Multi-view representation model based on graph autoencoder
Graph representation learning is a hot topic in non-Euclidean data in various domains, such as social networks, biological networks, etc. When some data labels are missing, graph autoencoder and graph variational autoencoder can perform outstanding abilities on node clustering or link prediction tas...
Uloženo v:
| Vydáno v: | Information sciences Ročník 632; s. 439 - 453 |
|---|---|
| Hlavní autoři: | , , , |
| Médium: | Journal Article |
| Jazyk: | angličtina |
| Vydáno: |
Elsevier Inc
01.06.2023
|
| 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 | Graph representation learning is a hot topic in non-Euclidean data in various domains, such as social networks, biological networks, etc. When some data labels are missing, graph autoencoder and graph variational autoencoder can perform outstanding abilities on node clustering or link prediction tasks. However, most existing graph representation learning ignores data's multi-modal features and takes the node features and graph structure features as one view. Besides, most graph autoencoders only reconstruct the node feature matrix or adjacency matrix, which does not fully use the hidden representation information. In this paper, we propose a multi-view representation model based on graph autoencoder, which can employ the global structure topology, latent local topology, and feature relative information. Meanwhile, we add another decoder to reconstruct the node feature matrix as an auxiliary task. In this way, the proposed framework can utilize the learned representation sufficiently. We validate the effectiveness of our framework on four datasets, and the experimental results demonstrate superior performance compared with other advanced frameworks. |
|---|---|
| AbstractList | Graph representation learning is a hot topic in non-Euclidean data in various domains, such as social networks, biological networks, etc. When some data labels are missing, graph autoencoder and graph variational autoencoder can perform outstanding abilities on node clustering or link prediction tasks. However, most existing graph representation learning ignores data's multi-modal features and takes the node features and graph structure features as one view. Besides, most graph autoencoders only reconstruct the node feature matrix or adjacency matrix, which does not fully use the hidden representation information. In this paper, we propose a multi-view representation model based on graph autoencoder, which can employ the global structure topology, latent local topology, and feature relative information. Meanwhile, we add another decoder to reconstruct the node feature matrix as an auxiliary task. In this way, the proposed framework can utilize the learned representation sufficiently. We validate the effectiveness of our framework on four datasets, and the experimental results demonstrate superior performance compared with other advanced frameworks. |
| Author | Lu, Guangquan Wu, Zhengtian Li, Jingci Ling, Fuqing |
| Author_xml | – sequence: 1 givenname: Jingci surname: Li fullname: Li, Jingci email: dadadacc527@163.com organization: Key Lab of Education Blockchain and Intelligent Technology, Ministry of Education, Guangxi Normal University, Guilin 541004, China – sequence: 2 givenname: Guangquan orcidid: 0000-0001-6908-6269 surname: Lu fullname: Lu, Guangquan email: lugq@mailbox.gxnu.edu.cn organization: Key Lab of Education Blockchain and Intelligent Technology, Ministry of Education, Guangxi Normal University, Guilin 541004, China – sequence: 3 givenname: Zhengtian orcidid: 0000-0001-7702-5730 surname: Wu fullname: Wu, Zhengtian email: wzht8@mail.usts.edu.cn organization: Electronic and Information Engineering, Suzhou University of Science and Technology, Suzhou 215009, China – sequence: 4 givenname: Fuqing surname: Ling fullname: Ling, Fuqing email: LingFQ123@163.com organization: Key Lab of Education Blockchain and Intelligent Technology, Ministry of Education, Guangxi Normal University, Guilin 541004, China |
