Semi-supervised overlapping community detection in attributed graph with graph convolutional autoencoder
[Display omitted] The architecture of our proposed method SSGCAE for semi-supervised overlapping community detection in attributed graph. •An end-to-end method SSGCAE for overlapping community detection is proposed.•SSGCAE is based on graph convolutional autoencoder driven by community detection.•SS...
Uloženo v:
| Vydáno v: | Information sciences Ročník 608; s. 1464 - 1479 |
|---|---|
| Hlavní autoři: | , , , , , |
| Médium: | Journal Article |
| Jazyk: | angličtina |
| Vydáno: |
Elsevier Inc
01.08.2022
|
| Témata: | |
| ISSN: | 0020-0255, 1872-6291 |
| On-line přístup: | Získat plný text |
| Tagy: |
Přidat tag
Žádné tagy, Buďte první, kdo vytvoří štítek k tomuto záznamu!
|
| Abstract | [Display omitted]
The architecture of our proposed method SSGCAE for semi-supervised overlapping community detection in attributed graph.
•An end-to-end method SSGCAE for overlapping community detection is proposed.•SSGCAE is based on graph convolutional autoencoder driven by community detection.•SSGCAE is comprehensively evaluated on synthetic and real attributed graphs.•SSGCAE outperforms state-of-the-art baselines.
Community detection in attributed graph is of great application value and many related methods have been continually presented. However, existing methods for community detection in attributed graph still cannot well solve three key problems simultaneously: link information and attribute information fusion, prior information integration and overlapping community detection. Aiming at these problems, in this paper we devise a semi-supervised overlapping community detection method named SSGCAE which is based on graph neural networks. This method is composed of three modules: graph convolutional autoencoder (GCAE), semi-supervision and modularity maximization, which are respectively utilized to fuse link information and attribute information, integrate prior information and detect overlapping communities. We treat GCAE as the backbone framework and train it by using the unified loss from these three modules. Through this way, these three modules are jointly correlated via the community membership representation, which is very beneficial to improve the overall performance. SSGCAE is comprehensively evaluated on synthetic and real attributed graphs, and experiment results show that it is very effective and outperforms state-of-the-art baseline approaches. |
|---|---|
| AbstractList | [Display omitted]
The architecture of our proposed method SSGCAE for semi-supervised overlapping community detection in attributed graph.
•An end-to-end method SSGCAE for overlapping community detection is proposed.•SSGCAE is based on graph convolutional autoencoder driven by community detection.•SSGCAE is comprehensively evaluated on synthetic and real attributed graphs.•SSGCAE outperforms state-of-the-art baselines.
Community detection in attributed graph is of great application value and many related methods have been continually presented. However, existing methods for community detection in attributed graph still cannot well solve three key problems simultaneously: link information and attribute information fusion, prior information integration and overlapping community detection. Aiming at these problems, in this paper we devise a semi-supervised overlapping community detection method named SSGCAE which is based on graph neural networks. This method is composed of three modules: graph convolutional autoencoder (GCAE), semi-supervision and modularity maximization, which are respectively utilized to fuse link information and attribute information, integrate prior information and detect overlapping communities. We treat GCAE as the backbone framework and train it by using the unified loss from these three modules. Through this way, these three modules are jointly correlated via the community membership representation, which is very beneficial to improve the overall performance. SSGCAE is comprehensively evaluated on synthetic and real attributed graphs, and experiment results show that it is very effective and outperforms state-of-the-art baseline approaches. |
| Author | Cheng, Junwei Tang, Yong Chen, Guohua Liu, Hai Zheng, Yulong He, Chaobo |
| Author_xml | – sequence: 1 givenname: Chaobo surname: He fullname: He, Chaobo email: hechaobo@foxmail.com organization: School of Computer Science, South China Normal University, Guangzhou 510631, China – sequence: 2 givenname: Yulong surname: Zheng fullname: Zheng, Yulong email: 1457367033@qq.com organization: School of Computer Science, South China Normal University, Guangzhou 510631, China – sequence: 3 givenname: Junwei surname: Cheng fullname: Cheng, Junwei email: jung@m.scnu.edu.cn organization: School of Computer Science, South China Normal University, Guangzhou 510631, China – sequence: 4 givenname: Yong surname: Tang fullname: Tang, Yong email: ytang@m.scnu.edu.cn organization: School of Computer Science, South China Normal University, Guangzhou 510631, China – sequence: 5 givenname: Guohua surname: Chen fullname: Chen, Guohua email: chengh3@qq.com organization: School of Computer Science, South China Normal University, Guangzhou 510631, China – sequence: 6 givenname: Hai surname: Liu fullname: Liu, Hai email: liuhai@m.scnu.edu.cn organization: School of Computer Science, South China Normal University, Guangzhou 510631, China |
