Loading…

Late Fusion Multiple Kernel Clustering With Local Kernel Alignment Maximization

Multi-view clustering, which appropriately integrates information from multiple sources to reveal data's inherent structure, is gaining traction in clustering. Though existing procedures have yielded satisfactory results, we observe that they have neglected the inherent local structure in the b...

Full description

Saved in:
Bibliographic Details
Published in:IEEE transactions on multimedia 2023, Vol.25, p.993-1007
Main Authors: Zhang, Tiejian, Liu, Xinwang, Gong, Lei, Wang, Siwei, Niu, Xin, Shen, Li
Format: Article
Language:English
Subjects:
Citations: Items that this one cites
Items that cite this one
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
cited_by cdi_FETCH-LOGICAL-c291t-52071cddcc07e83bdc88ee7fb02b38f9cea5bf66aa1f23a42e551c45c1804f2e3
cites cdi_FETCH-LOGICAL-c291t-52071cddcc07e83bdc88ee7fb02b38f9cea5bf66aa1f23a42e551c45c1804f2e3
container_end_page 1007
container_issue
container_start_page 993
container_title IEEE transactions on multimedia
container_volume 25
creator Zhang, Tiejian
Liu, Xinwang
Gong, Lei
Wang, Siwei
Niu, Xin
Shen, Li
description Multi-view clustering, which appropriately integrates information from multiple sources to reveal data's inherent structure, is gaining traction in clustering. Though existing procedures have yielded satisfactory results, we observe that they have neglected the inherent local structure in the base kernels. This may cause adverse effects on clustering. To solve the problem, we introduce LF-MKC-LKA, a simple yet effective late fusion multiple kernel clustering with local kernel alignment maximisation approach. In particular, we first determine the nearest k neighbours in the average kernel space for each sample and record the information in the nearest neighbor indicator matrix. Then, the nearest neighbor indicator matrix can be used to generate local structure matrix of each sample. The local kernels of each view may then be generated using the local structure matrix, retaining just the highly confident local similarities for learning the intrinsic global manifold of data. They can also be utilised to keep the block diagonal structure and improve the robustness of the underlying kernels against noise.We input the local kernels of each view into the kernel k-means (KKM) algorithm and get the local base partitions. Finally, we use a three-step iterative optimization approach to maximize the alignment of the consensus partition using base partitions and a regularisation term. As demonstrated, a significant number of trials on 11 multi-kernel benchmark datasets have shown that the proposed LF-MKC-LKA is effective and efficient. A number of experiments are also designed to demonstrate the fast convergence, excellent performance, robustness and low parameter sensitivity of the algorithm. Our code can be find at https://github.com/TiejianZhang/TMM21-LF-MKC-LKA .
doi_str_mv 10.1109/TMM.2021.3136094
format article
fullrecord <record><control><sourceid>proquest_ieee_</sourceid><recordid>TN_cdi_proquest_journals_2785446708</recordid><sourceformat>XML</sourceformat><sourcesystem>PC</sourcesystem><ieee_id>9653838</ieee_id><sourcerecordid>2785446708</sourcerecordid><originalsourceid>FETCH-LOGICAL-c291t-52071cddcc07e83bdc88ee7fb02b38f9cea5bf66aa1f23a42e551c45c1804f2e3</originalsourceid><addsrcrecordid>eNo9kNFLwzAQxoMoOKfvgi8FnzsvadKkj2M4FVv2MvExZNl1ZnTtbFJQ_3ozNuUe7uC-77vjR8gthQmlUDwsq2rCgNFJRrMcCn5GRrTgNAWQ8jzOgkFaMAqX5Mr7LQDlAuSILEoTMJkP3nVtUg1NcPsGk1fsW2ySWTP4gL1rN8m7Cx9J2VnT_C2njdu0O2xDUpkvt3M_JsSMa3JRm8bjzamPydv8cTl7TsvF08tsWqaWFTSk8RtJ7XptLUhU2WptlUKU9QrYKlN1YdGIVZ3nxtCaZYYzFIJaLixVwGuG2ZjcH3P3ffc5oA962w19G09qJpXgPJegogqOKtt33vdY633vdqb_1hT0AZuO2PQBmz5hi5a7o8Uh4r-8yEWmYv0CJ4RpRA</addsrcrecordid><sourcetype>Aggregation