| BookMark | eNp9kMFOwzAMhiM0JLrBA3DrC7Q46ZI0cEITDKQhLnCOssSFTF07JRmItyfTOHHYxZb167P1eUomwzggIdcUagpU3GxqP8SaAWtqYDUodkYK2kpWCabohBQADCpgnF-QaYwbAJhLIQpy-7Lvk6--PH6XAXcBIw7JJD8O5XZ02JdrE9GVefwIZvdZmn0acbA5CpfkvDN9xKu_PiPvjw9vi6dq9bp8XtyvKsuUTJURijHkrbPMrFWn8uFG8IYb2mLHhZVKOkmpm7cCROMaKXNxds6pbYUD08wIPe61YYwxYKd3wW9N-NEU9EFeb3SW1wd5DUxn-czIf4z1R60UjO9PkndHErNSfkvQ0fpsjM4HtEm70Z-gfwFrA3YJ |
| CitedBy_id | crossref_primary_10_1007_s10115_023_01979_3 crossref_primary_10_1016_j_ins_2024_121705 crossref_primary_10_1016_j_ins_2024_120739 crossref_primary_10_1021_acsomega_5c03029 crossref_primary_10_1007_s10115_025_02494_3 crossref_primary_10_1145_3663364 crossref_primary_10_1007_s10044_025_01517_7 crossref_primary_10_26599_TST_2023_9010142 crossref_primary_10_1109_ACCESS_2024_3447233 crossref_primary_10_1016_j_neunet_2025_107418 crossref_primary_10_1016_j_knosys_2025_113675 crossref_primary_10_1016_j_ins_2024_120780 crossref_primary_10_1145_3733604 crossref_primary_10_1016_j_ins_2024_120210 crossref_primary_10_1109_TCE_2024_3352186 crossref_primary_10_1016_j_ins_2025_122448 crossref_primary_10_1016_j_neucom_2025_131378 crossref_primary_10_1109_JBHI_2024_3424848 crossref_primary_10_1016_j_neucom_2024_127390 crossref_primary_10_1016_j_ipm_2024_103932 crossref_primary_10_1016_j_knosys_2023_111132 |
| Cites_doi | 10.1016/j.inffus.2021.07.013 10.1007/s00521-018-3934-y 10.1109/TKDE.2019.2903810 10.1093/comjnl/bxab104 10.1016/j.ipm.2022.102953 10.1016/j.neunet.2020.08.021 10.1109/TNSE.2021.3115104 10.1109/TKDE.2019.2957755 10.1007/s10618-010-0210-x 10.1109/ACCESS.2020.3018033 |
| ContentType | Journal Article |
| Copyright | 2023 Elsevier Inc. |
| Copyright_xml | – notice: 2023 Elsevier Inc. |
| DBID | AAYXX CITATION |
| DOI | 10.1016/j.ins.2023.02.092 |
| DatabaseName | CrossRef |
| DatabaseTitle | CrossRef |
| DatabaseTitleList | |
| DeliveryMethod | fulltext_linktorsrc |
| Discipline | Engineering Library & Information Science |
| EISSN | 1872-6291 |
| EndPage | 453 |
| ExternalDocumentID | 10_1016_j_ins_2023_02_092 S0020025523002852 |
| 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-c297t-a6922e58dc2ab9f904736535a18ef56c797d711d486063d3773d3dc451c86d0a3 |
| ISICitedReferencesCount | 27 |
| ISICitedReferencesURI | http://www.webofscience.com/api/gateway?GWVersion=2&SrcApp=Summon&SrcAuth=ProQuest&DestLinkType=CitingArticles&DestApp=WOS_CPL&KeyUT=000954456000001&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 | Tue Nov 18 21:57:12 EST 2025 Sat Nov 29 06:56:36 EST 2025 Fri Feb 23 02:38:29 EST 2024 |
| IsPeerReviewed | true |
| IsScholarly | true |
| Keywords | Graph representation learning Graph autoencoder Unsupervised learning Multi-view learning |
| Language | English |
| LinkModel | OpenURL |
| MergedId | FETCHMERGED-LOGICAL-c297t-a6922e58dc2ab9f904736535a18ef56c797d711d486063d3773d3dc451c86d0a3 |
| ORCID | 0000-0001-6908-6269 0000-0001-7702-5730 |
| PageCount | 15 |
| ParticipantIDs | crossref_primary_10_1016_j_ins_2023_02_092 crossref_citationtrail_10_1016_j_ins_2023_02_092 elsevier_sciencedirect_doi_10_1016_j_ins_2023_02_092 |
| PublicationCentury | 2000 |
| PublicationDate | June 2023 2023-06-00 |
| PublicationDateYYYYMMDD | 2023-06-01 |
| PublicationDate_xml | – month: 06 year: 2023 text: June 2023 |
| PublicationDecade | 2020 |
| PublicationTitle | Information sciences |
| PublicationYear | 2023 |
| Publisher | Elsevier Inc |
| Publisher_xml | – name: Elsevier Inc |