| BookMark | eNp9kMtOwzAQRS1UJNrCB7DLDySMncROxApVvKRKLIC15TqT1lVqR7YT1L8nFV2x6Gpmcc9o7lmQmXUWCbmnkFGg_GGfGRsyBoxlIDLI-RWZ00qwlLOazsgcgEEKrCxvyCKEPQAUgvM52X3iwaRh6NGPJmCTuBF9p_re2G2i3eEwWBOPSYMRdTTOJsYmKkZvNkOc0luv-l3yY-LuvGpnR9cNp6jqEjVEh1a7Bv0tuW5VF_DuPJfk--X5a_WWrj9e31dP61QzJmJa1S2HipelapDyEupc8UpttKqKSte8FbmqNFR5QdsWKRMFRa3ohhWNQKoFzZdE_N3V3oXgsZXaRHX6J3plOklBnoTJvZyEyZMwCUJOwiaS_iN7bw7KHy8yj38MTpVGg14GbabG2Bg_CZONMxfoX1kwiSU |
| CitedBy_id | crossref_primary_10_3390_s25082601 crossref_primary_10_1007_s10878_024_01254_3 crossref_primary_10_1016_j_inffus_2024_102254 crossref_primary_10_1016_j_eswa_2024_123973 crossref_primary_10_1016_j_ins_2024_121709 crossref_primary_10_1145_3613449 crossref_primary_10_1016_j_ins_2022_11_125 crossref_primary_10_1007_s13042_023_02074_3 crossref_primary_10_1016_j_eswa_2023_120748 crossref_primary_10_1007_s00521_023_09066_y crossref_primary_10_1016_j_adhoc_2024_103589 crossref_primary_10_1016_j_neucom_2024_128169 crossref_primary_10_1016_j_neucom_2024_127992 crossref_primary_10_1016_j_neucom_2025_130411 crossref_primary_10_1016_j_ins_2023_119200 crossref_primary_10_1016_j_knosys_2023_110961 crossref_primary_10_1109_ACCESS_2023_3328616 crossref_primary_10_1016_j_neunet_2025_107601 crossref_primary_10_1016_j_ins_2023_02_090 crossref_primary_10_1016_j_ins_2023_119877 crossref_primary_10_1080_10589759_2025_2541053 crossref_primary_10_1145_3716391 crossref_primary_10_1109_TKDE_2024_3389049 crossref_primary_10_1016_j_asoc_2024_112250 crossref_primary_10_1016_j_asoc_2025_113584 crossref_primary_10_1109_ACCESS_2025_3573293 crossref_primary_10_1007_s10489_024_05287_3 crossref_primary_10_1016_j_ins_2022_12_090 crossref_primary_10_1016_j_knosys_2025_114236 crossref_primary_10_1016_j_neucom_2024_128812 crossref_primary_10_1016_j_asoc_2024_111414 crossref_primary_10_1016_j_chaos_2024_115501 crossref_primary_10_1016_j_ins_2023_119055 crossref_primary_10_1016_j_ins_2025_122039 |
| Cites_doi | 10.1109/TSP.2020.3033962 10.1109/TCSS.2020.2988983 10.1145/2501654.2501657 10.1016/j.dss.2020.113303 10.1016/j.aiopen.2021.01.001 10.1016/j.cosrev.2020.100286 10.1073/pnas.122653799 10.1016/j.physrep.2016.09.002 10.1109/TKDE.2021.3104155 10.1145/2629616 10.1109/TCYB.2014.2377154 10.1109/TKDE.2019.2958342 10.1016/j.knosys.2020.105760 10.1109/TKDE.2020.2981333 10.1007/s11704-020-9203-0 10.1016/j.neucom.2020.07.125 10.1016/j.ins.2015.03.075 10.1016/j.ins.2016.11.028 10.1016/j.jnca.2018.02.011 10.1145/1921632.1921638 10.1109/TNNLS.2020.2978386 10.1109/TKDE.2018.2846555 10.1109/TCYB.2019.2931983 |
| ContentType | Journal Article |
| Copyright | 2022 Elsevier Inc. |
| Copyright_xml | – notice: 2022 Elsevier Inc. |
| DBID | AAYXX CITATION |
| DOI | 10.1016/j.ins.2022.07.036 |
| DatabaseName | CrossRef |
| DatabaseTitle | CrossRef |
| DatabaseTitleList | |
| DeliveryMethod | fulltext_linktorsrc |
| Discipline | Engineering Library & Information Science |
| EISSN | 1872-6291 |
| EndPage | 1479 |
| ExternalDocumentID | 10_1016_j_ins_2022_07_036 S0020025522007253 |
| GroupedDBID | --K --M --Z -~X .DC .~1 0R~ 1B1 1OL 1RT 1~. 1~5 29I 4.4 457 4G. 5GY 5VS 7-5 71M 8P~ 9JN 9JO AAAKF AAAKG AABNK AACTN AAEDT AAEDW AAIAV AAIKJ AAKOC AALRI AAOAW AAQFI AAQXK AARIN AAXUO AAYFN ABAOU ABBOA ABEFU ABFNM ABJNI ABMAC ABTAH ABUCO ABXDB ABYKQ ACAZW ACDAQ ACGFS ACNNM ACRLP ACZNC ADBBV ADEZE ADGUI ADJOM ADMUD ADTZH AEBSH AECPX AEKER AENEX AFFNX AFKWA AFTJW AGHFR AGUBO AGYEJ AHHHB AHJVU AHZHX AIALX AIEXJ AIGVJ AIKHN AITUG AJBFU AJOXV ALMA_UNASSIGNED_HOLDINGS AMFUW AMRAJ AOUOD APLSM ARUGR ASPBG AVWKF AXJTR AZFZN BJAXD BKOJK BLXMC CS3 DU5 EBS EFJIC EFLBG EJD EO8 EO9 EP2 EP3 F5P FDB FEDTE FGOYB FIRID FNPLU FYGXN G-Q GBLVA GBOLZ HAMUX HLZ HVGLF HZ~ H~9 IHE J1W JJJVA KOM LG9 LY1 M41 MHUIS MO0 MS~ N9A O-L O9- OAUVE OZT P-8 P-9 P2P PC. Q38 R2- RIG ROL RPZ SBC SDF SDG SDP SDS SES SEW SPC SPCBC SSB SSD SST SSV SSW SSZ T5K TN5 TWZ UHS WH7 WUQ XPP YYP ZMT ZY4 ~02 ~G- 77I 9DU AATTM AAXKI AAYWO AAYXX ABWVN ACLOT ACRPL ACVFH ADCNI ADNMO ADVLN AEIPS AEUPX AFJKZ AFPUW AGQPQ AIGII AIIUN AKBMS AKRWK AKYEP ANKPU APXCP CITATION EFKBS ~HD |
| ID | FETCH-LOGICAL-c227t-89f608655ade165093a68abca848c96f73a8c08341ffe12741eca1b24d7e1c713 |
| ISICitedReferencesCount | 37 |
| ISICitedReferencesURI | http://www.webofscience.com/api/gateway?GWVersion=2&SrcApp=Summon&SrcAuth=ProQuest&DestLinkType=CitingArticles&DestApp=WOS_CPL&KeyUT=000834614400015&url=https%3A%2F%2Fcvtisr.summon.serialssolutions.com%2F%23%21%2Fsearch%3Fho%3Df%26include.ft.matches%3Dt%26l%3Dnull%26q%3D |
| ISSN | 0020-0255 |
| IngestDate | Sat Nov 29 07:28:58 EST 2025 Tue Nov 18 22:11:29 EST 2025 Fri Feb 23 02:38:40 EST 2024 |
| IsPeerReviewed | true |
| IsScholarly | true |