Database</sourcetype><iscdi>true</iscdi><recordtype>article</recordtype><pqid>2785446708</pqid></control><display><type>article</type><title>Late Fusion Multiple Kernel Clustering With Local Kernel Alignment Maximization</title><source>IEEE Xplore (Online service)</source><creator>Zhang, Tiejian ; Liu, Xinwang ; Gong, Lei ; Wang, Siwei ; Niu, Xin ; Shen, Li</creator><creatorcontrib>Zhang, Tiejian ; Liu, Xinwang ; Gong, Lei ; Wang, Siwei ; Niu, Xin ; Shen, Li</creatorcontrib><description><![CDATA[Multi-view clustering, which appropriately integrates information from multiple sources to reveal data's inherent structure, is gaining traction in clustering. Though existing procedures have yielded satisfactory results, we observe that they have neglected the inherent local structure in the base kernels. This may cause adverse effects on clustering. To solve the problem, we introduce LF-MKC-LKA, a simple yet effective late fusion multiple kernel clustering with local kernel alignment maximisation approach. In particular, we first determine the nearest <inline-formula><tex-math notation="LaTeX">k</tex-math></inline-formula> neighbours in the average kernel space for each sample and record the information in the nearest neighbor indicator matrix. Then, the nearest neighbor indicator matrix can be used to generate local structure matrix of each sample. The local kernels of each view may then be generated using the local structure matrix, retaining just the highly confident local similarities for learning the intrinsic global manifold of data. They can also be utilised to keep the block diagonal structure and improve the robustness of the underlying kernels against noise.We input the local kernels of each view into the kernel <inline-formula><tex-math notation="LaTeX">k</tex-math></inline-formula>-means (KKM) algorithm and get the local base partitions. Finally, we use a three-step iterative optimization approach to maximize the alignment of the consensus partition using base partitions and a regularisation term. As demonstrated, a significant number of trials on 11 multi-kernel benchmark datasets have shown that the proposed LF-MKC-LKA is effective and efficient. A number of experiments are also designed to demonstrate the fast convergence, excellent performance, robustness and low parameter sensitivity of the algorithm. Our code can be find at https://github.com/TiejianZhang/TMM21-LF-MKC-LKA .]]></description><identifier>ISSN: 1520-9210</identifier><identifier>EISSN: 1941-0077</identifier><identifier>DOI: 10.1109/TMM.2021.3136094</identifier><identifier>CODEN: ITMUF8</identifier><language>eng</language><publisher>Piscataway: IEEE</publisher><subject>Algorithms ; Alignment ; Benchmark testing ; block diagonal structure ; Clustering ; Clustering algorithms ; Iterative methods ; Kernel ; Kernels ; local base partition ; local kernel ; Manifolds ; Maximization ; Multiple kernel clustering ; neighbor ; Optimization ; Parameter sensitivity ; Partitioning algorithms ; Regularization ; Robustness</subject><ispartof>IEEE transactions on multimedia, 2023, Vol.25, p.993-1007</ispartof><rights>Copyright The Institute of Electrical and Electronics Engineers, Inc. (IEEE) 2023</rights><lds50>peer_reviewed</lds50><woscitedreferencessubscribed>false</woscitedreferencessubscribed><citedby>FETCH-LOGICAL-c291t-52071cddcc07e83bdc88ee7fb02b38f9cea5bf66aa1f23a42e551c45c1804f2e3</citedby><cites>FETCH-LOGICAL-c291t-52071cddcc07e83bdc88ee7fb02b38f9cea5bf66aa1f23a42e551c45c1804f2e3</cites><orcidid>0000-0002-9396-7688 ; 0000-0001-9517-262X ; 0000-0002-5230-2241 ; 