Multi-order attribute network representation learning via constructing hierarchical graphs
Network representation learning (NRL) is widely used for such tasks as link prediction, node classification in network analysis. For NRL, it is a challenge in effectively fusing structural features and attribute information. To address the problem, this paper proposes a multi-order attribute network...
Gespeichert in:
| Veröffentlicht in: | International journal of machine learning and cybernetics 2024-06, Vol.15 (6), p.2095-2110 |
|---|---|
| Hauptverfasser: | , , , |
| Format: | Artikel |
| Sprache: | eng |
| Schlagworte: | |
| Online-Zugang: | Volltext |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| container_end_page | 2110 |
|---|---|
| container_issue | 6 |
| container_start_page | 2095 |
| container_title | International journal of machine learning and cybernetics |
| container_volume | 15 |
| creator | Zhou, Mingqiang Han, Qizhi Liu, Dan Wu, Quanwang |
| description | Network representation learning (NRL) is widely used for such tasks as link prediction, node classification in network analysis. For NRL, it is a challenge in effectively fusing structural features and attribute information. To address the problem, this paper proposes a multi-order attribute network representation learning model via constructing hierarchical graphs (Multi-NRL). Firstly, the model constructs a series of hierarchical graphs on the original network through structure merging and attribute merging, which contain multi-order structural feature and attribute information from detailed to sketchy. Then, it performs hierarchical network representation on these graphs. Finally, it gains the final network representation through concatenating of the hierarchical network representation. Experimental results show Multi-NRL outperforms the best baseline by up-to 9.6% improvement in link prediction, and 13.9% in node classification with six real-world networks, which demonstrates the effectiveness of our model. |
| doi_str_mv | 10.1007/s13042-023-02018-x |
| format | Article |
| fullrecord | <record><control><sourceid>proquest_cross</sourceid><recordid>TN_cdi_proquest_journals_3059398202</recordid><sourceformat>XML</sourceformat><sourcesystem>PC</sourcesystem><sourcerecordid>3059398202</sourcerecordid><originalsourceid>FETCH-LOGICAL-c298t-3b921040cd2c9f745c22d667d964ea22b494e05bbfb6159cf0934727270b31b23</originalsourceid><addsrcrecordid>eNqFkE1LAzEQhhdRsNT-AU8LnlcnyX7lKMUvqHhREC8hyWbb1DW7TrJa_72pFb1phjDD8LzvwJskxwROCUB15gmDnGZAWfxA6myzl0xIXdZZDfXj_s9ckcNk5v0a4iuBMaCT5Ol27ILNemwMpjIEtGoMJnUmvPf4nKIZ0Hjjggy2d2lnJDrrlumblanunQ846rBdrKxBiXpltezSJcph5Y-Sg1Z23sy--zR5uLy4n19ni7urm_n5ItOU1yFjilMCOeiGat5WeaEpbcqyaniZG0mpynluoFCqVSUpuG6Bs7yisUAxoiibJic73wH719H4INb9iC6eFAwKznhN4V-KAC9oHSm6ozT23qNpxYD2ReKHICC2YYtd2CI6iq-wxSaK2E7kI-yWBn-t_1B9AvZegoM</addsrcrecordid><sourcetype>Aggregation Database</sourcetype><iscdi>true</iscdi><recordtype>article</recordtype><pqid>3059109528</pqid></control><display><type>article</type><title>Multi-order attribute network representation learning via constructing hierarchical graphs</title><source>SpringerLink Journals - AutoHoldings</source><creator>Zhou, Mingqiang ; Han, Qizhi ; Liu, Dan ; Wu, Quanwang</creator><creatorcontrib>Zhou, Mingqiang ; Han, Qizhi ; Liu, Dan ; Wu, Quanwang</creatorcontrib><description>Network representation learning (NRL) is widely used for such tasks as link prediction, node classification in network analysis. For NRL, it is a challenge in effectively fusing structural features and attribute information. To address the problem, this paper proposes a multi-order attribute network representation learning model via constructing hierarchical graphs (Multi-NRL). Firstly, the model constructs a series of hierarchical graphs on the original network through structure merging and attribute merging, which contain multi-order structural feature and attribute information from detailed to sketchy. Then, it performs hierarchical network representation on these graphs. Finally, it gains the final network representation through concatenating of the hierarchical network representation. Experimental results show Multi-NRL outperforms the best baseline by up-to 9.6% improvement in link prediction, and 13.9% in node classification with six real-world networks, which demonstrates the effectiveness of our model.