| Keywords | Graph neural networks Graph convolutional autoencoder Semi-supervised learning Attributed graph Overlapping community detection |
| Language | English |
| LinkModel | OpenURL |
| MergedId | FETCHMERGED-LOGICAL-c227t-89f608655ade165093a68abca848c96f73a8c08341ffe12741eca1b24d7e1c713 |
| PageCount | 16 |
| ParticipantIDs | crossref_citationtrail_10_1016_j_ins_2022_07_036 crossref_primary_10_1016_j_ins_2022_07_036 elsevier_sciencedirect_doi_10_1016_j_ins_2022_07_036 |
| PublicationCentury | 2000 |
| PublicationDate | August 2022 2022-08-00 |
| PublicationDateYYYYMMDD | 2022-08-01 |
| PublicationDate_xml | – month: 08 year: 2022 text: August 2022 |
| PublicationDecade | 2020 |
| PublicationTitle | Information sciences |
| PublicationYear | 2022 |
| Publisher | Elsevier Inc |
| Publisher_xml | – name: Elsevier Inc |
| References | Hajiramezanali, Hasanzadeh, Narayanan, Duffield, Zhou, Qian (b0055) 2019 Yang, Cao, Jin, Wang, Meng (b0215) 2015; 45 Kipf, Welling (b0100) 2017 Yang, Liu, Liu, Tao (b0220) 2021; 33 Alsini, Datta, Huynh (b0005) 2020; 7 Javed, Younis, Latif, Qadir, Baig (b0075) 2018; 108 Xie, Kelley, Szymanski (b0200) 2013; 45 Yao, Mao, Luo (b0230) 2019 Falih, Grozavu, Kanawati, Bennani (b0030) 2018 Shi, Fan, Kwok (b0155) 2020 Xu, Hu, Leskovec, Jegelka (b0210) 2019 Liu, Wang, He, Jiao, Jin, Cannistraci (b0120) 2017; 381 Pourhabibi, Ong, Kam, Boo (b0130) 2020; 133 Jin, Liu, Li, Zhang (b0090) 2019 M.J. Wang, L.F. Yu, D. Zheng, et al. Deep graph library: towards efficient and scalable deep learning on graphs, (2019) arXiv:1909.01315. Guo, Pan, Zhu, Zhang (b0050) 2019; 31 Wu, Pan, Chen, Long, Zhang, Yu (b0195) 2021; 32 Glorot, Bengio (b0045) 2010 Ruiz, Gama, Ribeiro (b0145) 2020; 68 Qiao, Deng, Li, Hu, Song, Gao (b0135) 2021; 420 Chakraborty, Dalmia, Mukherjee, Ganguly (b0015) 2017; 50 Ruan, Fuhry, Parthasarathy (b0140) 2013 Zhang, Cui, Zhu (b0240) 2022; 34 Newman (b0125) 2006; 3 Z.Q. Xu, Y.P Ke, Y. Wang, H. Cheng, J. Cheng, GBAGC: a general bayesian framework for attributed graph clustering, ACM Transactions on Knowledge Discovery from Data 9 (2014) 1-43. Kipf, Welling (b0105) 2016 He, Wang, Jiang (b0060) 2015 Li, Wu, Ester, Kao, Wang, Zheng (b0115) 2017 Yang, Leskovec (b0225) 2013 Chunaev (b0025) 2020; 37 Jin, He, Chai, He (b0085) 2021; 15 Bo, Wang, Shi, Zhu, Lu, Cui (b0010) 2020 Cheng, Zhou, Yu (b0020) 2011; 5 Velickovic, Cucurull, Casanova, Romero, Lio, Bengio (b0170) 2018 Teng, Liu, Li (b0165) 2021; 51 Girvan, Newman (b0040) 2002; 99 Shchur, Günnemann (b0150) 2019 Wang, Pan, Hu, Long, Jiang, Zhang (b0180) 2019 Jia, Zhang, Zhang, Wang (b0080) 2019 Huang, Zhong, Wang, Gong, Ma (b0070) 2020; 196 Lancichinetti, Fortunato, Radicchi (b0110) 2008; 78 Su, Xue, Liu, Wu, Yang, Zhou, Hu, Paris, Nepal, Ji, Sheng, Yu (b0160) 2022 Wang, Jin, Cao, Yang, Zhang (b0175) 2016 Wang, Liu, Jiao, Chen, Jin (b0190) 2018 Fortunato, Hric (b0035) 2016; 659 Zhou, Cui, Hu, Zhang, Yang, Liu, Wang, Li, Sun (b0245) 2020; 1 Jin, Yu, Jiao, Pan, He, Wu, Yu, Zhang (b0095) 2021 Ye, Ji (b0235) 2021 Huang, Cheng, Yu (b0065) 2015; 314 Kipf (10.1016/j.ins.2022.07.036_b0105) 2016 10.1016/j.ins.2022.07.036_b0205 Velickovic (10.1016/j.ins.2022.07.036_b0170) 2018 Cheng (10.1016/j.ins.2022.07.036_b0020) 2011; 5 Fortunato (10.1016/j.ins.2022.07.036_b0035) 2016; 659 He (10.1016/j.ins.2022.07.036_b0060) 2015 Zhang (10.1016/j.ins.2022.07.036_b0240) 2022; 34 Li (10.1016/j.ins.2022.07.036_b0115) 2017 Pourhabibi (10.1016/j.ins.2022.07.036_b0130) 2020; 133 Yang (10.1016/j.ins.2022.07.036_b0225) 2013 Wang (10.1016/j.ins.2022.07.036_b0175) 2016 Glorot (10.1016/j.ins.2022.07.036_b0045) 2010 Jia (10.1016/j.ins.2022.07.036_b0080) 2019 Hajiramezanali (10.1016/j.ins.2022.07.036_b0055) 2019 Xu (10.1016/j.ins.2022.07.036_b0210) 2019 Su (10.1016/j.ins.2022.07.036_b0160) 2022 Zhou (10.1016/j.ins.2022.07.036_b0245) 2020; 1 Javed (10.1016/j.ins.2022.07.036_b0075) 2018; 108 Jin (10.1016/j.ins.2022.07.036_b0090) 2019 Teng (10.1016/j.ins.2022.07.036_b0165) 2021; 51 Wang (10.1016/j.ins.2022.07.036_b0180) 2019 Ruan (10.1016/j.ins.2022.07.036_b0140) 2013 Alsini (10.1016/j.ins.2022.07.036_b0005) 2020; 7 Huang (10.1016/j.ins.2022.07.036_b0065) 2015; 314 Yang (10.1016/j.ins.2022.07.036_b0220) 2021; 33 Jin (10.1016/j.ins.2022.07.036_b0095) 2021 Chakraborty (10.1016/j.ins.2022.07.036_b0015) 2017; 50 Newman (10.1016/j.ins.2022.07.036_b0125) 2006; 3 Chunaev (10.1016/j.ins.2022.07.036_b0025) 2020; 37 Qiao (10.1016/j.ins.2022.07.036_b0135) 2021; 420 Liu (10.1016/j.ins.2022.07.036_b0120) 2017; 381 Wu (10.1016/j.ins.2022.07.036_b0195) 2021; 32 Guo (10.1016/j.ins.2022.07.036_b0050) 2019; 31 Lancichinetti (10.1016/j.ins.2022.07.036_b0110) 2008; 78 Bo (10.1016/j.ins.2022.07.036_b0010) 2020 Ruiz (10.1016/j.ins.2022.07.036_b0145) 2020; 68 Girvan (10.1016/j.ins.2022.07.036_b0040) 2002; 99 Shchur (10.1016/j.ins.2022.07.036_b0150) 2019 Falih (10.1016/j.ins.2022.07.036_b0030) 2018 Yang (10.1016/j.ins.2022.07.036_b0215) 2015; 45 Shi (10.1016/j.ins.2022.07.036_b0155) 2020 10.1016/j.ins.2022.07.036_b0185 Jin (10.1016/j.ins.2022.07.036_b0085) 2021; 15 Wang (10.1016/j.ins.2022.07.036_b0190) 2018 Yao (10.1016/j.ins.2022.07.036_b0230) 2019 Ye (10.1016/j.ins.2022.07.036_b0235) 2021 Huang (10.1016/j.ins.2022.07.036_b0070) 2020; 196 Kipf (10.1016/j.ins.2022.07.036_b0100) 2017 Xie (10.1016/j.ins.2022.07.036_b0200) 2013; 45 |
