Lixue ban
spelling doaj.art-c74bd0d62bcc468697528b8a493124e52024-04-01T01:52:11ZzhoZhejiang University PressZhejiang Daxue xuebao. Lixue ban1008-94972023-09-0150556957910.3785/j.issn.1008-9497.2023.05.008Robust multi-view clustering algorithm based on sparse consensus graph decomposition(基于稀疏一致图分解的鲁棒多视图聚类算法)耿莉(GENG Li)0https://orcid.org/0000-0002-8051-5236耿莉(GENG Li)1https://orcid.org/0000-0001-8603-9704School of Science, Chang'an University, Xi'an 710064, China(长安大学 理学院,陕西 西安 710064)School of Science, Chang'an University, Xi'an 710064, China(长安大学 理学院,陕西 西安 710064)由于数据形式日益复杂,陆续涌现了大量多视图聚类算法。但现有方法存在计算复杂度较高、需要额外的后续处理步骤、构造的相似图非最优等缺点。基于此,首先提出一种基于稀疏一致图分解的单视图聚类算法,然后将其扩展为多视图聚类算法,考虑不同视图对最终结果的贡献不同,对每个视图分配适当的权重,同时利用L2.1范数,得到性能更优的一致图,在一致图基础上学习非负表示矩阵,经交替迭代得到聚类结果。最后在多个数据集上进行比较实验,验证了该算法的有效性。https://doi.org/10.3785/j.issn.1008-9497.2023.05.008
spellingShingle 耿莉(GENG Li)
耿莉(GENG Li)
Robust multi-view clustering algorithm based on sparse consensus graph decomposition(基于稀疏一致图分解的鲁棒多视图聚类算法)
Zhejiang Daxue xuebao. Lixue ban
title Robust multi-view clustering algorithm based on sparse consensus graph decomposition(基于稀疏一致图分解的鲁棒多视图聚类算法)
title_full Robust multi-view clustering algorithm based on sparse consensus graph decomposition(基于稀疏一致图分解的鲁棒多视图聚类算法)
title_fullStr Robust multi-view clustering algorithm based on sparse consensus graph decomposition(基于稀疏一致图分解的鲁棒多视图聚类算法)
title_full_unstemmed Robust multi-view clustering algorithm based on sparse consensus graph decomposition(基于稀疏一致图分解的鲁棒多视图聚类算法)
title_short Robust multi-view clustering algorithm based on sparse consensus graph decomposition(基于稀疏一致图分解的鲁棒多视图聚类算法)
title_sort robust multi view clustering algorithm based on sparse consensus graph decomposition 基于稀疏一致图分解的鲁棒多视图聚类算法
url https://doi.org/10.3785/j.issn.1008-9497.2023.05.008
work_keys_str_mv AT gěnglìgengli robustmultiviewclusteringalgorithmbasedonsparseconsensusgraphdecompositionjīyúxīshūyīzhìtúfēnjiědelǔbàngduōshìtújùlèisuànfǎ
AT gěnglìgengli robustmultiviewclusteringalgorithmbasedonsparseconsensusgraphdecompositionjīyúxīshūyīzhìtúfēnjiědelǔbàngduōshìtújùlèisuànfǎ