| References | Tang, Liu (br0500) 2011; 23 Lu, Huang (br0070) 2021; 64 Kipf, Welling (br0200) 2016 Wu, Souza, Zhang, Fifty, Yu, Weinberger (br0250) 2019 Jin, Derr, Wang, Ma, Liu, Tang (br0290) 2021 Gonzalez, Gong, Laponogov, Veselkov, Bronstein (br0340) 2020 Veličković, Cucurull, Casanova, Romero, Liò, Bengio (br0110) 2018 Yang, Qiu, Song, Tao, Wang (br0160) 2020 Weng, Zhang, Dou (br0320) 2020; 8 Wang, Pan, Long, Zhu, Jiang (br0230) 2017 Glorot, Bengio (br0490) 2010 Li, Han, Wu (br0240) 2018 Lu, Li, Wei (br0060) 2022; 59 Ahn, Kim (br0450) 2021 Page, Brin, Motwani, Winograd (br0300) 1999 Xuan, Wang, Zhao, Yuan, Fu, Ruan, Chen (br0360) 2019; 33 Ma, Xiao, Zhou, Wang (br0350) 2018 Wang, Chen, Ma, Zhou, Ruan, Chen, Xuan (br0370) 2021; 8 Zaremba, Sutskever, Vinyals (br0030) 2014 Fan, Wang, Shi, Lu, Lin, Wang (br0390) 2020 Salha, Limnios, Hennequin, Tran, Vazirgiannis (br0330) 2019 Hasanzadeh, Hajiramezanali, Narayanan, Duffield, Zhou, Qian (br0440) 2019 Peng, Hu, Kong, Gan, Mo, Shi, Zhu (br0040) 2022 Kipf, Welling (br0100) 2017 Salha, Hennequin, Vazirgiannis (br0310) 2019 Goodfellow, Pouget-Abadie, Mirza, Xu, Warde-Farley, Ozair, Courville, Bengio (br0210) 2014; 3 Pan, Hu, Long, Jiang, Yao, Zhang (br0190) 2018 Park, Lee, Chang, Lee, Choi (br0220) 2019 Yang, Wang, Song, Yuan, Tao (br0180) 2019 Perozzi, Al-Rfou, Skiena (br0420) 2014 Wang, Yang, Liu (br0380) 2019; 32 Defferrard, Bresson, Vandergheynst (br0090) 2016; 29 Xie, Zhang, Gong, Tang, Han (br0400) 2020; 132 Wang, Zhu, Bo, Cui, Shi, Pei (br0150) 2020 Gilmer, Schoenholz, Riley, Vinyals, Dahl (br0130) 2017 Lu, Gan, Yin, Luo, Li, Zhao (br0010) 2020; 32 Bruna, Zaremba, Szlam, LeCun (br0050) 2014 Li, Muller, Thabet, Ghanem (br0260) 2019 Xu, Ruan, Körpeoglu, Kumar, Achan (br0120) ICLR 2020, Addis Ababa, Ethiopia, April 26-30, 2020 Shi, Fan, Kwok (br0430) 2020; vol. 34 Pan, Shi, Dokmanic (br0460) 2021 Xia, Pan, Du, Yin (br0470) 2014; vol. 28 Kingma, Ba (br0480) 2014 Luan, Zhao, Chang, Precup (br0270) 2019 Abadi, Barham, Chen, Chen, Davis, Dean, Devin, Ghemawat, Irving, Isard (br0410) 2016 Hassani, Khasahmadi (br0280) 2020 Gan, Hu, Mo, Kang, Peng, Zhu, Zhu (br0140) 2022 Yang, Feng, Song, Wang (br0170) 2020 Albawi, Mohammed, Al-Zawi (br0020) 2017 Zhu, Ma, Yuan, Zhu (br0080) 2022; 77 Salha (10.1016/j.ins.2023.02.092_br0330) 2019 Glorot (10.1016/j.ins.2023.02.092_br0490) 2010 Gonzalez (10.1016/j.ins.2023.02.092_br0340) Defferrard (10.1016/j.ins.2023.02.092_br0090) 2016; 29 Wang (10.1016/j.ins.2023.02.092_br0150) 2020 Wang (10.1016/j.ins.2023.02.092_br0380) 2019; 32 Tang (10.1016/j.ins.2023.02.092_br0500) 2011; 23 Park (10.1016/j.ins.2023.02.092_br0220) 2019 Kingma (10.1016/j.ins.2023.02.092_br0480) 2014 Jin (10.1016/j.ins.2023.02.092_br0290) 2021 Wang (10.1016/j.ins.2023.02.092_br0370) 2021; 8 Pan (10.1016/j.ins.2023.02.092_br0460) Yang (10.1016/j.ins.2023.02.092_br0180) 2019 Hassani (10.1016/j.ins.2023.02.092_br0280) 2020 Xuan (10.1016/j.ins.2023.02.092_br0360) 2019; 33 Lu (10.1016/j.ins.2023.02.092_br0060) 2022; 59 Hasanzadeh (10.1016/j.ins.2023.02.092_br0440) 2019 Fan (10.1016/j.ins.2023.02.092_br0390) 2020 Xia (10.1016/j.ins.2023.02.092_br0470) 2014; vol. 28 Goodfellow (10.1016/j.ins.2023.02.092_br0210) 2014; 3 Kipf (10.1016/j.ins.2023.02.092_br0200) 2016 Luan (10.1016/j.ins.2023.02.092_br0270) 2019 Yang (10.1016/j.ins.2023.02.092_br0160) 2020 Lu (10.1016/j.ins.2023.02.092_br0070) 2021; 64 Pan (10.1016/j.ins.2023.02.092_br0190) 2018 Wang (10.1016/j.ins.2023.02.092_br0230) 2017 Zhu (10.1016/j.ins.2023.02.092_br0080) 2022; 77 Shi (10.1016/j.ins.2023.02.092_br0430) 2020; vol. 34 Ahn (10.1016/j.ins.2023.02.092_br0450) 2021 Bruna (10.1016/j.ins.2023.02.092_br0050) 2014 Peng (10.1016/j.ins.2023.02.092_br0040) 2022 Zaremba (10.1016/j.ins.2023.02.092_br0030) Lu (10.1016/j.ins.2023.02.092_br0010) 2020; 32 Page (10.1016/j.ins.2023.02.092_br0300) 1999 Albawi (10.1016/j.ins.2023.02.092_br0020) 2017 Xu (10.1016/j.ins.2023.02.092_br0120) 2020 Perozzi (10.1016/j.ins.2023.02.092_br0420) 2014 Xie (10.1016/j.ins.2023.02.092_br0400) 2020; 132 Yang (10.1016/j.ins.2023.02.092_br0170) 2020 Abadi (10.1016/j.ins.2023.02.092_br0410) 2016 Kipf (10.1016/j.ins.2023.02.092_br0100) 2017 Weng (10.1016/j.ins.2023.02.092_br0320) 2020; 8 Veličković (10.1016/j.ins.2023.02.092_br0110) 2018 Wu (10.1016/j.ins.2023.02.092_br0250) 2019 Gan (10.1016/j.ins.2023.02.092_br0140) 2022 Salha (10.1016/j.ins.2023.02.092_br0310) 2019 Li (10.1016/j.ins.2023.02.092_br0260) 2019 Gilmer (10.1016/j.ins.2023.02.092_br0130) 2017 Li (10.1016/j.ins.2023.02.092_br0240) 2018 Ma (10.1016/j.ins.2023.02.092_br0350) 2018 |
