Heterogeneous Hypergraph Variational Autoencoder for Link Prediction
Link prediction aims at inferring missing links or predicting future ones based on the currently observed network. This topic is important for many applications such as social media, bioinformatics and recommendation systems. Most existing methods focus on homogeneous settings and consider only low-...
Saved in:
| Published in: | IEEE transactions on pattern analysis and machine intelligence Vol. 44; no. 8; pp. 4125 - 4138 |
|---|---|
| Main Authors: | , , , , , , |
| Format: | Journal Article |
| Language: | English |
| Published: |
United States
IEEE
01.08.2022
The Institute of Electrical and Electronics Engineers, Inc. (IEEE) |
| Subjects: | |
| ISSN: | 0162-8828, 1939-3539, 2160-9292, 1939-3539 |
| Online Access: | Get full text |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| Abstract | Link prediction aims at inferring missing links or predicting future ones based on the currently observed network. This topic is important for many applications such as social media, bioinformatics and recommendation systems. Most existing methods focus on homogeneous settings and consider only low-order pairwise relations while ignoring either the heterogeneity or high-order complex relations among different types of nodes, which tends to lead to a sub-optimal embedding result. This paper presents a method named Heterogeneous Hypergraph Variational Autoencoder (HeteHG-VAE) for link prediction in heterogeneous information networks (HINs). It first maps a conventional HIN to a heterogeneous hypergraph with a certain kind of semantics to capture both the high-order semantics and complex relations among nodes, while preserving the low-order pairwise topology information of the original HIN. Then, deep latent representations of nodes and hyperedges are learned by a Bayesian deep generative framework from the heterogeneous hypergraph in an unsupervised manner. Moreover, a hyperedge attention module is designed to learn the importance of different types of nodes in each hyperedge. The major merit of HeteHG-VAE lies in its ability of modeling multi-level relations in heterogeneous settings. Extensive experiments on real-world datasets demonstrate the effectiveness and efficiency of the proposed method. |
|---|---|
| AbstractList | Link prediction aims at inferring missing links or predicting future ones based on the currently observed network. This topic is important for many applications such as social media, bioinformatics and recommendation systems. Most existing methods focus on homogeneous settings and consider only low-order pairwise relations while ignoring either the heterogeneity or high-order complex relations among different types of nodes, which tends to lead to a sub-optimal embedding result. This paper presents a method named Heterogeneous Hypergraph Variational Autoencoder (HeteHG-VAE) for link prediction in heterogeneous information networks (HINs). It first maps a conventional HIN to a heterogeneous hypergraph with a certain kind of semantics to capture both the high-order semantics and complex relations among nodes, while preserving the low-order pairwise topology information of the original HIN. Then, deep latent representations of nodes and hyperedges are learned by a Bayesian deep generative framework from the heterogeneous