Optimizing Variational Graph Autoencoder for Community Detection with Dual Optimization
Variational Graph Autoencoder (VGAE) has recently gained traction for learning representations on graphs. Its inception has allowed models to achieve state-of-the-art performance for challenging tasks such as link prediction, rating prediction, and node clustering. However, a fundamental flaw exists...
Uloženo v:
| Vydáno v: | Entropy (Basel, Switzerland) Ročník 22; číslo 2; s. 197 |
|---|---|
| Hlavní autoři: | , , |
| Médium: | Journal Article |
| Jazyk: | angličtina |
| Vydáno: |
MDPI
01.02.2020
MDPI AG |
| Témata: | |
| ISSN: | 1099-4300, 1099-4300 |
| On-line přístup: | Získat plný text |
| Tagy: |
Přidat tag
Žádné tagy, Buďte první, kdo vytvoří štítek k tomuto záznamu!
|
| Abstract | Variational Graph Autoencoder (VGAE) has recently gained traction for learning representations on graphs. Its inception has allowed models to achieve state-of-the-art performance for challenging tasks such as link prediction, rating prediction, and node clustering. However, a fundamental flaw exists in Variational Autoencoder (VAE)-based approaches. Specifically, merely minimizing the loss of VAE increases the deviation from its primary objective. Focusing on Variational Graph Autoencoder for Community Detection (VGAECD) we found that optimizing the loss using the stochastic gradient descent often leads to sub-optimal community structure especially when initialized poorly. We address this shortcoming by introducing a dual optimization procedure. This procedure aims to guide the optimization process and encourage learning of the primary objective. Additionally, we linearize the encoder to reduce the number of learning parameters. The outcome is a robust algorithm that outperforms its predecessor. |
|---|---|
| AbstractList | Variational Graph Autoencoder (VGAE) has recently gained traction for learning representations on graphs. Its inception has allowed models to achieve state-of-the-art performance for challenging tasks such as link prediction, rating prediction, and node clustering. However, a fundamental flaw exists in Variational Autoencoder (VAE)-based approaches. Specifically, merely minimizing the loss of VAE increases the deviation from its primary objective. Focusing on Variational Graph Autoencoder for Community Detection (VGAECD) we found that optimizing the loss using the stochastic gradient descent often leads to sub-optimal community structure especially when initialized poorly. We address this shortcoming by introducing a dual optimization procedure. This procedure aims to guide the optimization process and encourage learning of the primary objective. Additionally, we linearize the encoder to reduce the number of learning parameters. The outcome is a robust algorithm that outperforms its predecessor.Variational Graph Autoencoder (VGAE) has recently gained traction for learning representations on graphs. Its inception has allowed models to achieve state-of-the-art performance for challenging tasks such as link prediction, rating prediction, and node clustering. However, a fundamental flaw exists in Variational Autoencoder (VAE)-based approaches. Specifically, merely minimizing the loss of VAE increases the deviation from its primary objective. Focusing on Variational Graph Autoencoder for Community Detection (VGAECD) we found that optimizing the loss using the stochastic gradient descent often leads to sub-optimal