Temporal Network Embedding for Link Prediction via VAE Joint Attention Mechanism

Network representation learning or embedding aims to project the network into a low-dimensional space that can be devoted to different network tasks. Temporal networks are an important type of network whose topological structure changes over time. Compared with methods on static networks, temporal n...

Ausführliche Beschreibung

Gespeichert in:
Bibliographische Detailangaben
Veröffentlicht in:IEEE transaction on neural networks and learning systems Jg. 33; H. 12; S. 7400 - 7413
Hauptverfasser: Jiao, Pengfei, Guo, Xuan, Jing, Xin, He, Dongxiao, Wu, Huaming, Pan, Shirui, Gong, Maoguo, Wang, Wenjun
Format: Journal Article
Sprache:Englisch
Veröffentlicht: United States IEEE 01.12.2022
The Institute of Electrical and Electronics Engineers, Inc. (IEEE)
Schlagworte:
ISSN:2162-237X, 2162-2388, 2162-2388
Online-Zugang:Volltext
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
Abstract Network representation learning or embedding aims to project the network into a low-dimensional space that can be devoted to different network tasks. Temporal networks are an important type of network whose topological structure changes over time. Compared with methods on static networks, temporal network embedding (TNE) methods are facing three challenges: 1) it cannot describe the temporal dependence across network snapshots; 2) the node embedding in the latent space fails to indicate changes in the network topology; and 3) it cannot avoid a lot of redundant computation via parameter inheritance on a series of snapshots. To overcome these problems, we propose a novel TNE method named temporal network embedding method based on the VAE framework (TVAE), which is based on a variational autoencoder (VAE) to capture the evolution of temporal networks for link prediction. It not only generates low-dimensional embedding vectors for nodes but also preserves the dynamic nonlinear features of temporal networks. Through the combination of a self-attention mechanism and recurrent neural networks, TVAE can update node representations and keep the temporal dependence of vectors over time. We utilize parameter inheritance to keep the new embedding close to the previous one, rather than explicitly using regularization, and thus, it is effective for large-scale networks. We evaluate our model and several baselines on synthetic data sets and real-world networks. The experimental results demonstrate that TVAE has superior performance and lower time cost compared with the baselines.
AbstractList Network representation learning or embedding aims to project the network into a low-dimensional space that can be devoted to different network tasks. Temporal networks are an important type of network whose topological structure changes over time. Compared with methods on static networks, temporal network embedding (TNE) methods are facing three challenges: 1) it cannot describe the temporal dependence across network snapshots; 2) the node embedding in the latent space fails to indicate changes in the network topology; and 3) it cannot avoid a lot of redundant computation via parameter inheritance on a series of snapshots. To overcome these problems, we propose a novel TNE method named temporal network embedding method based on the VAE framework (TVAE), which is based on a variational autoencoder (VAE) to capture the evolution of temporal networks for link prediction. It not only generates low-dimensional embedding vectors for nodes but also preserves the dynamic nonlinear features of temporal networks. Through the combination of a self-attention mechanism and recurrent neural networks, TVAE can update node representations and keep the temporal dependence of vectors over time. We utilize parameter inheritance to keep the new embedding close to the previous one, rather than explicitly using regularization, and thus, it is effective for large-scale networks. We evaluate our model and several baselines on synthetic data sets and real-world networks. The experimental results demonstrate that TVAE has superior performance and lower time cost compared with the baselines.