hypergraph in an unsupervised manner. Moreover, a hyperedge attention module is designed to learn the importance of different types of nodes in each hyperedge. The major merit of HeteHG-VAE lies in its ability of modeling multi-level relations in heterogeneous settings. Extensive experiments on real-world datasets demonstrate the effectiveness and efficiency of the proposed method.Link prediction aims at inferring missing links or predicting future ones based on the currently observed network. This topic is important for many applications such as social media, bioinformatics and recommendation systems. Most existing methods focus on homogeneous settings and consider only low-order pairwise relations while ignoring either the heterogeneity or high-order complex relations among different types of nodes, which tends to lead to a sub-optimal embedding result. This paper presents a method named Heterogeneous Hypergraph Variational Autoencoder (HeteHG-VAE) for link prediction in heterogeneous information networks (HINs). It first maps a conventional HIN to a heterogeneous hypergraph with a certain kind of semantics to capture both the high-order semantics and complex relations among nodes, while preserving the low-order pairwise topology information of the original HIN. Then, deep latent representations of nodes and hyperedges are learned by a Bayesian deep generative framework from the heterogeneous hypergraph in an unsupervised manner. Moreover, a hyperedge attention module is designed to learn the importance of different types of nodes in each hyperedge. The major merit of HeteHG-VAE lies in its ability of modeling multi-level relations in heterogeneous settings. Extensive experiments on real-world datasets demonstrate the effectiveness and efficiency of the proposed method. Link prediction aims at inferring missing links or predicting future ones based on the currently observed network. This topic is important for many applications such as social media, bioinformatics and recommendation systems. Most existing methods focus on homogeneous settings and consider only low-order pairwise relations while ignoring either the heterogeneity or high-order complex relations among different types of nodes, which tends to lead to a sub-optimal embedding result. This paper presents a method named Heterogeneous Hypergraph Variational Autoencoder (HeteHG-VAE) for link prediction in heterogeneous information networks (HINs). It first maps a conventional HIN to a heterogeneous hypergraph with a certain kind of semantics to capture both the high-order semantics and complex relations among nodes, while preserving the low-order pairwise topology information of the original HIN. Then, deep latent representations of nodes and hyperedges are learned by a Bayesian deep generative framework from the heterogeneous hypergraph in an unsupervised manner. Moreover, a hyperedge attention module is designed to learn the importance of different types of nodes in each hyperedge. The major merit of HeteHG-VAE lies in its ability of modeling multi-level relations in heterogeneous settings. Extensive experiments on real-world datasets demonstrate the effectiveness and efficiency of the proposed method. |
| Author | Wei, Yuxuan Gao, Yue Zhang, Fengbin Zou, Changqing Fan, Haoyi Li, Zuoyong Dai, Qionghai |