| References_xml | – volume: 37 year: 2020 ident: b0025 article-title: Community detection in node-attributed social networks: a survey publication-title: Computer Science Review – start-page: 587 year: 2013 end-page: 596 ident: b0225 article-title: Overlapping community detection at scale: a nonnegative matrix factorization approach publication-title: Proceedings of the 6th ACM International Conference on Web Search and Data Mining (WSDM) – start-page: 152 year: 2019 end-page: 159 ident: b0090 article-title: Graph convolutional networks meet markov random fields: semi-supervised community detection in attribute networks publication-title: in: Proceedings of the 32nd AAAI Conference on Artificial Intelligence (AAAI) – volume: 78 year: 2008 ident: b0110 article-title: Benchmark graphs for testing community detection algorithms publication-title: Physical Review E – volume: 32 start-page: 4 year: 2021 end-page: 24 ident: b0195 article-title: A comprehensive survey on graph neural networks publication-title: IEEE Transactions on Neural Networks and Learning Systems – volume: 99 start-page: 7821 year: 2002 end-page: 7826 ident: b0040 article-title: Community structure in social and biological networks publication-title: Proceedings of the National Academy of Sciences – volume: 133 year: 2020 ident: b0130 article-title: Fraud detection: a systematic literature review of graph-based anomaly detection approaches publication-title: Decision Support Systems – volume: 51 start-page: 138 year: 2021 end-page: 150 ident: b0165 article-title: Overlapping community detection in directed and undirected attributed networks using a multiobjective evolutionary algorithm publication-title: IEEE Transactions on Cybernetics – start-page: 784 year: 2019 end-page: 794 ident: b0080 article-title: CommunityGAN: community detection with generative adversarial nets publication-title: Proceedings of the 28th International Conference on World Wide Web (WWW) – volume: 45 start-page: 1 year: 2013 end-page: 35 ident: b0200 article-title: Overlapping community detection in networks: the state-of-the-art and comparative study publication-title: ACM Computing Surveys – start-page: 1400 year: 2020 end-page: 1410 ident: b0010 article-title: Structural deep clustering network publication-title: Proceedings of the 29th International Conference on World Wide Web (WWW) – start-page: 1 year: 2017 end-page: 14 ident: b0100 article-title: Semi-supervised classification with graph convolutional networks publication-title: Proceedings of the 5th International Conference on Learning Representations (ICLR) – start-page: 1 year: 2019 end-page: 7 ident: b0150 article-title: Overlapping community detection with graph neural networks publication-title: Proceedings of the 1st International Workshop on Deep Learning for Graphs (DLG) – start-page: 906 year: 2020 end-page: 913 ident: b0155 article-title: Effective decoding in graph auto-encoder using triadic closure publication-title: Proceedings of the 33rd AAAI Conference on Artificial Intelligence (AAAI) – start-page: 265 year: 2016 end-page: 271 ident: b0175 article-title: Semantic community identification in large attribute networks publication-title: Proceedings of the 30th AAAI Conference on Artificial Intelligence (AAAI) – volume: 45 start-page: 2585 year: 2015 end-page: 2598 ident: b0215 article-title: A unified semi-supervised community detection framework using latent space graph regularization publication-title: IEEE Transactions on Cybernetics – reference: M.J. Wang, L.F. Yu, D. Zheng, et al. Deep graph library: towards efficient and scalable deep learning on graphs, (2019) arXiv:1909.01315. – start-page: 1299 year: 2018 end-page: 1306 ident: b0030 article-title: Community detection in attributed network publication-title: Proceedings of the 27th International Conference on World Wide Web (WWW) – start-page: 1621 year: 2017 end-page: 1629 ident: b0115 article-title: Semi-supervised clustering in attributed heterogeneous information networks publication-title: Proceedings of the 26th International Conference on World Wide Web (WWW) – reference: Z.Q. Xu, Y.P Ke, Y. Wang, H. Cheng, J. Cheng, GBAGC: a general bayesian framework for attributed graph clustering, ACM Transactions on Knowledge Discovery from Data 9 (2014) 1-43. – volume: 1 start-page: 57 year: 2020 end-page: 81 ident: b0245 article-title: Graph neural networks: a review of methods and applications publication-title: AI Open – start-page: 1 year: 2019 end-page: 11 ident: b0055 article-title: Variational graph recurrent neural networks publication-title: Proceedings of the 33rd Conference in Neural Information Processing Systems (NeurIPS) – year: 2021 ident: b0095 article-title: A survey of community detection approaches: from statistical modeling to deep learning publication-title: IEEE Transactions on Knowledge and Data Engineering (Early Access) – year: 2021 ident: b0235 article-title: Sparse graph attention networks publication-title: IEEE Transactions on Knowledge and Data Engineering (Early Access) – volume: 50 start-page: 54 year: 2017 ident: b0015 article-title: Metrics for community analysis: a survey publication-title: ACM Computing Surveys – start-page: 1 year: 2019 end-page: 17 ident: b0210 article-title: How powerful are graph neural networks? in publication-title: Proceedings of the 7th International Conference on Learning Representations (ICLR) – volume: 34 start-page: 249 year: 2022 end-page: 270 ident: b0240 article-title: Deep learning on graphs: a survey publication-title: IEEE Transactions on Knowledge and Data Engineering – volume: 68 start-page: 6303 year: 2020 end-page: 6318 ident: b0145 article-title: Gated graph recurrent neural networks publication-title: IEEE Transactions on Signal Processing – year: 2022 ident: b0160 article-title: A comprehensive survey on community detection with deep learning publication-title: IEEE Transactions on Neural Networks and Learning Systems (Early Access) – start-page: 7370 year: 2019 end-page: 7377 ident: b0230 article-title: Graph convolutional networks for text classification publication-title: Proceedings of the 32nd AAAI Conference on Artificial Intelligence (AAAI) – start-page: 1089 year: 2013 end-page: 1098 ident: b0140 article-title: Efficient community detection in large networks using content and links publication-title: Proceedings of the 22nd International Conference on World Wide Web (WWW) – volume: 420 start-page: 246 year: 2021 end-page: 265 ident: b0135 article-title: Research on historical phase division of terrorism: an analysis method by time series complex network publication-title: Neurocomputing – volume: 314 start-page: 77 year: 2015 end-page: 99 ident: b0065 article-title: Dense community detection in multi-valued attributed networks publication-title: Information Sciences – start-page: 3670 year: 2019 end-page: 3676 ident: b0180 article-title: Attributed graph clustering: a deep attentional embedding approach publication-title: Proceedings of the 28th International Joint Conference on Artificial Intelligence (IJCAI) – volume: 5 start-page: 12 year: 2011 ident: b0020 article-title: Clustering large attributed graphs: a balance between structural and attribute similarities publication-title: ACM Transactions on Knowledge Discovery from Data – volume: 659 start-page: 1 year: 2016 end-page: 44 ident: b0035 article-title: Community detection in networks: a user guide publication-title: Physics Reports – start-page: 249 year: 2010 end-page: 256 ident: b0045 article-title: Understanding the difficulty of training deep feedforward neural networks publication-title: Proceedings of the 13th International Conference on Artificial Intelligence and Statistics (AIS) – start-page: 218 year: 2018 end-page: 230 ident: b0190 article-title: A unified weakly supervised framework for community detection and semantic matching publication-title: Proceedings of the 22nd Pacific-Asia Conference on Knowledge Discovery and Data Mining (PAKDD) – start-page: 1 year: 2018 end-page: 12 ident: b0170 article-title: Graph attention networks publication-title: Proceedings of the 6th International Conference on Learning Representations (ICLR) – volume: 381 start-page: 304 year: 2017 end-page: 321 ident: b0120 article-title: Semi-supervised community detection based on non-negative matrix factorization with node popularity publication-title: Information Sciences – volume: 7 start-page: 971 year: 2020 end-page: 982 ident: b0005 article-title: On utilizing communities detected from social networks in hashtag recommendation publication-title: IEEE Transactions on Computational Social Systems – volume: 33 start-page: 2349 year: 2021 end-page: 2368 ident: b0220 article-title: A survey on canonical correlation analysis publication-title: IEEE Transactions on Knowledge and Data Engineering – volume: 31 start-page: 706 year: 2019 end-page: 719 ident: b0050 article-title: CFOND: consensus factorization for co-clustering networked data publication-title: IEEE Transactions Knowledge Data Engineering – start-page: 1281 year: 2015 end-page: 1290 ident: b0060 article-title: Discovering canonical correlations between topical and topological information in document networks publication-title: Proceedings of the 24th ACM International on Conference on Information and Knowledge Management (CIKM) – volume: 15 year: 2021 ident: b0085 article-title: Semi-supervised community detection on attributed networks using non-negative matrix tri-factorization with node popularity publication-title: Frontiers of Computer Science – volume: 196 year: 2020 ident: b0070 article-title: Detecting community in attributed networks by dynamically exploring node attributes and topological structure publication-title: Knowledge-Based Systems – start-page: 1 year: 2016 end-page: 3 ident: b0105 article-title: Variational graph auto-encoders publication-title: Proceedings of the 30th Conference in Neural Information Processing Systems (NeurIPS) – volume: 108 start-page: 