Network representation learning or embedding aims to project the network into a low-dimensional space that can be devoted to different network tasks. Temporal networks are an important type of network whose topological structure changes over time. Compared with methods on static networks, temporal network embedding (TNE) methods are facing three challenges: 1) it cannot describe the temporal dependence across network snapshots; 2) the node embedding in the latent space fails to indicate changes in the network topology; and 3) it cannot avoid a lot of redundant computation via parameter inheritance on a series of snapshots. To overcome these problems, we propose a novel TNE method named temporal network embedding method based on the VAE framework (TVAE), which is based on a variational autoencoder (VAE) to capture the evolution of temporal networks for link prediction. It not only generates low-dimensional embedding vectors for nodes but also preserves the dynamic nonlinear features of temporal networks. Through the combination of a self-attention mechanism and recurrent neural networks, TVAE can update node representations and keep the temporal dependence of vectors over time. We utilize parameter inheritance to keep the new embedding close to the previous one, rather than explicitly using regularization, and thus, it is effective for large-scale networks. We evaluate our model and several baselines on synthetic data sets and real-world networks. The experimental results demonstrate that TVAE has superior performance and lower time cost compared with the baselines.Network representation learning or embedding aims to project the network into a low-dimensional space that can be devoted to different network tasks. Temporal networks are an important type of network whose topological structure changes over time. Compared with methods on static networks, temporal network embedding (TNE) methods are facing three challenges: 1) it cannot describe the temporal dependence across network snapshots; 2) the node embedding in the latent space fails to indicate changes in the network topology; and 3) it cannot avoid a lot of redundant computation via parameter inheritance on a series of snapshots. To overcome these problems, we propose a novel TNE method named temporal network embedding method based on the VAE framework (TVAE), which is based on a variational autoencoder (VAE) to capture the evolution of temporal networks for link prediction. It not only generates low-dimensional embedding vectors for nodes but also preserves the dynamic nonlinear features of temporal networks. Through the combination of a self-attention mechanism and recurrent neural networks, TVAE can update node representations and keep the temporal dependence of vectors over time. We utilize parameter inheritance to keep the new embedding close to the previous one, rather than explicitly using regularization, and thus, it is effective for large-scale networks. We evaluate our model and several baselines on synthetic data sets and real-world networks. The experimental results demonstrate that TVAE has superior performance and lower time cost compared with the baselines.
Author Jing, Xin
Jiao, Pengfei
Wu, Huaming
Guo, Xuan
Pan, Shirui
Gong, Maoguo
Wang, Wenjun
He, Dongxiao
Author_xml – sequence: 1
  givenname: Pengfei
  orcidid: 0000-0003-1049-1002
  surname: Jiao
  fullname: Jiao, Pengfei
  email: pjiao@tju.edu.cn
  organization: Center of Biosafety Research and Strategy, Law School, Tianjin University, Tianjin, China
– sequence: 2
  givenname: Xuan
  orcidid: 0000-0001-8569-4192
  surname: Guo
  fullname: Guo, Xuan
  email: guoxuan@tju.edu.cn
  organization: College of Intelligence and Computing, Tianjin University, Tianjin, China
– sequence: 3
  givenname: Xin
  surname: Jing
  fullname: Jing, Xin