community structure especially when initialized poorly. We address this shortcoming by introducing a dual optimization procedure. This procedure aims to guide the optimization process and encourage learning of the primary objective. Additionally, we linearize the encoder to reduce the number of learning parameters. The outcome is a robust algorithm that outperforms its predecessor. Variational Graph Autoencoder (VGAE) has recently gained traction for learning representations on graphs. Its inception has allowed models to achieve state-of-the-art performance for challenging tasks such as link prediction, rating prediction, and node clustering. However, a fundamental flaw exists in Variational Autoencoder (VAE)-based approaches. Specifically, merely minimizing the loss of VAE increases the deviation from its primary objective. Focusing on Variational Graph Autoencoder for Community Detection (VGAECD) we found that optimizing the loss using the stochastic gradient descent often leads to sub-optimal community structure especially when initialized poorly. We address this shortcoming by introducing a dual optimization procedure. This procedure aims to guide the optimization process and encourage learning of the primary objective. Additionally, we linearize the encoder to reduce the number of learning parameters. The outcome is a robust algorithm that outperforms its predecessor. |
| Author | Murata, Tsuyoshi Choong, Jun Jin Liu, Xin |
| AuthorAffiliation | 2 National Institute of Advanced Industrial Science and Technology, Tokyo 135-0064, Japan; xin.liu@aist.go.jp 1 Department of Computer Science, Tokyo Institute of Technology, Tokyo 152-8552, Japan; murata@c.titech.ac.jp |
| AuthorAffiliation_xml | – name: 1 Department of Computer Science, Tokyo Institute of Technology, Tokyo 152-8552, Japan; murata@c.titech.ac.jp – name: 2 National Institute of Advanced Industrial Science and Technology, Tokyo 135-0064, Japan; xin.liu@aist.go.jp |
| Author_xml | – sequence: 1 givenname: Jun Jin orcidid: 0000-0001-6078-1636 surname: Choong fullname: Choong, Jun Jin – sequence: 2 givenname: Xin orcidid: 0000-0002-2336-7409 surname: Liu fullname: Liu, Xin – sequence: 3 givenname: Tsuyoshi surname: Murata fullname: Murata, Tsuyoshi |
| BookMark | eNptkU1v1DAQhi1U1C964B_kCIel_nZyQaq2UCpV6oWWozVxxruuEntxnKLy60l3VxVFnGz5feaZkeeEHMQUkZD3jH4SoqHnyDnllDXmDTlmtGkWUlB68Nf9iJyM4wOlXHCmD8mRELxWjeHH5MftpoQh_A5xVd1DDlBCitBXVxk26-piKgmjSx3myqdcLdMwTDGUp-oSC7pntvoVyrq6nOaavWqreEfeeuhHPNufp-Tu65fvy2-Lm9ur6-XFzcJJzcsC0NWuNc6gU9oz3XoONXCtUTNvvKINCBTcaejaRkvwErmmruvmnEqO4pRc77xdgge7yWGA_GQTBLt9SHllIZfgerQGuPAC0VHPpKJYK9PyVnRU1VwqbGbX551rM7UDdg5jydC_kr5OYljbVXq0RjGtuZoFH_aCnH5OOBY7hNFh30PENI2WS10LSY1hM_pxh7qcxjGjf2nDqH1eqn1Z6sye_8O6ULa_PE8R-v9U_AEHoaX4 |
| CitedBy_id | crossref_primary_10_3390_e23020192 crossref_primary_10_1007_s12652_024_04871_2 crossref_primary_10_1155_2023_9011738 crossref_primary_10_1016_j_neunet_2022_06_021 crossref_primary_10_1016_j_eswa_2023_119775 crossref_primary_10_1109_ACCESS_2023_3257021 crossref_primary_10_3390_e23040403 crossref_primary_10_1007_s00521_025_11028_5 crossref_primary_10_1016_j_cageo_2024_105621 crossref_primary_10_1007_s00202_024_02520_7 crossref_primary_10_3390_e24020276 crossref_primary_10_3390_e22080819 crossref_primary_10_3390_info15090568 crossref_primary_10_3390_electronics12112437 crossref_primary_10_3390_app11167179 |