| References_xml | – volume: 33 start-page: 2776 year: 2019 end-page: 2789 ident: br0360 article-title: Subgraph networks with application to structural feature space expansion publication-title: IEEE Trans. Knowl. Data Eng. – start-page: 4116 year: 2020 end-page: 4126 ident: br0280 article-title: Contrastive multi-view representation learning on graphs publication-title: International Conference on Machine Learning – volume: 132 start-page: 180 year: 2020 end-page: 189 ident: br0400 article-title: Mgat: multi-view graph attention networks publication-title: Neural Netw. – start-page: 10711 year: 2019 end-page: 10722 ident: br0440 article-title: Semi-implicit graph variational auto-encoders publication-title: Advances in Neural Information Processing Systems 32: Annual Conference on Neural Information Processing Systems 2019 – start-page: 6519 year: 2019 end-page: 6528 ident: br0220 article-title: Symmetric graph convolutional autoencoder for unsupervised graph representation learning publication-title: Proceedings of the IEEE/CVF International Conference on Computer Vision – year: 2019 ident: br0310 article-title: Keep it simple: graph autoencoders without graph convolutional networks publication-title: Workshop on Graph Representation Learning, 33rd Conference on Neural Information Processing Systems – start-page: 10943 year: 2019 end-page: 10953 ident: br0270 article-title: Break the ceiling: stronger multi-scale deep graph convolutional networks publication-title: Advances in Neural Information Processing Systems 32: Annual Conference on Neural Information Processing Systems 2019 – start-page: 3070 year: 2020 end-page: 3076 ident: br0390 article-title: One2multi graph autoencoder for multi-view graph clustering publication-title: Proceedings of the Web Conference 2020 – start-page: 249 year: 2010 end-page: 256 ident: br0490 article-title: Understanding the difficulty of training deep feedforward neural networks publication-title: Proceedings of the Thirteenth International Conference on Artificial Intelligence and Statistics, JMLR Workshop and Conference Proceedings – start-page: 4099 year: 2019 end-page: 4105 ident: br0180 article-title: SPAGAN: shortest path graph attention network publication-title: Proceedings of the Twenty-Eighth International Joint Conference on Artificial Intelligence – start-page: 148 year: 2021 end-page: 156 ident: br0290 article-title: Node similarity preserving graph convolutional networks publication-title: Proceedings of the 14th ACM International Conference on Web Search and Data Mining – volume: 8 start-page: 3478 year: 2021 end-page: 3490 ident: br0370 article-title: Sampling subgraph network with application to graph classification publication-title: IEEE Trans. Netw. Sci. Eng. – start-page: 889 year: 2017 end-page: 898 ident: br0230 article-title: Mgae: marginalized graph autoencoder for graph clustering publication-title: Proceedings of the 2017 ACM on Conference on Information and Knowledge Management – volume: 77 start-page: 53 year: 2022 end-page: 61 ident: br0080 article-title: Interpretable learning based dynamic graph convolutional networks for Alzheimer's disease analysis publication-title: Inf. Fusion – start-page: 3477 year: 2018 end-page: 3483 ident: br0350 article-title: Drug similarity integration through attentive multi-view graph auto-encoders publication-title: Proceedings of the Twenty-Seventh International Joint Conference on Artificial Intelligence, IJCAI-18, International Joint Conferences on Artificial Intelligence Organization – year: 2018 ident: br0240 article-title: Deeper insights into graph convolutional networks for semi-supervised learning publication-title: Thirty-Second AAAI Conference on Artificial Intelligence – start-page: 589 year: 2019 end-page: 598 ident: br0330 article-title: Gravity-inspired graph autoencoders for directed link prediction publication-title: Proceedings of the 28th ACM International Conference on Information and Knowledge Management – year: 2022 ident: br0140 article-title: Multigraph fusion for dynamic graph convolutional network publication-title: IEEE Trans. Neural Netw. Learn. Syst. – start-page: 1243 year: 2020 end-page: 1253 ident: br0150 article-title: Am-gcn: adaptive multi-channel graph convolutional networks publication-title: Proceedings of the 26th ACM SIGKDD International Conference on Knowledge Discovery & Data Mining – volume: vol. 34 start-page: 906 year: 2020 end-page: 913 ident: br0430 article-title: Effective decoding in graph auto-encoder using triadic closure publication-title: Proceedings of the AAAI Conference on Artificial Intelligence – volume: 32 start-page: 1116 year: 2019 end-page: 1129 ident: br0380 article-title: Gmc: graph-based multi-view clustering publication-title: IEEE Trans. Knowl. Data Eng. – year: 2022 ident: br0040 article-title: Reverse graph learning for graph neural network publication-title: IEEE Trans. Neural Netw. Learn. Syst. – volume: 23 start-page: 447 year: 2011 end-page: 478 ident: br0500 article-title: Leveraging social media networks for classification publication-title: Data Min. Knowl. Discov. – year: 2014 ident: br0030 article-title: Recurrent neural network regularization – start-page: 2827 year: 2021 end-page: 2831 ident: br0450 article-title: Variational graph normalized autoencoders publication-title: Proceedings of the 30th ACM International Conference on Information & Knowledge Management – volume: 8 start-page: 152637 year: 2020 end-page: 152645 ident: br0320 article-title: Adversarial attention-based variational graph autoencoder publication-title: IEEE Access – start-page: 701 year: 2014 end-page: 710 ident: br0420 article-title: Deepwalk: online learning of social representations publication-title: Proceedings of the 20th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining – start-page: 265 year: 2016 end-page: 283 ident: br0410 article-title: Tensorflow: a system for large-scale machine learning publication-title: 12th USENIX Symposium on Operating Systems Design and Implementation (OSDI 16) – year: 2018 ident: br0110 article-title: Graph attention networks publication-title: International Conference on Learning Representations – year: 2014 ident: br0050 article-title: Spectral networks and locally connected networks on graphs publication-title: 2nd International Conference on Learning Representations – volume: 32 start-page: 6467 year: 2020 end-page: 6480 ident: br0010 article-title: Multi-task learning using a hybrid representation for text classification publication-title: Neural Comput. Appl. – volume: 64 start-page: 1069 year: 2021 end-page: 1079 ident: br0070 article-title: Learning representation from concurrence-words graph for aspect sentiment classification publication-title: Comput. J. – start-page: 6861 year: 2019 end-page: 6871 ident: br0250 article-title: Simplifying graph convolutional networks publication-title: International Conference on Machine Learning – start-page: 1263 year: 2017 end-page: 1272 ident: br0130 article-title: Neural message passing for quantum chemistry publication-title: International Conference on Machine Learning – volume: vol. 28 year: 2014 ident: br0470 article-title: Robust multi-view spectral clustering via low-rank and sparse decomposition publication-title: Proceedings of the AAAI Conference on Artificial Intelligence – year: 1999 ident: br0300 article-title: The pagerank citation ranking: Bringing order to the web – year: 2020 ident: br0340 article-title: Graph attentional autoencoder for anticancer hyperfood prediction – year: 2021 ident: br0460 article-title: Neural link prediction with walk pooling – volume: 59 year: 2022 ident: br0060 article-title: Aspect