| Author_xml | – sequence: 1 givenname: Haoyi orcidid: 0000-0001-9428-7812 surname: Fan fullname: Fan, Haoyi email: isfanhy@gmail.com organization: School of Computer Science and Technology, Harbin University of Science and Technology, Harbin, China – sequence: 2 givenname: Fengbin surname: Zhang fullname: Zhang, Fengbin email: zhangfengbin@hrbust.edu.cn organization: School of Computer Science and Technology, Harbin University of Science and Technology, Harbin, China – sequence: 3 givenname: Yuxuan surname: Wei fullname: Wei, Yuxuan email: weiyuxua19@mails.tsinghua.edu.cn organization: School of Software, BRNist, THUICBS, Tsinghua University, Beijing, China – sequence: 4 givenname: Zuoyong orcidid: 0000-0003-0952-9915 surname: Li fullname: Li, Zuoyong email: fzulzytdq@126.com organization: Fujian Provincial Key Laboratory of Information Processing and Intelligent Control, Minjiang University, Fuzhou, China – sequence: 5 givenname: Changqing orcidid: 0000-0001-8264-6849 surname: Zou fullname: Zou, Changqing email: aaronzou1125@gmail.com organization: Sun Yat-sen University, Guangzhou, China – sequence: 6 givenname: Yue orcidid: 0000-0002-4971-590X surname: Gao fullname: Gao, Yue email: kevin.gaoy@gmail.com organization: School of Software, BRNist, THUICBS, Tsinghua University, Beijing, China – sequence: 7 givenname: Qionghai orcidid: 0000-0001-7043-3061 surname: Dai fullname: Dai, Qionghai email: qhdai@tsinghua.edu.cn organization: Department of Automation, BRNist, THUICBS, Tsinghua University, Beijing, China |
| BackLink | https://www.ncbi.nlm.nih.gov/pubmed/33587699$$D View this record in MEDLINE/PubMed |
| BookMark | eNp9kT1PHDEQhi1EBAfJHwhStFIamr147PXHlCe-DumiUJC0lvHNEsPe-uLdLfj32fuAgoJqmud5NTPvCTtsU0uMfQU-BeD44_5u9vN2KriAqeQKJcgDNhGgeYkCxSGbcNCitFbYY3bSdU-cQ6W4PGLHUiprNOKEXc6pp5weqaU0dMX8ZU35Mfv13-KPz9H3MbW-KWZDn6gNaUm5qFMuFrF9Lu4yLWPYEJ_Zp9o3HX3Zz1P2-_rq_mJeLn7d3F7MFmWQCvoS5GaDWkIwdb1EXivBK5TcoEYw6H3gD0FqA7aqtTXeWg2BDKHWpIwhecrOd7nrnP4N1PVuFbtATeO32ztRIQehtKlG9Ps79CkNebxlpLQVCGiMGKlve2p4WNHSrXNc-fziXv8zAnYHhJy6LlPtQuy3X-mzj40D7jZVuG0VblOF21cxquKd-pr-oXS2kyIRvQkoVaWwkv8Bd36SNg |
| CODEN | ITPIDJ |
| CitedBy_id | crossref_primary_10_1109_TIFS_2025_3529321 crossref_primary_10_1109_TPAMI_2025_3535763 crossref_primary_10_1109_JIOT_2024_3484996 crossref_primary_10_1007_s40747_022_00964_7 crossref_primary_10_1155_2021_4699420 crossref_primary_10_1109_TSC_2023_3319713 crossref_primary_10_1109_TPAMI_2023_3331389 crossref_primary_10_3389_fmed_2022_840319 crossref_primary_10_1016_j_neunet_2022_08_028 crossref_primary_10_1088_2632_2153_adf375 crossref_primary_10_3389_fmed_2025_1549491 crossref_primary_10_1109_TKDE_2024_3488375 crossref_primary_10_1016_j_jmsy_2024_06_011 crossref_primary_10_1016_j_ress_2023_109304 crossref_primary_10_1109_JSEN_2023_3319537 crossref_primary_10_1109_TCYB_2022_3181810 crossref_primary_10_1109_TMI_2023_3313778 crossref_primary_10_1109_TCSS_2023_3260118 crossref_primary_10_1109_TPAMI_2021_3132503 crossref_primary_10_1109_ACCESS_2024_3398555 crossref_primary_10_1002_int_22683 crossref_primary_10_1145_3494567 crossref_primary_10_1109_TPAMI_2022_3178156 crossref_primary_10_1007_s10489_024_05945_6 crossref_primary_10_1016_j_procs_2024_09_313 crossref_primary_10_1109_TBDATA_2024_3442549 crossref_primary_10_1145_3703156 crossref_primary_10_1109_ACCESS_2022_3204284 crossref_primary_10_1016_j_ins_2024_120453 crossref_primary_10_1109_TAI_2024_3524984 crossref_primary_10_1109_TCAD_2023_3343228 crossref_primary_10_1016_j_patcog_2023_109818 |