| Cites_doi | 10.1109/TBDATA.2016.2631512 10.1073/pnas.98.2.404 10.1007/978-1-4614-7163-9_239-1 10.1103/PhysRevE.69.026113 10.1016/j.physrep.2016.09.002 10.1145/1134271.1134277 10.1073/pnas.122653799 10.1145/2939672.2939754 10.24963/ijcai.2018/362 10.1023/A:1009953814988 10.1088/1742-5468/2008/10/P10008 10.1145/3159652.3159706 10.1073/pnas.0601602103 10.1103/PhysRevE.81.046106 10.1109/TKDE.2018.2846555 10.1016/j.engappai.2019.08.003 10.1103/PhysRevE.78.046110 10.1007/s003579900004 10.1145/2736277.2741093 10.1145/2287076.2287104 10.1086/jar.33.4.3629752 10.1145/990308.990313 10.1109/ICDM.2018.00022 10.1103/PhysRevE.85.056109 10.1145/2623330.2623732 10.1023/A:1007665907178 10.1103/PhysRevE.76.036106 10.1111/j.2517-6161.1977.tb01600.x 10.1371/journal.pone.0018209 10.1109/TII.2019.2908056 10.1073/pnas.0605965104 10.1145/3289600.3291029 10.1109/TIT.2015.2490670 10.1609/aaai.v28i1.8916 10.1007/s10115-013-0693-z 10.1109/TPAMI.2013.50 10.1016/j.physrep.2009.11.002 10.1007/978-3-540-87700-4_107 10.1145/2806416.2806512 10.1103/PhysRevE.83.016107 10.1214/09-SS057 10.1103/PhysRevE.90.012805 10.1007/11569596_31 10.1145/168304.168306 10.1109/FOCS.2015.47 10.1088/1742-5468/2005/09/P09008 |
| ContentType | Journal Article |
| Copyright | 2020 by the authors. 2020 |
| Copyright_xml | – notice: 2020 by the authors. 2020 |
| DBID | AAYXX CITATION 7X8 5PM DOA |
| DOI | 10.3390/e22020197 |
| DatabaseName | CrossRef MEDLINE - Academic PubMed Central (Full Participant titles) DOAJ Directory of Open Access Journals |
| DatabaseTitle | CrossRef MEDLINE - Academic |
| DatabaseTitleList | MEDLINE - Academic CrossRef |
| Database_xml | – sequence: 1 dbid: DOA name: Directory of Open Access Journals url: https://www.doaj.org/ sourceTypes: Open Website – sequence: 2 dbid: 7X8 name: MEDLINE - Academic url: https://search.proquest.com/medline sourceTypes: Aggregation Database |
| DeliveryMethod | fulltext_linktorsrc |
| EISSN | 1099-4300 |
| ExternalDocumentID | oai_doaj_org_article_7a23f3eec0f1450e857b2b3d058245e9 PMC7516625 10_3390_e22020197 |
| GroupedDBID | 29G 2WC 5GY 5VS 8FE 8FG AADQD AAFWJ AAYXX ABDBF ABJCF ACIWK ACUHS ADBBV AEGXH AENEX AFFHD AFKRA AFPKN AFZYC ALMA_UNASSIGNED_HOLDINGS BCNDV BENPR BGLVJ CCPQU CITATION CS3 DU5 E3Z ESX F5P GROUPED_DOAJ GX1 HCIFZ HH5 IAO J9A KQ8 L6V M7S MODMG M~E OK1 OVT PGMZT PHGZM PHGZT PIMPY PQGLB PROAC PTHSS RNS RPM TR2 TUS XSB ~8M 7X8 5PM |
| ID | FETCH-LOGICAL-c462t-aec8cb7c7ec56f16bf2a8a266e61f7f509a3e32c6adb964af4e260cdde61042e3 |
| IEDL.DBID | DOA |
| ISICitedReferencesCount | 18 |
| ISICitedReferencesURI | http://www.webofscience.com/api/gateway?GWVersion=2&SrcApp=Summon&SrcAuth=ProQuest&DestLinkType=CitingArticles&DestApp=WOS_CPL&KeyUT=000521371400057&url=https%3A%2F%2Fcvtisr.summon.serialssolutions.com%2F%23%21%2Fsearch%3Fho%3Df%26include.ft.matches%3Dt%26l%3Dnull%26q%3D |
| ISSN | 1099-4300 |
| IngestDate | Fri Oct 03 12:27:29 EDT 2025 Tue Nov 04 01:59:38 EST 2025 Sun Nov 09 10:59:27 EST 2025 Sat Nov 29 07:14:09 EST 2025 Tue Nov 18 22:13:38 EST 2025 |
| IsDoiOpenAccess | true |
| IsOpenAccess | true |
| IsPeerReviewed | true |
| IsScholarly | true |
| Issue | 2 |
| Language | English |
| License | Licensee MDPI, Basel, Switzerland. This article is an open access article distributed under the terms and conditions of the Creative Commons Attribution (CC BY) license (http://creativecommons.org/licenses/by/4.0/). |
| LinkModel | DirectLink |
| MergedId | FETCHMERGED-LOGICAL-c462t-aec8cb7c7ec56f16bf2a8a266e61f7f509a3e32c6adb964af4e260cdde61042e3 |