sentiment analysis with heterogeneous graph neural networks publication-title: Inf. Process. Manag. – year: 2017 ident: br0100 article-title: Semi-supervised classification with graph convolutional networks publication-title: International Conference on Learning Representations (ICLR) – volume: 3 year: 2014 ident: br0210 article-title: Generative adversarial networks publication-title: Adv. Neural Inf. Process. Syst. – start-page: 9267 year: 2019 end-page: 9276 ident: br0260 article-title: Deepgcns: can gcns go as deep as cnns? publication-title: Proceedings of the IEEE/CVF International Conference on Computer Vision – year: 2014 ident: br0480 article-title: Adam: a method for stochastic optimization publication-title: Comput. Sci. – start-page: 20286 year: 2020 end-page: 20296 ident: br0170 article-title: Factorizable graph convolutional networks publication-title: Advances in Neural Information Processing Systems, vol. 33 – start-page: 2609 year: 2018 end-page: 2615 ident: br0190 article-title: Adversarially regularized graph autoencoder for graph embedding publication-title: Proceedings of the Twenty-Seventh International Joint Conference on Artificial Intelligence – start-page: 1 year: 2017 end-page: 6 ident: br0020 article-title: Understanding of a convolutional neural network publication-title: 2017 International Conference on Engineering and Technology (ICET) – year: 2020 ident: br0160 article-title: Distilling knowledge from graph convolutional networks publication-title: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) – volume: 29 start-page: 3844 year: 2016 end-page: 3852 ident: br0090 article-title: Convolutional neural networks on graphs with fast localized spectral filtering publication-title: Adv. Neural Inf. Process. Syst. – year: ICLR 2020, Addis Ababa, Ethiopia, April 26-30, 2020 ident: br0120 article-title: Inductive representation learning on temporal graphs publication-title: 8th International Conference on Learning Representations – year: 2016 ident: br0200 article-title: Variational graph auto-encoders publication-title: NIPS Workshop on Bayesian Deep Learning – year: 2020 ident: 10.1016/j.ins.2023.02.092_br0120 article-title: Inductive representation learning on temporal graphs – year: 2022 ident: 10.1016/j.ins.2023.02.092_br0040 article-title: Reverse graph learning for graph neural network publication-title: IEEE Trans. Neural Netw. Learn. Syst. – start-page: 20286 year: 2020 ident: 10.1016/j.ins.2023.02.092_br0170 article-title: Factorizable graph convolutional networks – start-page: 6519 year: 2019 ident: 10.1016/j.ins.2023.02.092_br0220 article-title: Symmetric graph convolutional autoencoder for unsupervised graph representation learning – start-page: 148 year: 2021 ident: 10.1016/j.ins.2023.02.092_br0290 article-title: Node similarity preserving graph convolutional networks – volume: 77 start-page: 53 year: 2022 ident: 10.1016/j.ins.2023.02.092_br0080 article-title: Interpretable learning based dynamic graph convolutional networks for Alzheimer's disease analysis publication-title: Inf. Fusion doi: 10.1016/j.inffus.2021.07.013 – start-page: 9267 year: 2019 ident: 10.1016/j.ins.2023.02.092_br0260 article-title: Deepgcns: can gcns go as deep as cnns? – volume: 32 start-page: 6467 year: 2020 ident: 10.1016/j.ins.2023.02.092_br0010 article-title: Multi-task learning using a hybrid representation for text classification publication-title: Neural Comput. Appl. doi: 10.1007/s00521-018-3934-y – start-page: 2827 year: 2021 ident: 10.1016/j.ins.2023.02.092_br0450 article-title: Variational graph normalized autoencoders – ident: 10.1016/j.ins.2023.02.092_br0340 – volume: 32 start-page: 1116 issue: 6 year: 2019 ident: 10.1016/j.ins.2023.02.092_br0380 article-title: Gmc: graph-based multi-view clustering publication-title: IEEE Trans. Knowl. Data Eng. doi: 10.1109/TKDE.2019.2903810 – volume: 64 start-page: 1069 issue: 7 year: 2021 ident: 10.1016/j.ins.2023.02.092_br0070 