| Cites_doi | 10.1109/ICDM.2015.91 10.1109/ICDM.2018.00104 10.1145/3308558.3313562 10.1109/TKDE.2017.2730207 10.1145/3097983.3098036 10.1145/3018661.3018735 10.1145/3366423.3380027 10.1109/TKDE.2018.2833443 10.1109/TKDE.2018.2819980 10.1093/bioinformatics/bty294 10.1109/IJCNN.2019.8851893 10.1145/2339530.2339729 10.1145/3308558.3313635 10.1609/aaai.v34i04.6178 10.1145/2623330.2623732 10.1609/aaai.v32i1.11573 10.1109/TKDE.2017.2754499 10.1109/CVPR.2010.5540012 10.1145/3219819.3220006 10.1145/3178876.3186152 10.1109/TIT.2019.2940246 10.1145/3132847.3132953 10.1038/nature06830 10.1007/s10479-011-0841-3 10.1109/TKDE.2016.2598561 10.1016/j.physa.2010.11.027 10.1109/TIP.2018.2862625 10.1609/aaai.v32i1.11266 10.14778/3402707.3402736 10.1007/BF02289026 10.1145/2783258.2783307 10.1109/TNNLS.2018.2869747 10.1145/2939672.2939754 10.1145/1935826.1935914 10.1109/TPAMI.2020.3039374 10.1145/2736277.2741093 10.1145/3292500.3330961 10.1002/asi.20591 10.1016/S0378-8733(03)00009-1 10.1007/978-3-319-93417-4_38 10.7551/mitpress/7503.003.0205 10.1609/aaai.v32i1.11782 10.1609/aaai.v31i1.10805 10.1145/2020408.2020575 10.1609/aaai.v33i01.33013558 10.1109/TKDE.2017.2733530 10.1103/PhysRevE.82.036106 |
| ContentType | Journal Article |
| Copyright | Copyright The Institute of Electrical and Electronics Engineers, Inc. (IEEE) 2022 |
| Copyright_xml | – notice: Copyright The Institute of Electrical and Electronics Engineers, Inc. (IEEE) 2022 |
| DBID | 97E RIA RIE AAYXX CITATION NPM 7SC 7SP 8FD JQ2 L7M L~C L~D 7X8 |
| DOI | 10.1109/TPAMI.2021.3059313 |
| DatabaseName | IEEE All-Society Periodicals Package (ASPP) 2005–Present IEEE All-Society Periodicals Package (ASPP) 1998–Present IEEE Electronic Library (IEL) CrossRef PubMed Computer and Information Systems Abstracts Electronics & Communications Abstracts Technology Research Database ProQuest Computer Science Collection Advanced Technologies Database with Aerospace Computer and Information Systems Abstracts Academic Computer and Information Systems Abstracts Professional MEDLINE - Academic |
| DatabaseTitle | CrossRef PubMed Technology Research Database Computer and Information Systems Abstracts – Academic Electronics & Communications Abstracts ProQuest Computer Science Collection Computer and Information Systems Abstracts Advanced Technologies Database with Aerospace Computer and Information Systems Abstracts Professional MEDLINE - Academic |
| DatabaseTitleList | MEDLINE - Academic Technology Research Database PubMed |
| Database_xml | – sequence: 1 dbid: NPM name: PubMed url: http://www.ncbi.nlm.nih.gov/entrez/query.fcgi?db=PubMed sourceTypes: Index Database – sequence: 2 dbid: RIE name: IEEE Electronic Library (IEL) url: https://ieeexplore.ieee.org/ sourceTypes: Publisher – sequence: 3 dbid: 7X8 name: MEDLINE - Academic url: https://search.proquest.com/medline sourceTypes: Aggregation Database |
| DeliveryMethod | fulltext_linktorsrc |
| Discipline | Engineering Computer Science |
| EISSN | 2160-9292 1939-3539 |
| EndPage | 4138 |
| ExternalDocumentID | 33587699 10_1109_TPAMI_2021_3059313 9354594 |
| Genre | orig-research Journal Article |