87 year: 2018 end-page: 111 ident: b0075 article-title: Community detection in networks: a multidisciplinary review publication-title: Journal of Network and Computer Applications – volume: 3 start-page: 8577 year: 2006 end-page: 8582 ident: b0125 publication-title: Modularity and community structure in networks, in: Proceedings of the national academy of sciences – volume: 68 start-page: 6303 year: 2020 ident: 10.1016/j.ins.2022.07.036_b0145 article-title: Gated graph recurrent neural networks publication-title: IEEE Transactions on Signal Processing doi: 10.1109/TSP.2020.3033962 – start-page: 1 year: 2019 ident: 10.1016/j.ins.2022.07.036_b0210 article-title: How powerful are graph neural networks? in – volume: 7 start-page: 971 issue: 4 year: 2020 ident: 10.1016/j.ins.2022.07.036_b0005 article-title: On utilizing communities detected from social networks in hashtag recommendation publication-title: IEEE Transactions on Computational Social Systems doi: 10.1109/TCSS.2020.2988983 – volume: 45 start-page: 1 issue: 4 year: 2013 ident: 10.1016/j.ins.2022.07.036_b0200 article-title: Overlapping community detection in networks: the state-of-the-art and comparative study publication-title: ACM Computing Surveys doi: 10.1145/2501654.2501657 – volume: 133 year: 2020 ident: 10.1016/j.ins.2022.07.036_b0130 article-title: Fraud detection: a systematic literature review of graph-based anomaly detection approaches publication-title: Decision Support Systems doi: 10.1016/j.dss.2020.113303 – year: 2022 ident: 10.1016/j.ins.2022.07.036_b0160 article-title: A comprehensive survey on community detection with deep learning publication-title: IEEE Transactions on Neural Networks and Learning Systems (Early Access) – start-page: 587 year: 2013 ident: 10.1016/j.ins.2022.07.036_b0225 article-title: Overlapping community detection at scale: a nonnegative matrix factorization approach – start-page: 265 year: 2016 ident: 10.1016/j.ins.2022.07.036_b0175 article-title: Semantic community identification in large attribute networks – start-page: 1 year: 2019 ident: 10.1016/j.ins.2022.07.036_b0150 article-title: Overlapping community detection with graph neural networks – volume: 1 start-page: 57 year: 2020 ident: 10.1016/j.ins.2022.07.036_b0245 article-title: Graph neural networks: a review of methods and applications publication-title: AI Open doi: 10.1016/j.aiopen.2021.01.001 – volume: 37 year: 2020 ident: 10.1016/j.ins.2022.07.036_b0025 article-title: Community detection in node-attributed social networks: a survey publication-title: Computer Science Review doi: 10.1016/j.cosrev.2020.100286 – volume: 99 start-page: 7821 issue: 12 year: 2002 ident: 10.1016/j.ins.2022.07.036_b0040 article-title: Community structure in social and biological networks publication-title: Proceedings of the National Academy of Sciences doi: 10.1073/pnas.122653799 – start-page: 1 year: 2017 ident: 10.1016/j.ins.2022.07.036_b0100 article-title: Semi-supervised classification with graph convolutional networks – volume: 659 start-page: 1 year: 2016 ident: 10.1016/j.ins.2022.07.036_b0035 article-title: Community detection in networks: a user guide publication-title: Physics Reports doi: 10.1016/j.physrep.2016.09.002 – volume: 3 start-page: 8577 issue: 23 year: 2006 ident: 10.1016/j.ins.2022.07.036_b0125 publication-title: Modularity and community structure in networks, in: Proceedings of the national academy of sciences – start-page: 1281 year: 2015 ident: 10.1016/j.ins.2022.07.036_b0060 article-title: Discovering canonical correlations between topical and topological information in document networks – year: 2021 ident: 10.1016/j.ins.2022.07.036_b0095 article-title: A survey of community detection approaches: from statistical modeling to deep learning publication-title: IEEE Transactions on Knowledge and Data Engineering (Early Access) doi: 10.1109/TKDE.2021.3104155 – ident: 10.1016/j.ins.2022.07.036_b0205 doi: 10.1145/2629616 – volume: 50 start-page: 54 issue: 4 year: 2017 ident: 10.1016/j.ins.2022.07.036_b0015 article-title: Metrics for community analysis: a survey publication-title: ACM Computing Surveys – volume: 45 start-page: 2585 issue: 11 year: 2015 ident: 10.1016/j.ins.2022.07.036_b0215 article-title: A unified semi-supervised community detection framework using latent space graph regularization publication-title: IEEE Transactions on Cybernetics doi: 10.1109/TCYB.2014.2377154 – start-page: 1089 year: 2013 ident: 10.1016/j.ins.2022.07.036_b0140 article-title: Efficient community detection in large networks using content and links – start-page: 906 year: 2020 ident: 10.1016/j.ins.2022.07.036_b0155 article-title: Effective decoding in graph auto-encoder using triadic closure – volume: 33 start-page: 2349 issue: 6 year: 2021 ident: 10.1016/j.ins.2022.07.036_b0220 article-title: A survey on canonical correlation analysis publication-title: IEEE Transactions on Knowledge and Data Engineering doi: 10.1109/TKDE.2019.2958342 – volume: 196 year: 2020 ident: 10.1016/j.ins.2022.07.036_b0070 article-title: Detecting community in attributed networks by dynamically