0000-0001-9066-1475</orcidid></display><links><openurl>$$Topenurl_article</openurl><openurlfulltext>$$Topenurlfull_article</openurlfulltext><thumbnail>$$Tsyndetics_thumb_exl</thumbnail><linktohtml>$$Uhttps://ieeexplore.ieee.org/document/9653838$$EHTML$$P50$$Gieee$$H</linktohtml><link.rule.ids>314,780,784,4024,27923,27924,27925,54796</link.rule.ids></links><search><creatorcontrib>Zhang, Tiejian</creatorcontrib><creatorcontrib>Liu, Xinwang</creatorcontrib><creatorcontrib>Gong, Lei</creatorcontrib><creatorcontrib>Wang, Siwei</creatorcontrib><creatorcontrib>Niu, Xin</creatorcontrib><creatorcontrib>Shen, Li</creatorcontrib><title>Late Fusion Multiple Kernel Clustering With Local Kernel Alignment Maximization</title><title>IEEE transactions on multimedia</title><addtitle>TMM</addtitle><description><![CDATA[Multi-view clustering, which appropriately integrates information from multiple sources to reveal data's inherent structure, is gaining traction in clustering. Though existing procedures have yielded satisfactory results, we observe that they have neglected the inherent local structure in the base kernels. This may cause adverse effects on clustering. To solve the problem, we introduce LF-MKC-LKA, a simple yet effective late fusion multiple kernel clustering with local kernel alignment maximisation approach. In particular, we first determine the nearest <inline-formula><tex-math notation="LaTeX">k</tex-math></inline-formula> neighbours in the average kernel space for each sample and record the information in the nearest neighbor indicator matrix. Then, the nearest neighbor indicator matrix can be used to generate local structure matrix of each sample. The local kernels of each view may then be generated using the local structure matrix, retaining just the highly confident local similarities for learning the intrinsic global manifold of data. They can also be utilised to keep the block diagonal structure and improve the robustness of the underlying kernels against noise.We input the local kernels of each view into the kernel <inline-formula><tex-math notation="LaTeX">k</tex-math></inline-formula>-means (KKM) algorithm and get the local base partitions. Finally, we use a three-step iterative optimization approach to maximize the alignment of the consensus partition using base partitions and a regularisation term. As demonstrated, a significant number of trials on 11 multi-kernel benchmark datasets have shown that the proposed LF-MKC-LKA is effective and efficient. A number of experiments are also designed to demonstrate the fast convergence, excellent performance, robustness and low parameter sensitivity of the algorithm. Our code can be find at https://github.com/TiejianZhang/TMM21-LF-MKC-LKA .]]></description><subject>Algorithms</subject><subject>Alignment</subject><subject>Benchmark testing</subject><subject>block diagonal structure</subject><subject>Clustering</subject><subject>Clustering algorithms</subject><subject>Iterative methods</subject><subject>Kernel</subject><subject>Kernels</subject><subject>local base partition</subject><subject>local kernel</subject><subject>Manifolds</subject><subject>Maximization</subject><subject>Multiple kernel clustering</subject><subject>neighbor</subject><subject>Optimization</subject><subject>Parameter sensitivity</subject><subject>Partitioning algorithms</subject><subject>Regularization</subject><subject>Robustness</subject><issn>1520-9210</issn><issn>1941-0077</issn><fulltext>true</fulltext><rsrctype>article</rsrctype><creationdate>2023</creationdate><recordtype>article</recordtype><recordid>eNo9kNFLwzAQxoMoOKfvgi8FnzsvadKkj2M4FVv2MvExZNl1ZnTtbFJQ_3ozNuUe7uC-77vjR8gthQmlUDwsq2rCgNFJRrMcCn5GRrTgNAWQ8jzOgkFaMAqX5Mr7LQDlAuSILEoTMJkP3nVtUg1NcPsGk1fsW2ySWTP4gL1rN8m7Cx9J2VnT_C2njdu0O2xDUpkvt3M_JsSMa3JRm8bjzamPydv8cTl7TsvF08tsWqaWFTSk8RtJ7XptLUhU2WptlUKU9QrYKlN1YdGIVZ3nxtCaZYYzFIJaLixVwGuG2ZjcH3P3ffc5oA962w19G09qJpXgPJegogqOKtt33vdY633vdqb_1hT0AZuO2PQBmz5hi5a7o8Uh4r-8yEWmYv0CJ4RpRA</recordid><startdate>2023</startdate><enddate>2023</enddate><creator>Zhang, Tiejian</creator><creator>Liu, Xinwang</creator><creator>Gong, Lei</creator><creator>Wang, Siwei</creator><creator>Niu, Xin</creator><creator>Shen, Li</creator><general>IEEE</general><general>The