| GrantInformation_xml | – fundername: Tsinghua University Initiative Scientific Research Program grantid: 20197020003 – fundername: Natural Science Foundation of Fujian Province grantid: 2020J02024 funderid: 10.13039/501100003392 – fundername: National Natural Science Foundation of China grantid: U1701262; 61972187; 61172168 funderid: 10.13039/501100001809 – fundername: Fuzhou Science and Technology Project grantid: 2020-RC-186 |
| GroupedDBID | --- -DZ -~X .DC 0R~ 29I 4.4 53G 5GY 6IK 97E AAJGR AARMG AASAJ AAWTH ABAZT ABQJQ ABVLG ACGFO ACGFS ACIWK ACNCT AENEX AGQYO AHBIQ AKJIK AKQYR ALMA_UNASSIGNED_HOLDINGS ASUFR ATWAV BEFXN BFFAM BGNUA BKEBE BPEOZ CS3 DU5 E.L EBS EJD F5P HZ~ IEDLZ IFIPE IPLJI JAVBF LAI M43 MS~ O9- OCL P2P PQQKQ RIA RIE RNS RXW TAE TN5 UHB ~02 5VS 9M8 AAYXX ABFSI ADRHT AETEA AETIX AGSQL AI. AIBXA ALLEH CITATION FA8 H~9 IBMZZ ICLAB IFJZH RNI RZB VH1 NPM RIC Z5M 7SC 7SP 8FD JQ2 L7M L~C L~D 7X8 |
| ID | FETCH-LOGICAL-c351t-130014f31c7ffd90f52049307969179aac0bc367184f687a8861ce7e966e577e3 |
| IEDL.DBID | RIE |
| ISICitedReferencesCount | 107 |
| ISICitedReferencesURI | http://www.webofscience.com/api/gateway?GWVersion=2&SrcApp=Summon&SrcAuth=ProQuest&DestLinkType=CitingArticles&DestApp=WOS_CPL&KeyUT=000820522100002&url=https%3A%2F%2Fcvtisr.summon.serialssolutions.com%2F%23%21%2Fsearch%3Fho%3Df%26include.ft.matches%3Dt%26l%3Dnull%26q%3D |
| ISSN | 0162-8828 1939-3539 |
| IngestDate | Thu Oct 02 10:27:02 EDT 2025 Mon Jun 30 04:19:32 EDT 2025 Wed Feb 19 02:28:38 EST 2025 Sat Nov 29 05:16:00 EST 2025 Tue Nov 18 22:33:42 EST 2025 Wed Aug 27 02:23:53 EDT 2025 |
| IsPeerReviewed | true |
| IsScholarly | true |
| Issue | 8 |
| Language | English |
| License | https://ieeexplore.ieee.org/Xplorehelp/downloads/license-information/IEEE.html |
| LinkModel | DirectLink |
| MergedId | FETCHMERGED-LOGICAL-c351t-130014f31c7ffd90f52049307969179aac0bc367184f687a8861ce7e966e577e3 |
| Notes | ObjectType-Article-1 SourceType-Scholarly Journals-1 ObjectType-Feature-2 content type line 14 content type line 23 |
| ORCID | 0000-0001-8264-6849 0000-0001-7043-3061 0000-0003-0952-9915 0000-0001-9428-7812 0000-0002-4971-590X |
| PMID | 33587699 |
| PQID | 2682919772 |
| PQPubID | 85458 |
| PageCount | 14 |
| ParticipantIDs | proquest_journals_2682919772 pubmed_primary_33587699 ieee_primary_9354594 proquest_miscellaneous_2490125674 crossref_citationtrail_10_1109_TPAMI_2021_3059313 crossref_primary_10_1109_TPAMI_2021_3059313 |
| PublicationCentury | 2000 |
| PublicationDate | 2022-08-01 |
| PublicationDateYYYYMMDD | 2022-08-01 |
| PublicationDate_xml | – month: 08 year: 2022 text: 2022-08-01 day: 01 |
| PublicationDecade | 2020 |
| PublicationPlace | United States |
| PublicationPlace_xml | – name: United States – name: New York |
| PublicationTitle | IEEE transactions on pattern analysis and machine intelligence |
| PublicationTitleAbbrev | TPAMI |
| PublicationTitleAlternate | IEEE Trans Pattern Anal Mach Intell |
| PublicationYear | 2022 |
| Publisher | IEEE The Institute of Electrical and Electronics Engineers, Inc. (IEEE) |
| Publisher_xml | – name: IEEE – name: The Institute of Electrical and Electronics Engineers, Inc. (IEEE) |