exploring node attributes and topological structure publication-title: Knowledge-Based Systems doi: 10.1016/j.knosys.2020.105760 – start-page: 784 year: 2019 ident: 10.1016/j.ins.2022.07.036_b0080 article-title: CommunityGAN: community detection with generative adversarial nets – year: 2021 ident: 10.1016/j.ins.2022.07.036_b0235 article-title: Sparse graph attention networks publication-title: IEEE Transactions on Knowledge and Data Engineering (Early Access) – start-page: 1 year: 2018 ident: 10.1016/j.ins.2022.07.036_b0170 article-title: Graph attention networks – volume: 78 issue: 2 year: 2008 ident: 10.1016/j.ins.2022.07.036_b0110 article-title: Benchmark graphs for testing community detection algorithms publication-title: Physical Review E – volume: 34 start-page: 249 issue: 1 year: 2022 ident: 10.1016/j.ins.2022.07.036_b0240 article-title: Deep learning on graphs: a survey publication-title: IEEE Transactions on Knowledge and Data Engineering doi: 10.1109/TKDE.2020.2981333 – ident: 10.1016/j.ins.2022.07.036_b0185 – volume: 15 year: 2021 ident: 10.1016/j.ins.2022.07.036_b0085 article-title: Semi-supervised community detection on attributed networks using non-negative matrix tri-factorization with node popularity publication-title: Frontiers of Computer Science doi: 10.1007/s11704-020-9203-0 – start-page: 218 year: 2018 ident: 10.1016/j.ins.2022.07.036_b0190 article-title: A unified weakly supervised framework for community detection and semantic matching – volume: 420 start-page: 246 year: 2021 ident: 10.1016/j.ins.2022.07.036_b0135 article-title: Research on historical phase division of terrorism: an analysis method by time series complex network publication-title: Neurocomputing doi: 10.1016/j.neucom.2020.07.125 – start-page: 1400 year: 2020 ident: 10.1016/j.ins.2022.07.036_b0010 article-title: Structural deep clustering network – volume: 314 start-page: 77 year: 2015 ident: 10.1016/j.ins.2022.07.036_b0065 article-title: Dense community detection in multi-valued attributed networks publication-title: Information Sciences doi: 10.1016/j.ins.2015.03.075 – volume: 381 start-page: 304 year: 2017 ident: 10.1016/j.ins.2022.07.036_b0120 article-title: Semi-supervised community detection based on non-negative matrix factorization with node popularity publication-title: Information Sciences doi: 10.1016/j.ins.2016.11.028 – volume: 108 start-page: 87 year: 2018 ident: 10.1016/j.ins.2022.07.036_b0075 article-title: Community detection in networks: a multidisciplinary review publication-title: Journal of Network and Computer Applications doi: 10.1016/j.jnca.2018.02.011 – volume: 5 start-page: 12 issue: 2 year: 2011 ident: 10.1016/j.ins.2022.07.036_b0020 article-title: Clustering large attributed graphs: a balance between structural and attribute similarities publication-title: ACM Transactions on Knowledge Discovery from Data doi: 10.1145/1921632.1921638 – start-page: 152 year: 2019 ident: 10.1016/j.ins.2022.07.036_b0090 article-title: Graph convolutional networks meet markov random fields: semi-supervised community detection in attribute networks – start-page: 1299 year: 2018 ident: 10.1016/j.ins.2022.07.036_b0030 article-title: Community detection in attributed network – start-page: 249 year: 2010 ident: 10.1016/j.ins.2022.07.036_b0045 article-title: Understanding the difficulty of training deep feedforward neural networks – start-page: 7370 year: 2019 ident: 10.1016/j.ins.2022.07.036_b0230 article-title: Graph convolutional networks for text classification – start-page: 1 year: 2016 ident: 10.1016/j.ins.2022.07.036_b0105 article-title: Variational graph auto-encoders – start-page: 1621 year: 2017 ident: 10.1016/j.ins.2022.07.036_b0115 article-title: Semi-supervised clustering in attributed heterogeneous information networks – volume: 32 start-page: 4 issue: 1 year: 2021 ident: 10.1016/j.ins.2022.07.036_b0195 article-title: A comprehensive survey on graph neural networks publication-title: IEEE Transactions on Neural Networks and Learning Systems doi: 10.1109/TNNLS.2020.2978386 – volume: 31 start-page: 706 issue: 4 year: 2019 ident: 10.1016/j.ins.2022.07.036_b0050 article-title: CFOND: consensus factorization for co-clustering networked data publication-title: IEEE Transactions Knowledge Data Engineering doi: 10.1109/TKDE.2018.2846555 – volume: 51 start-page: 138 issue: 1 year: 2021 ident: 10.1016/j.ins.2022.07.036_b0165 article-title: Overlapping community detection in directed and undirected attributed networks using a multiobjective evolutionary algorithm publication-title: IEEE Transactions on Cybernetics doi: 10.1109/TCYB.2019.2931983 – start-page: 3670 year: 2019 ident: 10.1016/j.ins.2022.07.036_b0180 article-title: Attributed graph clustering: a deep attentional embedding approach – start-page: 1 year: 2019 ident: 10.1016/j.ins.2022.07.036_b0055 article-title: Variational graph recurrent neural networks |
| SSID | ssj0004766 |
| Score | 2.533123 |
| Snippet | [Display omitted]
The architecture of our proposed method SSGCAE for semi-supervised overlapping community detection in attributed graph.