Institute of Electrical and Electronics Engineers, Inc. (IEEE)</general><scope>97E</scope><scope>RIA</scope><scope>RIE</scope><scope>AAYXX</scope><scope>CITATION</scope><scope>7SC</scope><scope>7SP</scope><scope>8FD</scope><scope>JQ2</scope><scope>L7M</scope><scope>L~C</scope><scope>L~D</scope><orcidid>https://orcid.org/0000-0002-9396-7688</orcidid><orcidid>https://orcid.org/0000-0001-9517-262X</orcidid><orcidid>https://orcid.org/0000-0002-5230-2241</orcidid><orcidid>https://orcid.org/0000-0001-9066-1475</orcidid></search><sort><creationdate>2023</creationdate><title>Late Fusion Multiple Kernel Clustering With Local Kernel Alignment Maximization</title><author>Zhang, Tiejian ; Liu, Xinwang ; Gong, Lei ; Wang, Siwei ; Niu, Xin ; Shen, Li</author></sort><facets><frbrtype>5</frbrtype><frbrgroupid>cdi_FETCH-LOGICAL-c291t-52071cddcc07e83bdc88ee7fb02b38f9cea5bf66aa1f23a42e551c45c1804f2e3</frbrgroupid><rsrctype>articles</rsrctype><prefilter>articles</prefilter><language>eng</language><creationdate>2023</creationdate><topic>Algorithms</topic><topic>Alignment</topic><topic>Benchmark testing</topic><topic>block diagonal structure</topic><topic>Clustering</topic><topic>Clustering algorithms</topic><topic>Iterative methods</topic><topic>Kernel</topic><topic>Kernels</topic><topic>local base partition</topic><topic>local kernel</topic><topic>Manifolds</topic><topic>Maximization</topic><topic>Multiple kernel clustering</topic><topic>neighbor</topic><topic>Optimization</topic><topic>Parameter sensitivity</topic><topic>Partitioning algorithms</topic><topic>Regularization</topic><topic>Robustness</topic><toplevel>peer_reviewed</toplevel><toplevel>online_resources</toplevel><creatorcontrib>Zhang, Tiejian</creatorcontrib><creatorcontrib>Liu, Xinwang</creatorcontrib><creatorcontrib>Gong, Lei</creatorcontrib><creatorcontrib>Wang, Siwei</creatorcontrib><creatorcontrib>Niu, Xin</creatorcontrib><creatorcontrib>Shen, Li</creatorcontrib><collection>IEEE All-Society Periodicals Package (ASPP) 2005-present</collection><collection>IEEE All-Society Periodicals Package (ASPP) 1998–Present</collection><collection>IEEE Electronic Library Online</collection><collection>CrossRef</collection><collection>Computer and Information Systems Abstracts</collection><collection>Electronics &amp; Communications Abstracts</collection><collection>Technology Research Database</collection><collection>ProQuest Computer Science Collection</collection><collection>Advanced Technologies Database with Aerospace</collection><collection>Computer and Information Systems Abstracts – Academic</collection><collection>Computer and Information Systems Abstracts Professional</collection><jtitle>IEEE transactions on multimedia</jtitle></facets><delivery><delcategory>Remote Search Resource</delcategory><fulltext>fulltext</fulltext></delivery><addata><au>Zhang, Tiejian</au><au>Liu, Xinwang</au><au>Gong, Lei</au><au>Wang, Siwei</au><au>Niu, Xin</au><au>Shen, Li</au><format>journal</format><genre>article</genre><ristype>JOUR</ristype><atitle>Late Fusion Multiple Kernel Clustering With Local Kernel Alignment Maximization</atitle><jtitle>IEEE transactions on multimedia</jtitle><stitle>TMM</stitle><date>2023</date><risdate>2023</risdate><volume>25</volume><spage>993</spage><epage>1007</epage><pages>993-1007</pages><issn>1520-9210</issn><eissn>1941-0077</eissn><coden>ITMUF8</coden><abstract><![CDATA[Multi-view clustering, which appropriately integrates information from multiple sources to