| Notes | ObjectType-Article-1 SourceType-Scholarly Journals-1 ObjectType-Feature-2 content type line 23 |
| ORCID | 0000-0002-2336-7409 0000-0001-6078-1636 |
| OpenAccessLink | https://doaj.org/article/7a23f3eec0f1450e857b2b3d058245e9 |
| PMID | 33285972 |
| PQID | 2468340771 |
| PQPubID | 23479 |
| ParticipantIDs | doaj_primary_oai_doaj_org_article_7a23f3eec0f1450e857b2b3d058245e9 pubmedcentral_primary_oai_pubmedcentral_nih_gov_7516625 proquest_miscellaneous_2468340771 crossref_primary_10_3390_e22020197 crossref_citationtrail_10_3390_e22020197 |
| PublicationCentury | 2000 |
| PublicationDate | 2020-02-01 |
| PublicationDateYYYYMMDD | 2020-02-01 |
| PublicationDate_xml | – month: 02 year: 2020 text: 2020-02-01 day: 01 |
| PublicationDecade | 2020 |
| PublicationTitle | Entropy (Basel, Switzerland) |
| PublicationYear | 2020 |
| Publisher | MDPI MDPI AG |
| Publisher_xml | – name: MDPI – name: MDPI AG |
| References | ref_50 Snijders (ref_18) 1997; 14 Good (ref_40) 2010; 81 ref_14 Dempster (ref_65) 1977; 39 ref_13 ref_57 ref_12 Blondel (ref_38) 2008; 2008 Newman (ref_2) 2001; 98 ref_11 Fortunato (ref_39) 2007; 104 ref_10 ref_53 ref_52 ref_51 Seshadhri (ref_55) 2012; 85 ref_17 Kannan (ref_37) 2004; 51 ref_16 Fortunato (ref_62) 2016; 659 Airoldi (ref_58) 2008; 9 Higgins (ref_64) 2017; 2 ref_60 Jordan (ref_29) 1999; 37 ref_25 ref_24 ref_68 ref_23 ref_67 ref_22 ref_66 Bengio (ref_9) 2013; 35 ref_21 ref_20 ref_63 Danon (ref_72) 2005; 2005 Newman (ref_73) 2004; 69 Larremore (ref_59) 2014; 90 ref_28 ref_27 ref_26 Leskovec (ref_54) 2010; 11 Pearl (ref_15) 2009; 3 Fortunato (ref_7) 2010; 486 Karrer (ref_19) 2011; 83 ref_36 ref_34 ref_33 Yang (ref_71) 2015; 42 ref_31 ref_30 Raghavan (ref_41) 2007; 76 Abbe (ref_61) 2016; 62 Harper (ref_3) 2016; 5 Guo (ref_46) 2018; 31 Girvan (ref_35) 2002; 99 Murphy (ref_32) 2010; 19 Lancichinetti (ref_56) 2008; 78 Zachary (ref_1) 1977; 33 Newman (ref_8) 2006; 103 Su (ref_4) 2019; 15 ref_45 ref_43 ref_42 McCallum (ref_70) 2000; 3 Agreste (ref_44) 2017; 3 Moscato (ref_47) 2019; 85 ref_49 ref_48 Sen (ref_69) 2008; 29 ref_5 ref_6 |
| References_xml | – volume: 3 start-page: 289 year: 2017 ident: ref_44 article-title: An Empirical Comparison of Algorithms to Find Communities in Directed Graphs and Their Application in Web Data Analytics publication-title: IEEE Trans. Big Data doi: 10.1109/TBDATA.2016.2631512 – volume: 98 start-page: 404 year: 2001 ident: ref_2 article-title: The Structure of Scientific Collaboration Networks publication-title: Proc. Natl. Acad. Sci. USA doi: 10.1073/pnas.98.2.404 – ident: ref_49 – ident: ref_57 doi: 10.1007/978-1-4614-7163-9_239-1 – ident: ref_5 – volume: 69 start-page: 026113 year: 2004 ident: ref_73 article-title: Finding and Evaluating Community Structure in Networks publication-title: Phys. Rev. E doi: 10.1103/PhysRevE.69.026113 – ident: ref_26 – ident: ref_51 – volume: 659 start-page: 1 year: 2016 ident: ref_62 article-title: Community Detection in Networks: A User Guide publication-title: Phys. Rep. doi: 10.1016/j.physrep.2016.09.002 – ident: ref_68 doi: 10.1145/1134271.1134277 – volume: 99 start-page: 7821 year: 2002 ident: ref_35 article-title: Community Structure in Social and Biological Networks publication-title: Proc. Natl. Acad. Sci. USA doi: 10.1073/pnas.122653799 – ident: ref_11 doi: 10.1145/2939672.2939754 – ident: ref_23 doi: 10.24963/ijcai.2018/362 – ident: ref_16 – volume: 3 start-page: 127 year: 2000 ident: ref_70 article-title: Automating the Construction of Internet Portals with Machine Learning publication-title: Inf. Retr. doi: 10.1023/A:1009953814988 – volume: 2008 start-page: P10008 year: 2008 ident: ref_38 article-title: Fast Unfolding of Communities in Large Networks publication-title: J. Stat. Mech. Theory Exp. doi: 10.1088/1742-5468/2008/10/P10008 – ident: ref_52 doi: 10.1145/3159652.3159706 – volume: 103 start-page: 8577 year: 2006 ident: ref_8 article-title: Modularity and Community Structure in Networks publication-title: Proc. Natl. Acad. Sci. USA doi: 10.1073/pnas.0601602103 – volume: 81 start-page: 046106 year: 2010 ident: ref_40 article-title: The Performance of Modularity Maximization in Practical Contexts publication-title: Phys. Rev. E doi: 10.1103/PhysRevE.81.046106 – volume: 31 start-page: 706 year: 2018 ident: ref_46 article-title: CFOND: Consensus Factorization for Co-Clustering Networked Data publication-title: IEEE Trans. Knowl. Data Eng. doi: 10.1109/TKDE.2018.2846555 – volume: 19 start-page: 45 year: 2010 ident: ref_32 article-title: Introducing the Graph 500 publication-title: Cray Users Group (CUG) – volume: 85 start-page: 773 year: 2019 ident: ref_47 article-title: Community Detection Based on Game Theory publication-title: Eng. Appl. Artif. Intell. doi: 10.1016/j.engappai.2019.08.003 – ident: ref_31 – volume: 78 start-page: 046110 year: 2008 ident: ref_56 article-title: Benchmark Graphs for Testing Community Detection Algorithms publication-title: Phys. Rev. E doi: 10.1103/PhysRevE.78.046110 – ident: ref_27 – volume: 14 start-page: 75 year: 1997 ident: ref_18 article-title: Estimation and Prediction for Stochastic Blockmodels for Graphs with Latent Block Structure publication-title: J. Classif. doi: 10.1007/s003579900004 – ident: ref_48 – volume: 9 start-page: 1981 year: 2008 ident: ref_58 article-title: Mixed Membership Stochastic Blockmodels publication-title: J. Mach. Learn. Res. – ident: ref_10 – ident: ref_13 doi: 10.1145/2736277.2741093 – ident: ref_33 doi: 10.1145/2287076.2287104 – volume: 33 start-page: 452 year: 1977 ident: ref_1 article-title: An Information Flow Model for Conflict and Fission in Small Groups publication-title: J. Anthropol. Res. doi: 10.1086/jar.33.4.3629752 – volume: 51 start-page: 497 year: 2004 ident: ref_37 article-title: On Clusterings: Good, Bad and Spectral publication-title: J. ACM doi: 10.1145/990308.990313 – ident: ref_66 – ident: ref_17 – ident: ref_20 – ident: ref_22 doi: 10.1109/ICDM.2018.00022 – ident: ref_28 – volume: 11 start-page: 985 year: 2010 ident: ref_54 article-title: Kronecker Graphs: An Approach to Modeling Networks publication-title: J. Mach. Learn. Res. – ident: ref_30 – volume: 85 start-page: 056109 year: 2012 ident: ref_55 article-title: Community Structure and Scale-Free Collections of Erdos-Rényi Graphs publication-title: Phys. Rev. E doi: 10.1103/PhysRevE.85.056109 – volume: 29 start-page: 93 year: 2008 ident: ref_69 article-title: Collective Classification in Network Data publication-title: AI Mag. – ident: ref_24 – ident: ref_34 – ident: ref_12 doi: 10.1145/2623330.2623732 – volume: 37 start-page: 183 year: 1999 ident: ref_29 article-title: An Introduction to Variational Methods for Graphical Models publication-title: Mach. Learn. doi: 10.1023/A:1007665907178 – volume: 76 start-page: 036106 year: 2007 ident: ref_41 article-title: Near Linear Time Algorithm to Detect Community Structures in Large-Scale Networks publication-title: Phys. Rev. E doi: 10.1103/PhysRevE.76.036106 – volume: 2 start-page: 6 year: 2017 ident: ref_64 article-title: Beta-VAE: Learning Basic Visual Concepts with a Constrained Variational Framework publication-title: ICLR – volume: 39 start-page: 1 year: 1977 ident: ref_65 article-title: Maximum Likelihood from Incomplete Data via the EM Algorithm publication-title: J. R. Stat. Soc. Ser. B (Methodol.) doi: 10.1111/j.2517-6161.1977.tb01600.x – ident: ref_43 doi: 10.1371/journal.pone.0018209 – volume: 15 start-page: 4266 year: 2019 ident: ref_4 article-title: An Edge Intelligence Empowered Recommender System Enabling Cultural Heritage Applications publication-title: IEEE Trans. Ind. Inform. doi: 10.1109/TII.2019.2908056 – volume: 104 start-page: 36 year: 2007 ident: ref_39 article-title: Resolution Limit in Community Detection publication-title: Proc. Natl. Acad. Sci. USA doi: 10.1073/pnas.0605965104 – ident: ref_14 – ident: ref_63 – ident: ref_21 – volume: 5 start-page: 19 year: 2016 ident: ref_3 article-title: The Movielens Datasets: History and Context publication-title: ACM Trans. Interact. Intell. Syst. (TiiS) – ident: ref_53 doi: 10.1145/3289600.3291029 – volume: 62 start-page: 471 year: 2016 ident: ref_61 article-title: Exact Recovery in the Stochastic Block Model publication-title: IEEE Trans. Inf. Theory doi: 10.1109/TIT.2015.2490670 – ident: ref_50 doi: 10.1609/aaai.v28i1.8916 – ident: ref_6 – volume: 42 start-page: 181 year: 2015 ident: ref_71 article-title: Defining and Evaluating Network Communities Based on Ground-Truth publication-title: Knowl. Inf. Syst. doi: 10.1007/s10115-013-0693-z – volume: 35 start-page: 1798 year: 2013 ident: ref_9 article-title: Representation Learning: A Review and New Perspectives publication-title: IEEE Trans. Pattern Anal. Mach. Intell. doi: 10.1109/TPAMI.2013.50 – volume: 486 start-page: 75 year: 2010 ident: ref_7 article-title: Community Detection in Graphs publication-title: Phys. Rep. doi: 10.1016/j.physrep.2009.11.002 – ident: ref_25 – ident: ref_36 doi: 10.1007/978-3-540-87700-4_107 – ident: ref_45 doi: 10.1145/2806416.2806512 – volume: 83 start-page: 016107 year: 2011 ident: ref_19 article-title: Stochastic Blockmodels and Community Structure in Networks publication-title: Phys. Rev. E doi: 10.1103/PhysRevE.83.016107 – volume: 3 start-page: 96 year: 2009 ident: ref_15 article-title: Causal Inference in Statistics: An Overview publication-title: Stat. Surv. doi: 10.1214/09-SS057 – volume: 90 start-page: 012805 year: 2014 ident: ref_59 article-title: Efficiently Inferring Community Structure in Bipartite Networks publication-title: Phys. Rev. E doi: 10.1103/PhysRevE.90.012805 – ident: ref_42 doi: 10.1007/11569596_31 – ident: ref_67 doi: 10.1145/168304.168306 – ident: ref_60 doi: 10.1109/FOCS.2015.47 – volume: 2005 start-page: P09008 year: 2005 ident: ref_72 article-title: Comparing Community Structure Identification publication-title: J. Stat. Mech. Theory Exp. doi: 10.1088/1742-5468/2005/09/P09008 |
| SSID | ssj0023216 |
| Score | 2.3517451 |
| Snippet | Variational Graph Autoencoder (VGAE) has recently gained traction for learning representations on graphs. Its inception has allowed models to achieve... |
| SourceID | doaj pubmedcentral proquest crossref |
| SourceType | Open Website Open Access Repository Aggregation Database Enrichment Source Index Database |
| StartPage | 197 |
| SubjectTerms | graph neural network network embedding variational autoencoder variational inference |