article-title: Learning representation from concurrence-words graph for aspect sentiment classification publication-title: Comput. J. doi: 10.1093/comjnl/bxab104 – ident: 10.1016/j.ins.2023.02.092_br0460 – year: 2017 ident: 10.1016/j.ins.2023.02.092_br0100 article-title: Semi-supervised classification with graph convolutional networks – year: 1999 ident: 10.1016/j.ins.2023.02.092_br0300 – volume: 59 issue: 4 year: 2022 ident: 10.1016/j.ins.2023.02.092_br0060 article-title: Aspect sentiment analysis with heterogeneous graph neural networks publication-title: Inf. Process. Manag. doi: 10.1016/j.ipm.2022.102953 – start-page: 2609 year: 2018 ident: 10.1016/j.ins.2023.02.092_br0190 article-title: Adversarially regularized graph autoencoder for graph embedding – year: 2018 ident: 10.1016/j.ins.2023.02.092_br0240 article-title: Deeper insights into graph convolutional networks for semi-supervised learning – volume: 132 start-page: 180 year: 2020 ident: 10.1016/j.ins.2023.02.092_br0400 article-title: Mgat: multi-view graph attention networks publication-title: Neural Netw. doi: 10.1016/j.neunet.2020.08.021 – start-page: 265 year: 2016 ident: 10.1016/j.ins.2023.02.092_br0410 article-title: Tensorflow: a system for large-scale machine learning – start-page: 1 year: 2017 ident: 10.1016/j.ins.2023.02.092_br0020 article-title: Understanding of a convolutional neural network – start-page: 1263 year: 2017 ident: 10.1016/j.ins.2023.02.092_br0130 article-title: Neural message passing for quantum chemistry – volume: 3 issue: 06 year: 2014 ident: 10.1016/j.ins.2023.02.092_br0210 article-title: Generative adversarial networks publication-title: Adv. Neural Inf. Process. Syst. – start-page: 589 year: 2019 ident: 10.1016/j.ins.2023.02.092_br0330 article-title: Gravity-inspired graph autoencoders for directed link prediction – volume: 8 start-page: 3478 issue: 4 year: 2021 ident: 10.1016/j.ins.2023.02.092_br0370 article-title: Sampling subgraph network with application to graph classification publication-title: IEEE Trans. Netw. Sci. Eng. doi: 10.1109/TNSE.2021.3115104 – year: 2014 ident: 10.1016/j.ins.2023.02.092_br0480 article-title: Adam: a method for stochastic optimization publication-title: Comput. Sci. – start-page: 701 year: 2014 ident: 10.1016/j.ins.2023.02.092_br0420 article-title: Deepwalk: online learning of social representations – year: 2016 ident: 10.1016/j.ins.2023.02.092_br0200 article-title: Variational graph auto-encoders – volume: 33 start-page: 2776 issue: 6 year: 2019 ident: 10.1016/j.ins.2023.02.092_br0360 article-title: Subgraph networks with application to structural feature space expansion publication-title: IEEE Trans. Knowl. Data Eng. doi: 10.1109/TKDE.2019.2957755 – ident: 10.1016/j.ins.2023.02.092_br0030 – start-page: 3477 year: 2018 ident: 10.1016/j.ins.2023.02.092_br0350 article-title: Drug similarity integration through attentive multi-view graph auto-encoders – year: 2019 ident: 10.1016/j.ins.2023.02.092_br0310 article-title: Keep it simple: graph autoencoders without graph convolutional networks – volume: vol. 34 start-page: 906 year: 2020 ident: 10.1016/j.ins.2023.02.092_br0430 article-title: Effective decoding in graph auto-encoder using triadic closure – start-page: 249 year: 2010 ident: 10.1016/j.ins.2023.02.092_br0490 article-title: Understanding the difficulty of training deep feedforward neural networks – start-page: 10943 year: 2019 ident: 10.1016/j.ins.2023.02.092_br0270 article-title: Break the ceiling: stronger multi-scale deep graph convolutional networks – volume: 29 start-page: 3844 year: 2016 ident: 10.1016/j.ins.2023.02.092_br0090 article-title: Convolutional neural networks on graphs with fast localized spectral filtering publication-title: Adv. Neural Inf. Process. Syst. – start-page: 3070 year: 2020 ident: 10.1016/j.ins.2023.02.092_br0390 article-title: One2multi graph autoencoder for multi-view graph clustering – year: 2014 ident: 10.1016/j.ins.2023.02.092_br0050 