•An end-to-end method... |
| SourceID | crossref elsevier |
| SourceType | Enrichment Source Index Database Publisher |
| StartPage | 1464 |
| SubjectTerms | Attributed graph Graph convolutional autoencoder Graph neural networks Overlapping community detection Semi-supervised learning |
| Title | Semi-supervised overlapping community detection in attributed graph with graph convolutional autoencoder |
| URI | https://dx.doi.org/10.1016/j.ins.2022.07.036 |
| Volume | 608 |
| WOSCitedRecordID | wos000834614400015&url=https%3A%2F%2Fcvtisr.summon.serialssolutions.com%2F%23%21%2Fsearch%3Fho%3Df%26include.ft.matches%3Dt%26l%3Dnull%26q%3D |
| hasFullText | 1 |
| inHoldings | 1 |
| isFullTextHit | |
| isPrint | |
| journalDatabaseRights | – providerCode: PRVESC databaseName: ScienceDirect database customDbUrl: eissn: 1872-6291 dateEnd: 99991231 omitProxy: false ssIdentifier: ssj0004766 issn: 0020-0255 databaseCode: AIEXJ dateStart: 19950101 isFulltext: true titleUrlDefault: https://www.sciencedirect.com providerName: Elsevier |
| link | http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwtV1Nb9QwELWWlgM9ICggSinyAXEARcqHYzvHChWVClVIFLScIsd2xK6WJOombf8A_7vj2E7C0iJ64BJZluNNdl7GM-OZZ4ReRwlVQhVxQIgowUHRJCg4KwJZJiWnmnLVs_N_-8ROT_l8nn2ezX75WpiLFasqfnWVNf9V1NAHwjals3cQ9zApdEAbhA5XEDtc_0nwX_TPRbDuGqME1mBOmhzNlWgaV11rykHA8Fa61dInOorWnnsFo3sCaxudtU2Tlu6e19AKdG1tqC-VS-pd-kT4oQjynVtTB1v9WLtt_bqoxzC1tjrme7eq3drZ5xi47pOuutSLMargBvuhLkoBDq7PkRurBsLA-C9TzUtDPtGdoLPJZB2OiD1l5g8db8MNS3BMDN16HPfkq8kNfNob69yQfegT25Y5TJGbKfKQ5TDFPbQdszQD5bh9-PFofjIW2DK76e1fwm-P94mCG89xs4EzMVrOHqGHztvAhxYlj9FMV7toZ8JBuYsOXOUKfoMnUsRO5z9BPzbwhCd4wgOe8IAnvKjwiCfcgwgbPLnmb3jCEzw9RV8_HJ29Pw7c8RyBjGPWBjwrQYA0TYXSkSFiTATlopCCEy4zWrJEcAkWPonKUkeGJklLERUxUUxHkkXJM7RV1ZV-jjAYvQI0Q0FVqEiackGp0ARmk2BBMxXuodD_p7l03PXmCJVVfqss99Db4ZbGErf8bTDxgsrdV2ItyhxAd_ttL-7yG_vowfhhvERb7XmnD9B9edEu1uevHOKuAerRqbM |
| linkProvider | Elsevier |
| openUrl | ctx_ver=Z39.88-2004&ctx_enc=info%3Aofi%2Fenc%3AUTF-8&rfr_id=info%3Asid%2Fsummon.serialssolutions.com&rft_val_fmt=info%3Aofi%2Ffmt%3Akev%3Amtx%3Ajournal&rft.genre=article&rft.atitle=Semi-supervised+overlapping+community+detection+in+attributed+graph+with+graph+convolutional+autoencoder&rft.jtitle=Information+sciences&rft.au=He%2C+Chaobo&rft.au=Zheng%2C+Yulong&rft.au=Cheng%2C+Junwei&rft.au=Tang%2C+Yong&rft.date=2022-08-01&rft.issn=0020-0255&rft.volume=608&rft.spage=1464&rft.epage=1479&rft_id=info:doi/10.1016%2Fj.ins.2022.07.036&rft.externalDBID=n%2Fa&rft.externalDocID=10_1016_j_ins_2022_07_036 |
| thumbnail_l | http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/lc.gif&issn=0020-0255&client=summon |
| thumbnail_m | http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/mc.gif&issn=0020-0255&client=summon |
| thumbnail_s | http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/sc.gif&issn=0020-0255&client=summon |