| Title | Optimizing Variational Graph Autoencoder for Community Detection with Dual Optimization |
| URI | https://www.proquest.com/docview/2468340771 https://pubmed.ncbi.nlm.nih.gov/PMC7516625 https://doaj.org/article/7a23f3eec0f1450e857b2b3d058245e9 |
| Volume | 22 |
| WOSCitedRecordID | wos000521371400057&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: PRVAON databaseName: Directory of Open Access Journals customDbUrl: eissn: 1099-4300 dateEnd: 99991231 omitProxy: false ssIdentifier: ssj0023216 issn: 1099-4300 databaseCode: DOA dateStart: 20160101 isFulltext: true titleUrlDefault: https://www.doaj.org/ providerName: Directory of Open Access Journals – providerCode: PRVHPJ databaseName: ROAD: Directory of Open Access Scholarly Resources customDbUrl: eissn: 1099-4300 dateEnd: 99991231 omitProxy: false ssIdentifier: ssj0023216 issn: 1099-4300 databaseCode: M~E dateStart: 19990101 isFulltext: true titleUrlDefault: https://road.issn.org providerName: ISSN International Centre – providerCode: PRVPQU databaseName: Engineering Database customDbUrl: eissn: 1099-4300 dateEnd: 99991231 omitProxy: false ssIdentifier: ssj0023216 issn: 1099-4300 databaseCode: M7S dateStart: 19990301 isFulltext: true titleUrlDefault: http://search.proquest.com providerName: ProQuest – providerCode: PRVPQU databaseName: ProQuest Central customDbUrl: eissn: 1099-4300 dateEnd: 99991231 omitProxy: false ssIdentifier: ssj0023216 issn: 1099-4300 databaseCode: BENPR dateStart: 19990301 isFulltext: true titleUrlDefault: https://www.proquest.com/central providerName: ProQuest – providerCode: PRVPQU databaseName: Publicly Available Content Database customDbUrl: eissn: 1099-4300 dateEnd: 99991231 omitProxy: false ssIdentifier: ssj0023216 issn: 1099-4300 databaseCode: PIMPY dateStart: 19990301 isFulltext: true titleUrlDefault: http://search.proquest.com/publiccontent providerName: ProQuest |
| link | http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwrV3Pb9MwFH5iY4ddEIhNlB-VQRx2iZbYju0cV9YCEpQK9qM7RY7zrFWCFHUpEhz423lO0mqRkHbZJYfEdpz34nzvc54_A7x1RKtUUfrIEpxGMjMyIljQUSxLS3AVo2kW0l580tOpmc-z2a2tvkJOWCsP3BruWFsuvEB0sU9kGurqgheijFPDZYrN0r1YZxsy1VEtwRPV6ggJIvXHyInjUzCje-jTiPT3Ist-XuQtoJk8hkddhMhO2p49gQdYPYXLLzS0fyz-ENCwC6K33RQeex_0ptnJul4GQcoSV4yCUNat-qh_s1Osm1yrioUJV3a6pjpdU00TB3A-GZ-9-xB1eyJETipeRxadcYV2Gl2qfKIKz62xhLKoEq89wb8VKLhTtiwyJa2XSIzF0UeM4iTJURzCbrWs8BmwUpdGGOW8Lb1MtSh8ETvpuc_IuuS1ARxtbJW7TjA87FvxPSfiEMyab806gDfboj9blYz_FRoFg28LBGHr5gS5O-_cnd_l7gG83rgrp4EQ_m7YCpfrm5xLZQTRU50MQPf82Ltj_0q1uG4ktXWaKGKCz--jiy9gPzxxm9r9Enbr1RpfwZ77VS9uVkPY0XMzhIej8XT2ddi8tcOQcPotHP-O6crs4-fZ1T9B6vcw |
| linkProvider | Directory of Open Access Journals |
| 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=Optimizing+Variational+Graph+Autoencoder+for+Community+Detection+with+Dual+Optimization&rft.jtitle=Entropy+%28Basel%2C+Switzerland%29&rft.au=Choong%2C+Jun+Jin&rft.au=Liu%2C+Xin&rft.au=Murata%2C+Tsuyoshi&rft.date=2020-02-01&rft.pub=MDPI&rft.eissn=1099-4300&rft.volume=22&rft.issue=2&rft_id=info:doi/10.3390%2Fe22020197&rft_id=info%3Apmid%2F33285972&rft.externalDocID=PMC7516625 |
| thumbnail_l | http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/lc.gif&issn=1099-4300&client=summon |
| thumbnail_m | http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/mc.gif&issn=1099-4300&client=summon |
| thumbnail_s | http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/sc.gif&issn=1099-4300&client=summon |