article-title: Spectral networks and locally connected networks on graphs – start-page: 4116 year: 2020 ident: 10.1016/j.ins.2023.02.092_br0280 article-title: Contrastive multi-view representation learning on graphs – year: 2018 ident: 10.1016/j.ins.2023.02.092_br0110 article-title: Graph attention networks – start-page: 1243 year: 2020 ident: 10.1016/j.ins.2023.02.092_br0150 article-title: Am-gcn: adaptive multi-channel graph convolutional networks – start-page: 889 year: 2017 ident: 10.1016/j.ins.2023.02.092_br0230 article-title: Mgae: marginalized graph autoencoder for graph clustering – volume: vol. 28 year: 2014 ident: 10.1016/j.ins.2023.02.092_br0470 article-title: Robust multi-view spectral clustering via low-rank and sparse decomposition – year: 2020 ident: 10.1016/j.ins.2023.02.092_br0160 article-title: Distilling knowledge from graph convolutional networks – start-page: 4099 year: 2019 ident: 10.1016/j.ins.2023.02.092_br0180 article-title: SPAGAN: shortest path graph attention network – volume: 23 start-page: 447 issue: 3 year: 2011 ident: 10.1016/j.ins.2023.02.092_br0500 article-title: Leveraging social media networks for classification publication-title: Data Min. Knowl. Discov. doi: 10.1007/s10618-010-0210-x – year: 2022 ident: 10.1016/j.ins.2023.02.092_br0140 article-title: Multigraph fusion for dynamic graph convolutional network publication-title: IEEE Trans. Neural Netw. Learn. Syst. – start-page: 10711 year: 2019 ident: 10.1016/j.ins.2023.02.092_br0440 article-title: Semi-implicit graph variational auto-encoders – start-page: 6861 year: 2019 ident: 10.1016/j.ins.2023.02.092_br0250 article-title: Simplifying graph convolutional networks – volume: 8 start-page: 152637 year: 2020 ident: 10.1016/j.ins.2023.02.092_br0320 article-title: Adversarial attention-based variational graph autoencoder publication-title: IEEE Access doi: 10.1109/ACCESS.2020.3018033 |
| SSID | ssj0004766 |
| Score | 2.5585968 |
| Snippet | Graph representation learning is a hot topic in non-Euclidean data in various domains, such as social networks, biological networks, etc. When some data labels... |
| SourceID | crossref elsevier |
| SourceType | Enrichment Source Index Database Publisher |
| StartPage | 439 |
| SubjectTerms | Graph autoencoder Graph representation learning Multi-view learning Unsupervised learning |
| Title | Multi-view representation model based on graph autoencoder |
| URI | https://dx.doi.org/10.1016/j.ins.2023.02.092 |
| Volume | 632 |
| WOSCitedRecordID | wos000954456000001&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: Elsevier SD Freedom Collection Journals 2021 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/eLvHCXMwtV1Lb9QwELbQlgMcKiggSinyAXFgFSlxHDvmVqFWUK0qDkWsuESO7ZSuUPpKqv78jl9JWmgFSFysXWu9j5lvPTP2zDcIvSWqFoQZG-TUTUJVzZKaU5WQRuqmSYUm0rHrL_jBQblcii8h3fbCtRPgbVteXYnT_6pqmANl29LZv1D38KYwAY9B6TCC2mH8I8W7ktrEFaQ4xspYXdT6rjdza7e0vSNwXNVz2XcnlsxShzTdVUxtH8oa58FKDt73wmUA7IPRU8fDXO9O2HvZHp31I-K-uenvP0x71E2AuAidVPb6s2g6w8kDyccMKX8cFktibmRsWv8zsYGKNzB-Vy05SRjxbbnitsvCuabfOKmnNAo2mHoC4V-2d3_SsIKYxDKtk9zRrfpeerdYs-0ltIuXIMQCF6oAK71GeCHKGVrb-by73B-LZ7m_0I7fO159uyTAWx_0e-dl4pAcPkHrIZLAOx4BT9ED026gxxN-yQ20HapS8Ds80ScO-_kz9GHECr6JFeywgh1WMDx1WMETrDxHX_d2Dz9-SkIzjUQRwbtEMkGIKUqtiKxFI-B356zIC5mVpimY4oJrnmXaNiVjuc45h0ErWmSqZDqV-Qs0a09a8xLhnPHMcM5UpjWlTSlJYSDMNixVilLZbKI0SqlSgWneNjz5WcWUwlUFgq2sYKuUVCDYTfR-WHLqaVbuezGNoq_CP8D7fxXg5O5lr_5t2RZ6NIL_NZp1573ZRg_VZXd8cf4moOkaENWLKw |
| 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=Multi-view+representation+model+based+on+graph+autoencoder&rft.jtitle=Information+sciences&rft.au=Li%2C+Jingci&rft.au=Lu%2C+Guangquan&rft.au=Wu%2C+Zhengtian&rft.au=Ling%2C+Fuqing&rft.date=2023-06-01&rft.pub=Elsevier+Inc&rft.issn=0020-0255&rft.eissn=1872-6291&rft.volume=632&rft.spage=439&rft.epage=453&rft_id=info:doi/10.1016%2Fj.ins.2023.02.092&rft.externalDocID=S0020025523002852 |
| 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 |