</description><identifier>ISSN: 1868-8071</identifier><identifier>EISSN: 1868-808X</identifier><identifier>DOI: 10.1007/s13042-023-02018-x</identifier><language>eng</language><publisher>Berlin/Heidelberg: Springer Berlin Heidelberg</publisher><subject>Artificial Intelligence ; Classification ; Complex Systems ; Computational Intelligence ; Control ; Engineering ; Graphical representations ; Graphs ; Learning ; Mechatronics ; Network analysis ; Original Article ; Pattern Recognition ; Robotics ; Social networks ; Systems Biology</subject><ispartof>International journal of machine learning and cybernetics, 2024-06, Vol.15 (6), p.2095-2110</ispartof><rights>The Author(s), under exclusive licence to Springer-Verlag GmbH Germany, part of Springer Nature 2023. Springer Nature or its licensor (e.g. a society or other partner) holds exclusive rights to this article under a publishing agreement with the author(s) or other rightsholder(s); author self-archiving of the accepted manuscript version of this article is solely governed by the terms of such publishing agreement and applicable law.</rights><lds50>peer_reviewed</lds50><woscitedreferencessubscribed>false</woscitedreferencessubscribed><cites>FETCH-LOGICAL-c298t-3b921040cd2c9f745c22d667d964ea22b494e05bbfb6159cf0934727270b31b23</cites><orcidid>0000-0003-3217-9503</orcidid></display><links><openurl>$$Topenurl_article</openurl><openurlfulltext>$$Topenurlfull_article</openurlfulltext><thumbnail>$$Tsyndetics_thumb_exl</thumbnail><linktopdf>$$Uhttps://link.springer.com/content/pdf/10.1007/s13042-023-02018-x$$EPDF$$P50$$Gspringer$$H</linktopdf><linktohtml>$$Uhttps://link.springer.com/10.1007/s13042-023-02018-x$$EHTML$$P50$$Gspringer$$H</linktohtml><link.rule.ids>314,776,780,27901,27902,41464,42533,51294</link.rule.ids></links><search><creatorcontrib>Zhou, Mingqiang</creatorcontrib><creatorcontrib>Han, Qizhi</creatorcontrib><creatorcontrib>Liu, Dan</creatorcontrib><creatorcontrib>Wu, Quanwang</creatorcontrib><title>Multi-order attribute network representation learning via constructing hierarchical graphs</title><title>International journal of machine learning and cybernetics</title><addtitle>Int. J. Mach. Learn. & Cyber</addtitle><description>Network representation learning (NRL) is widely used for such tasks as link prediction, node classification in network analysis. For NRL, it is a challenge in effectively fusing structural features and attribute information. To address the problem, this paper proposes a multi-order attribute network representation learning model via constructing hierarchical graphs (Multi-NRL). Firstly, the model constructs a series of hierarchical graphs on the original network through structure merging and attribute merging, which contain multi-order structural feature and attribute information from detailed to sketchy. Then, it performs hierarchical network representation on these graphs. Finally, it gains the final network representation through concatenating of the hierarchical network representation. Experimental results show Multi-NRL outperforms the best baseline by up-to 9.6% improvement in link prediction, and 13.9% in node classification with six real-world networks, which demonstrates the effectiveness of our model.</description><subject>Artificial Intelligence</subject><subject>Classification</subject><subject>Complex Systems</subject><subject>Computational Intelligence</subject><subject>Control</subject><subject>Engineering</subject><subject>Graphical representations</subject><subject>Graphs</subject><subject>Learning</subject><subject>Mechatronics</subject><subject>Network analysis</subject><subject>Original Article</subject><subject>Pattern Recognition</subject><subject>Robotics</subject><subject>Social networks</subject><subject>Systems Biology</subject><issn>1868-8071</issn><issn>1868-808X</issn><fulltext>true</fulltext><rsrctype>article</rsrctype><creationdate>2024</creationdate><recordtype>article</recordtype><recordid>eNqFkE1LAzEQhhdRsNT-AU8LnlcnyX7lKMUvqHhREC8hyWbb1DW7TrJa_72pFb1phjDD8LzvwJskxwROCUB15gmDnGZAWfxA6myzl0xIXdZZDfXj_s9ckcNk5v0a4iuBMaCT5Ol27ILNemwMpjIEtGoMJnUmvPf4nKIZ0Hjjggy2d2lnJDrrlumblanunQ846rBdrKxBiXpltezSJcph5Y-Sg1Z23sy--zR5uLy4n19ni7urm_n5ItOU1yFjilMCOeiGat5WeaEpbcqyaniZG0mpynluoFCqVSUpuG6Bs7yisUAxoiibJic73wH719H4INb9iC6eFAwKznhN4V-KAC9oHSm6ozT23qNpxYD2ReKHICC2YYtd2CI6iq-wxSaK2E7kI-yWBn-t_1B9AvZegoM</recordid><startdate>20240601</startdate><enddate>20240601</enddate><creator>Zhou, Mingqiang</creator><creator>Han, Qizhi</creator><creator>Liu, Dan</creator><creator>Wu, Quanwang</creator><general>Springer Berlin Heidelberg</general><general>Springer Nature B.V</general><scope>AAYXX</scope><scope>CITATION</scope><scope>JQ2</scope><orcidid>https://orcid.org/0000-0003-3217-9503</orcidid></search><sort><creationdate>20240601</creationdate><title>Multi-order attribute network representation learning via constructing hierarchical graphs</title><author>Zhou, Mingqiang ; Han, Qizhi ; Liu, Dan ; Wu, Quanwang</author></sort><facets><frbrtype>5</frbrtype><frbrgroupid>cdi_FETCH-LOGICAL-c298t-3b921040cd2c9f745c22d667d964ea22b494e05bbfb6159cf0934727270b31b23</frbrgroupid><rsrctype>articles</rsrctype><prefilter>articles</prefilter><language>eng</language><creationdate>2024</creationdate><topic>Artificial Intelligence</topic><topic>Classification</topic><topic>Complex Systems</topic><topic>Computational Intelligence</topic><topic>Control</topic><topic>Engineering</topic><topic>Graphical representations</topic><topic>Graphs</topic><topic>Learning</topic><topic>Mechatronics</topic><topic>Network analysis</topic><topic>Original Article</topic><topic>Pattern Recognition</topic><topic>Robotics</topic><topic>Social networks</topic><topic>Systems Biology</topic><toplevel>peer_reviewed</toplevel><toplevel>online_resources</toplevel><creatorcontrib>Zhou, Mingqiang</creatorcontrib><creatorcontrib>Han, Qizhi</creatorcontrib><creatorcontrib>Liu, Dan</creatorcontrib><creatorcontrib>Wu, Quanwang</creatorcontrib><collection>CrossRef</collection><collection>ProQuest Computer Science Collection</collection><jtitle>International journal of machine learning and cybernetics</jtitle></facets><delivery><delcategory>Remote Search Resource</delcategory><fulltext>fulltext</fulltext></delivery><addata><au>Zhou, Mingqiang</au><au>Han, Qizhi</au><au>Liu, Dan</au><au>Wu, Quanwang</au><format>journal</format><genre>article</genre><ristype>JOUR</ristype><atitle>Multi-order attribute network representation learning via constructing hierarchical graphs</atitle><jtitle>International journal of machine learning and cybernetics</jtitle><stitle>Int. J. Mach. Learn. & Cyber</stitle><date>2024-06-01</date><risdate>2024</risdate><volume>15</volume><issue>6</issue><spage>2095</spage><epage>2110</epage><pages>2095-2110</pages><issn>1868-8071</issn><eissn>1868-808X</eissn><abstract>Network representation learning (NRL) is widely used for such tasks as link prediction, node classification in network analysis. For NRL, it is a challenge in effectively fusing structural features and attribute information. To address the problem, this paper proposes a multi-order attribute network representation learning model via constructing hierarchical graphs (Multi-NRL). Firstly, the model constructs a series of hierarchical graphs on the original network through structure merging and attribute merging, which contain multi-order structural feature and attribute information from detailed to sketchy. Then, it performs hierarchical network representation on these graphs. Finally, it gains the final network representation through concatenating of the hierarchical network representation. Experimental results show Multi-NRL outperforms the best baseline by up-to 9.6% improvement in link prediction, and 13.9% in node classification with six real-world networks, which demonstrates the effectiveness of our model.</abstract><cop>Berlin/Heidelberg</cop><pub>Springer Berlin Heidelberg</pub><doi>10.1007/s13042-023-02018-x</doi><tpages>16</tpages><orcidid>https://orcid.org/0000-0003-3217-9503</orcidid></addata></record> |
| fulltext | fulltext |
| identifier | ISSN: 1868-8071 |
| ispartof | International journal of machine learning and cybernetics, 2024-06, Vol.15 (6), p.2095-2110 |
| issn | 1868-8071 1868-808X |
| language | eng |
| recordid | cdi_proquest_journals_3059398202 |
| source | SpringerLink Journals - AutoHoldings |
| subjects | Artificial Intelligence Classification Complex Systems Computational Intelligence Control Engineering Graphical representations Graphs Learning Mechatronics Network analysis Original Article Pattern Recognition Robotics Social networks Systems Biology |
| title | Multi-order attribute network representation learning via constructing hierarchical graphs |
| url | https://sfx.bib-bvb.de/sfx_tum?ctx_ver=Z39.88-2004&ctx_enc=info:ofi/enc:UTF-8&ctx_tim=2025-02-02T23%3A22%3A23IST&url_ver=Z39.88-2004&url_ctx_fmt=infofi/fmt:kev:mtx:ctx&rfr_id=info:sid/primo.exlibrisgroup.com:primo3-Article-proquest_cross&rft_val_fmt=info:ofi/fmt:kev:mtx:journal&rft.genre=article&rft.atitle=Multi-order%20attribute%20network%20representation%20learning%20via%20constructing%20hierarchical%20graphs&rft.jtitle=International%20journal%20of%20machine%20learning%20and%20cybernetics&rft.au=Zhou,%20Mingqiang&rft.date=2024-06-01&rft.volume=15&rft.issue=6&rft.spage=2095&rft.epage=2110&rft.pages=2095-2110&rft.issn=1868-8071&rft.eissn=1868-808X&rft_id=info:doi/10.1007/s13042-023-02018-x&rft_dat=%3Cproquest_cross%3E3059398202%3C/proquest_cross%3E%3Curl%3E%3C/url%3E&disable_directlink=true&sfx.directlink=off&sfx.report_link=0&rft_id=info:oai/&rft_pqid=3059109528&rft_id=info:pmid/&rfr_iscdi=true |