| References | ref57 ref12 ref56 Probst (ref67) 2020; 21 ref59 ref14 ref58 ref53 ref11 Liu (ref44) ref55 ref10 ref54 Kipf (ref36) ref17 Sankar (ref70) ref19 ref18 Salha (ref40) You (ref43) Li (ref64) ref51 Socher (ref3) ref48 ref47 ref49 Chami (ref45) ref8 ref7 ref9 Hamilton (ref41) ref4 ref6 ref5 Davidson (ref37) ref34 ref31 ref30 ref33 ref32 Zhang (ref13) ref2 ref1 Berge (ref52) 1985 ref39 Veličković (ref42) ref38 Kingma (ref69) Yadati (ref62) ref71 ref73 Nickel (ref15) Bordes (ref50) ref24 ref68 ref23 ref26 ref25 ref20 ref22 ref21 ref65 Kingma (ref28) ref27 ref29 Scheinerman (ref66) 2011 Kipf (ref35) 2017 Ganea (ref46) Nickel (ref72) Zhao (ref16) Li (ref63) Chien (ref60) ref61 |
| References_xml | – ident: ref33 doi: 10.1109/ICDM.2015.91 – volume-title: Proc. NIPS Workshop Bayesian Deep Learn. ident: ref36 article-title: Variational graph auto-encoders – ident: ref25 doi: 10.1109/ICDM.2018.00104 – start-page: 926 volume-title: Proc. Int. Conf. Neural Inf. Process. Syst. ident: ref3 article-title: Reasoning with neural tensor networks for knowledge base completion – start-page: 5165 volume-title: Proc. Int. Conf. Neural Inf. Process. Syst. ident: ref13 article-title: Link prediction based on graph neural networks – ident: ref22 doi: 10.1145/3308558.3313562 – start-page: 4868 volume-title: Proc. Int. Conf. Neural Inf. Process. Syst. ident: ref45 article-title: Hyperbolic graph convolutional neural networks – ident: ref29 doi: 10.1109/TKDE.2017.2730207 – year: 2017 ident: ref35 article-title: Semi-supervised classification with graph convolutional networks – start-page: 5345 volume-title: Proc. Int. Conf. Neural Inf. Process. Syst. ident: ref46 article-title: Hyperbolic neural networks – ident: ref19 doi: 10.1145/3097983.3098036 – ident: ref26 doi: 10.1145/3018661.3018735 – ident: ref49 doi: 10.1145/3366423.3380027 – volume-title: Proc. Int. Conf. Learn. Representations ident: ref69 article-title: Adam: A method for stochastic optimization – ident: ref8 doi: 10.1109/TKDE.2018.2833443 – volume-title: Proc. Workshop Graph Representation Learn. 33rd Conf. Neural Inf. Process. Syst. ident: ref40 article-title: Keep it simple: Graph autoencoders without graph convolutional networks – ident: ref2 doi: 10.1109/TKDE.2018.2819980 – ident: ref6 doi: 10.1093/bioinformatics/bty294 – start-page: 6338 volume-title: Proc. Int. Conf. Neural Inf. Process. Syst. ident: ref72 article-title: Poincaré embeddings for learning hierarchical representations – ident: ref34 doi: 10.1109/IJCNN.2019.8851893 – ident: ref7 doi: 10.1145/2339530.2339729 – start-page: 2466 volume-title: Proc. 22nd Int. Conf. Artif. Intell. Statist. ident: ref60 article-title: $HS^{2}$HS2: Active learning over hypergraphs with pointwise and pairwise queries – start-page: 4072 volume-title: Proc. 34th Int. Conf. Mach. Learn. ident: ref16 article-title: Leveraging node attributes for incomplete relational data – ident: ref58 doi: 10.1145/3308558.3313635 – ident: ref38 doi: 10.1609/aaai.v34i04.6178 – start-page: 2787 volume-title: Proc. Int. Conf. Neural Inf. Process. Syst. ident: ref50 article-title: Translating embeddings for modeling multi-relational data – ident: ref10 doi: 10.1145/2623330.2623732 – volume-title: Proc. Int. Conf. Learn. Representations ident: ref42 article-title: Graph attention networks – start-page: 7134 volume-title: Proc. 36th Int. Conf. Mach. Learn. ident: ref43 article-title: Position-aware graph neural networks – ident: ref51 doi: 10.1609/aaai.v32i1.11573 – ident: ref4 doi: 10.1109/TKDE.2017.2754499 – start-page: 1179 volume-title: Proc. Int. Conf. Neural Inf. Process. Syst. ident: ref15 article-title: Reducing the rank in relational factorization models by including observable patterns – volume-title: Graphs and Hypergraphs year: 1985 ident: ref52 – ident: ref55 doi: 10.1109/CVPR.2010.5540012 – ident: ref20 doi: 10.1145/3219819.3220006 – ident: ref27 doi: 10.1145/3178876.3186152 – ident: ref59 doi: 10.1109/TIT.2019.2940246 – ident: ref18 doi: 10.1145/3132847.3132953 – ident: ref5 doi: 10.1038/nature06830 – ident: ref73 doi: 10.1007/s10479-011-0841-3 – ident: ref65 doi: 10.1109/TKDE.2016.2598561 – ident: ref9 doi: 10.1016/j.physa.2010.11.027 – start-page: 2308 volume-title: Proc. Int. Conf. Neural Inf. Process. Syst. ident: ref63 article-title: Inhomogeneous hypergraph clustering with applications – ident: ref57 doi: 10.1109/TIP.2018.2862625 – ident: ref24 doi: 10.1609/aaai.v32i1.11266 – ident: ref48 doi: 10.14778/3402707.3402736 – start-page: 856 volume-title: Proc. 34th Conf. Uncertainty Artif. Intell. ident: ref37 article-title: Hyperspherical variational auto-encoders – ident: ref31 doi: 10.1007/BF02289026 – ident: ref47 doi: 10.1145/2783258.2783307 – ident: ref56 doi: 10.1109/TNNLS.2018.2869747 – start-page: 3014 volume-title: Proc. Int. Conf. Mach. Learn. ident: ref64 article-title: Submodular hypergraphs: P-Laplacians, cheeger inequalities and spectral clustering – start-page: 1024 volume-title: Proc. Int. Conf. Neural Inf. Process. Syst. ident: ref41 article-title: Inductive representation learning on large graphs – ident: ref12 doi: 10.1145/2939672.2939754 – ident: ref32 doi: 10.1145/1935826.1935914 – ident: ref54 doi: 10.1109/TPAMI.2020.3039374 – volume-title: Fractional Graph Theory: A Rational Approach to the Theory of Graphs year: 2011 ident: ref66 – volume: 21 start-page: 1 issue: 78 year: 2020 ident: ref67 article-title: Harmless overfitting: Using denoising autoencoders in estimation of distribution algorithms publication-title: J. Mach. Learn. Res. – ident: ref11 doi: 10.1145/2736277.2741093 – ident: ref21 doi: 10.1145/3292500.3330961 – ident: ref1 doi: 10.1002/asi.20591 – ident: ref30 doi: 10.1016/S0378-8733(03)00009-1 – ident: ref39 doi: 10.1007/978-3-319-93417-4_38 – volume-title: Proc. Workshop Representation Learn. Graphs Manifolds ident: ref70 article-title: Dynamic graph representation learning via self-attention networks – ident: ref53 doi: 10.7551/mitpress/7503.003.0205 – ident: ref68 doi: 10.1609/aaai.v32i1.11782 – ident: ref17 doi: 10.1609/aaai.v31i1.10805 – ident: ref14 doi: 10.1145/2020408.2020575 – volume-title: Proc. Int. Conf. Learn. Representations ident: ref28 article-title: Auto-encoding variational bayes – start-page: 8230 volume-title: Proc. Int. Conf. Neural Inf. Process. Syst. ident: ref44 article-title: Hyperbolic graph neural networks – ident: ref61 doi: 10.1609/aaai.v33i01.33013558 – start-page: 1509 volume-title: Proc. 33rd Conf. Neural Inf. Process. Syst. ident: ref62 article-title: HyperGCN: A new method for training graph convolutional networks on hypergraphs – ident: ref23 doi: 10.1109/TKDE.2017.2733530 – ident: ref71 doi: 10.1103/PhysRevE.82.036106 |
| SSID | ssj0014503 |
| Score | 2.671871 |
| Snippet | Link prediction aims at inferring missing links or predicting future ones based on the currently observed network. This topic is important for many... |
| SourceID | proquest pubmed crossref ieee |
| SourceType | Aggregation Database Index Database Enrichment Source Publisher |