  email: jingxin1895@gmail.com
  organization: College of Intelligence and Computing, Tianjin University, Tianjin, China
– sequence: 4
  givenname: Dongxiao
  orcidid: 0000-0002-1915-4179
  surname: He
  fullname: He, Dongxiao
  email: hedongxiao@tju.edu.cn
  organization: College of Intelligence and Computing, Tianjin University, Tianjin, China
– sequence: 5
  givenname: Huaming
  orcidid: 0000-0002-4761-9973
  surname: Wu
  fullname: Wu, Huaming
  email: whming@tju.edu.cn
  organization: Center for Applied Mathematics, Tianjin University, Tianjin, China
– sequence: 6
  givenname: Shirui
  orcidid: 0000-0003-0794-527X
  surname: Pan
  fullname: Pan, Shirui
  email: shirui.pan@monash.edu
  organization: Department of Data Science and AI, Faculty of Information Technology, Monash University, Clayton, VIC, Australia
– sequence: 7
  givenname: Maoguo
  orcidid: 0000-0002-0415-8556
  surname: Gong
  fullname: Gong, Maoguo
  email: gong@ieee.org
  organization: Key Laboratory of Intelligent Perception and Image Understanding of Ministry of Education, International Research Center for Intelligent Perception and Computation, Xidian University, Xi'an, China
– sequence: 8
  givenname: Wenjun
  orcidid: 0000-0003-1174-7241
  surname: Wang
  fullname: Wang, Wenjun
  email: wjwang@tju.edu.cn
  organization: College of Intelligence and Computing, Tianjin University, Tianjin, China
BackLink https://www.ncbi.nlm.nih.gov/pubmed/34106869$$D View this record in MEDLINE/PubMed
BookMark eNp9kUtvEzEQxy1URB_0C4CELHHpJcHvxzGqwkshVCIgbpbtnYDbXTv1bkB8ezZNyKEH5jKj0e8_M5r_OTrJJQNCLyiZUkrsm9VyufgyZYTRKSdGWKmfoDNGFZswbszJsdbfT9Fl39-SMRSRSthn6JQLSpRR9gzdrKDblOpbvIThd6l3eN4FaJqUf-B1qXiR8h2-qdCkOKSS8a_k8bfZHH8sKQ94NgyQH_qfIP70OfXdc_R07dseLg_5An19O19dv58sPr_7cD1bTCKXdJhYHYkK3kZvNedUgWZehobHoKQMnvp1IzXQQEgEr3yjSAxC6saYYI0yhF-gq_3cTS33W-gH16U-Qtv6DGXbOya5NcYIQUf09SP0tmxrHq9zTAumCSdqR706UNvQQeM2NXW-_nH_fjUCbA_EWvq-wvqIUOJ2nrgHT9zOE3fwZBSZR6KYBr972VB9av8vfbmXJgA47rJCWGE4_ws1Wpf8
CODEN ITNNAL
CitedBy_id crossref_primary_10_1007_s10489_023_04887_9
crossref_primary_10_3390_rs16061055
crossref_primary_10_3390_s23229125
crossref_primary_10_3390_math13050807
crossref_primary_10_1080_07421222_2025_2452016
crossref_primary_10_1109_ACCESS_2024_3483839
crossref_primary_10_1016_j_dsp_2024_104660
crossref_primary_10_1016_j_technovation_2025_103289
crossref_primary_10_1109_TNNLS_2023_3328924
crossref_primary_10_1145_3674834
crossref_primary_10_1016_j_knosys_2024_111929
crossref_primary_10_1186_s42400_024_00237_5
crossref_primary_10_1109_TKDE_2023_3295367
crossref_primary_10_1109_TNNLS_2024_3398253
crossref_primary_10_1002_asi_24711
crossref_primary_10_1109_TNNLS_2025_3545021
crossref_primary_10_1109_TNNLS_2023_3234005
crossref_primary_10_1109_TNNLS_2024_3359275
crossref_primary_10_7717_peerj_cs_822
crossref_primary_10_1016_j_neunet_2024_106979
crossref_primary_10_1109_TCSS_2024_3457897
crossref_primary_10_1109_TKDE_2022_3144250
crossref_primary_10_1109_TKDE_2023_3304478
crossref_primary_10_3390_su14084473
crossref_primary_10_1109_TKDE_2021_3124061
crossref_primary_10_1007_s10055_022_00689_5
crossref_primary_10_1109_JAS_2023_123450
crossref_primary_10_1109_TNSE_2022_3164659
crossref_primary_10_1109_TNNLS_2024_3394161
crossref_primary_10_1109_TSC_2024_3486171
crossref_primary_10_1007_s10994_023_06473_z
crossref_primary_10_1109_TNNLS_2024_3384348
crossref_primary_10_3389_frai_2023_1256352
crossref_primary_10_1007_s13042_025_02659_0
crossref_primary_10_1016_j_future_2021_08_005
crossref_primary_10_1016_j_eswa_2023_122596
crossref_primary_10_1109_ACCESS_2025_3587793
Cites_doi 10.1145/980972.980992
10.1109/TNNLS.2019.2920267
10.1145/2623330.2623733
10.1145/3292500.3330895
10.1609/aaai.v32i1.11257
10.1145/2736277.2741093
10.1145/2806416.2806512
10.1007/s11227-017-2225-1
10.1109/TKDE.2018.2849727
10.1609/aaai.v31i1.10488