reveal data's inherent structure, is gaining traction in clustering. Though existing procedures have yielded satisfactory results, we observe that they have neglected the inherent local structure in the base kernels. This may cause adverse effects on clustering. To solve the problem, we introduce LF-MKC-LKA, a simple yet effective late fusion multiple kernel clustering with local kernel alignment maximisation approach. In particular, we first determine the nearest <inline-formula><tex-math notation="LaTeX">k</tex-math></inline-formula> neighbours in the average kernel space for each sample and record the information in the nearest neighbor indicator matrix. Then, the nearest neighbor indicator matrix can be used to generate local structure matrix of each sample. The local kernels of each view may then be generated using the local structure matrix, retaining just the highly confident local similarities for learning the intrinsic global manifold of data. They can also be utilised to keep the block diagonal structure and improve the robustness of the underlying kernels against noise.We input the local kernels of each view into the kernel <inline-formula><tex-math notation="LaTeX">k</tex-math></inline-formula>-means (KKM) algorithm and get the local base partitions. Finally, we use a three-step iterative optimization approach to maximize the alignment of the consensus partition using base partitions and a regularisation term. As demonstrated, a significant number of trials on 11 multi-kernel benchmark datasets have shown that the proposed LF-MKC-LKA is effective and efficient. A number of experiments are also designed to demonstrate the fast convergence, excellent performance, robustness and low parameter sensitivity of the algorithm. Our code can be find at https://github.com/TiejianZhang/TMM21-LF-MKC-LKA .]]></abstract><cop>Piscataway</cop><pub>IEEE</pub><doi>10.1109/TMM.2021.3136094</doi><tpages>15</tpages><orcidid>https://orcid.org/0000-0002-9396-7688</orcidid><orcidid>https://orcid.org/0000-0001-9517-262X</orcidid><orcidid>https://orcid.org/0000-0002-5230-2241</orcidid><orcidid>https://orcid.org/0000-0001-9066-1475</orcidid></addata></record>
fulltext fulltext
identifier ISSN: 1520-9210
ispartof IEEE transactions on multimedia, 2023, Vol.25, p.993-1007
issn 1520-9210
1941-0077
language eng
recordid cdi_proquest_journals_2785446708
source IEEE Xplore (Online service)
subjects Algorithms
Alignment
Benchmark testing
block diagonal structure
Clustering
Clustering algorithms
Iterative methods
Kernel
Kernels
local base partition
local kernel
Manifolds
Maximization
Multiple kernel clustering
neighbor
Optimization
Parameter sensitivity
Partitioning algorithms
Regularization
Robustness
title Late Fusion Multiple Kernel Clustering With Local Kernel Alignment Maximization
url http://sfxeu10.hosted.exlibrisgroup.com/loughborough?ctx_ver=Z39.88-2004&ctx_enc=info:ofi/enc:UTF-8&ctx_tim=2024-12-25T09%3A47%3A11IST&url_ver=Z39.88-2004&url_ctx_fmt=infofi/fmt:kev:mtx:ctx&rfr_id=info:sid/primo.exlibrisgroup.com:primo3-Article-proquest_ieee_&rft_val_fmt=info:ofi/fmt:kev:mtx:journal&rft.genre=article&rft.atitle=Late%20Fusion%20Multiple%20Kernel%20Clustering%20With%20Local%20Kernel%20Alignment%20Maximization&rft.jtitle=IEEE%20transactions%20on%20multimedia&rft.au=Zhang,%20Tiejian&rft.date=2023&rft.volume=25&rft.spage=993&rft.epage=1007&rft.pages=993-1007&rft.issn=1520-9210&rft.eissn=1941-0077&rft.coden=ITMUF8&rft_id=info:doi/10.1109/TMM.2021.3136094&rft_dat=%3Cproquest_ieee_%3E2785446708%3C/proquest_ieee_%3E%3Cgrp_id%3Ecdi_FETCH-LOGICAL-c291t-52071cddcc07e83bdc88ee7fb02b38f9cea5bf66aa1f23a42e551c45c1804f2e3%3C/grp_id%3E%3Coa%3E%3C/oa%3E%3Curl%3E%3C/url%3E&rft_id=info:oai/&rft_pqid=2785446708&rft_id=info:pmid/&rft_ieee_id=9653838&rfr_iscdi=true