| StartPage | 4125 |
| SubjectTerms | Bioinformatics Fans Graph theory Graphs Heterogeneity Heterogeneous information network hyperedge attention hypergraph link prediction Network analysis Network topology Nodes Predictions Predictive models Recommender systems Semantics Stochastic processes Task analysis Topology variational inference |
| Title | Heterogeneous Hypergraph Variational Autoencoder for Link Prediction |
| URI | https://ieeexplore.ieee.org/document/9354594 https://www.ncbi.nlm.nih.gov/pubmed/33587699 https://www.proquest.com/docview/2682919772 https://www.proquest.com/docview/2490125674 |
| Volume | 44 |
| WOSCitedRecordID | wos000820522100002&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: PRVIEE databaseName: IEEE Electronic Library (IEL) customDbUrl: eissn: 2160-9292 dateEnd: 99991231 omitProxy: false ssIdentifier: ssj0014503 issn: 0162-8828 databaseCode: RIE dateStart: 19790101 isFulltext: true titleUrlDefault: https://ieeexplore.ieee.org/ providerName: IEEE |
| link | http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwlV1JS-xAEC508PA8uC_jRoR380XTWzp9HFwYQWUOKnMLPZ0OCDKRWfz9VvUkeR5U8BZIpxNqSdXX1V0fwN9COWG1krF0jMdSF1lsZSnjxJmMScWtckHTd_rhIRsOzWAJ_rVnYbz3YfOZP6fLUMsvKjenpbILIzDeG7kMy1rrxVmttmIgVWBBxgwGPRxhRHNAJjEXj4Pe_S1CQc7OBTHYMSLPEULhjyC0fP0fjwLByve5Zog5N-u_-9oNWKtzy6i3MIZNWPLjLVhveBui2o23YPVTE8JtuOrTjpgKDclX82nUR2A6CW2so2fE0fVaYdSbzyrqeVngRJjnRoRho8GEyjw0Ygeebq4fL_txza0QO6EYMdCTzErBnC7LwiSl4ogV0OFNigDOWOuSkRMpRi5Zppm2WZYy57VHdOSV1l7sQmdcjf0-RNwKiUFej4R1UqT4Ryg181TO4aOkKNMusEbCuasbjxP_xWseAEhi8qCgnBSU1wrqwln7zNui7caPo7dJ_O3IWvJdOGoUmdeeOc15mnHDMOvlXThtb6NPUaHEBknnCEkxbqtU4xR7CwNo527s5uDrdx7CH04HJMIWwSPozCZzfwwr7n32Mp2coOEOs5NguB_0heRu |
| linkProvider | IEEE |
| linkToHtml | http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwlV1Lb9QwEB61BalwoE_KQh9B4kazjV9xfFwB1VbdrvawoN4sr-NISGhT7aO_vzPeJHCAStwixXGieWTm89jzAXwqlRdOK5lKz3gqdVmkTlYyzbwpmFTcKR81PdLjcXF_byZbcNmdhQkhxM1noU-XsZZf1n5NS2VXRmC8N3IbXigpOduc1upqBlJFHmTMYdDHEUi0R2QyczWdDO5uEAxy1hfEYceIPkcIhb-C2PT1d0SKFCv_zjZj1Lne-7_v3Yc3TXaZDDbmcABbYX4Iey1zQ9I48iG8_qMN4RF8HdKemBpNKdTrZTJEaLqIjayTH4ikm9XCZLBe1dT1ssSJMNNNCMUmkwUVemjEMXy__jb9MkwbdoXUC8WIg55kVgnmdVWVJqsUR7SALm9yhHDGOZ_NvMgxdskqL7Qripz5oAPio6C0DuIt7MzreXgHCXdCYpjXM-G8FDn-EyrNAhV0-Cwrq7wHrJWw9U3rcWLA-GUjBMmMjQqypCDbKKgHn7tnHjaNN54dfUTi70Y2ku_BaatI2_jm0vK84IZh3st78LG7jV5FpRIXJW0RlGLkVrnGKU42BtDN3drN-7-_8wJ2h9O7kR3djG8_wCtOxyXihsFT2Fkt1uEMXvrH1c_l4jya7xOc1ObN |
| 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=Heterogeneous+Hypergraph+Variational+Autoencoder+for+Link+Prediction&rft.jtitle=IEEE+transactions+on+pattern+analysis+and+machine+intelligence&rft.au=Fan%2C+Haoyi&rft.au=Zhang%2C+Fengbin&rft.au=Yuxuan+Wei&rft.au=Li%2C+Zuoyong&rft.date=2022-08-01&rft.pub=The+Institute+of+Electrical+and+Electronics+Engineers%2C+Inc.+%28IEEE%29&rft.issn=0162-8828&rft.eissn=1939-3539&rft.volume=44&rft.issue=8&rft.spage=4125&rft_id=info:doi/10.1109%2FTPAMI.2021.3059313&rft.externalDBID=NO_FULL_TEXT |
| thumbnail_l | http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/lc.gif&issn=0162-8828&client=summon |
| thumbnail_m | http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/mc.gif&issn=0162-8828&client=summon |
| thumbnail_s | http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/sc.gif&issn=0162-8828&client=summon |