10.1609/aaai.v35i5.16583
10.1145/3336191.3371845
10.24963/ijcai.2018/288
10.1109/TBDATA.2018.2850013
10.1109/TNNLS.2020.2978386
10.1145/3340531.3411946
10.1609/aaai.v34i04.5984
10.1145/2939672.2939751
10.1109/TNNLS.2019.2945869
10.1145/3442381.3449914
10.1093/bioinformatics/bty294
10.1145/3363574
10.1109/TNNLS.2019.2919764
10.1145/3357384.3357943
10.1145/3219819.3220024
10.1145/1921632.1921636
10.1109/TNNLS.2018.2869225
10.1145/1081870.1081893
10.1145/2623330.2623732
10.1145/1401890.1401972
10.1145/2939672.2939754
10.1109/2945.841119
10.1145/1217299.1217301
10.1002/asi.20591
10.1007/978-3-319-73198-8_10
10.1016/j.knosys.2019.06.024
10.1109/MCI.2019.2919396
10.1137/1.9781611972818.31
10.1109/TKDE.2016.2591009
10.1145/2939672.2939753
10.1145/3132847.3132919
10.24963/ijcai.2019/548
10.1038/nprot.2009.177
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
CGR
CUY
CVF
ECM
EIF
NPM
7QF
7QO
7QP
7QQ
7QR
7SC
7SE
7SP
7SR
7TA
7TB
7TK
7U5
8BQ
8FD
F28
FR3
H8D
JG9
JQ2
KR7
L7M
L~C
L~D
P64
7X8
DOI 10.1109/TNNLS.2021.3084957
DatabaseName IEEE Xplore (IEEE)
IEEE All-Society Periodicals Package (ASPP) 1998–Present
IEEE Electronic Library (IEL)
CrossRef
Medline
MEDLINE
MEDLINE (Ovid)
MEDLINE
MEDLINE
PubMed
Aluminium Industry Abstracts
Biotechnology Research Abstracts
Calcium & Calcified Tissue Abstracts
Ceramic Abstracts
Chemoreception Abstracts
Computer and Information Systems Abstracts
Corrosion Abstracts
Electronics & Communications Abstracts
Engineered Materials Abstracts
Materials Business File
Mechanical & Transportation Engineering Abstracts
Neurosciences Abstracts
Solid State and Superconductivity Abstracts
METADEX
Technology Research Database
ANTE: Abstracts in New Technology & Engineering
Engineering Research Database
Aerospace Database
Materials Research Database
ProQuest Computer Science Collection
Civil Engineering Abstracts
Advanced Technologies Database with Aerospace
Computer and Information Systems Abstracts – Academic
Computer and Information Systems Abstracts Professional
Biotechnology and BioEngineering Abstracts
MEDLINE - Academic
DatabaseTitle CrossRef
MEDLINE
Medline Complete
MEDLINE with Full Text
PubMed
MEDLINE (Ovid)
Materials Research Database
Technology Research Database
Computer and Information Systems Abstracts – Academic
Mechanical & Transportation Engineering Abstracts
ProQuest Computer Science Collection
Computer and Information Systems Abstracts
Materials Business File
Aerospace Database
Engineered Materials Abstracts
Biotechnology Research Abstracts
Chemoreception Abstracts
Advanced Technologies Database with Aerospace
ANTE: Abstracts in New Technology & Engineering
Civil Engineering Abstracts
Aluminium Industry Abstracts
Electronics & Communications Abstracts
Ceramic Abstracts
Neurosciences Abstracts
METADEX
Biotechnology and BioEngineering Abstracts
Computer and Information Systems Abstracts Professional
Solid State and Superconductivity Abstracts
Engineering Research Database
Calcium & Calcified Tissue Abstracts
Corrosion Abstracts
MEDLINE - Academic
DatabaseTitleList MEDLINE
Materials Research Database

MEDLINE - Academic
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 Computer Science
EISSN 2162-2388
EndPage 7413
ExternalDocumentID 34106869
10_1109_TNNLS_2021_3084957
9449483
Genre orig-research
Research Support, Non-U.S. Gov't
Journal Article
GrantInformation_xml – fundername: National Key Research and Development Program of China
  grantid: 2018YFC0809804
  funderid: 10.13039/501100012166
– fundername: Tianjin Municipal Science and Technology Project
  grantid: 19ZXZNGX00030
– fundername: National Natural Science Foundation of China
  grantid: 61902278; 62071327; 61876128
  funderid: 10.13039/501100001809
GroupedDBID 0R~
4.4
5VS
6IK
97E
AAJGR
AARMG
AASAJ
AAWTH
ABAZT
ABQJQ
ABVLG
ACIWK
ACPRK
AENEX
AFRAH
AGQYO
AGSQL
AHBIQ
AKJIK
AKQYR
ALMA_UNASSIGNED_HOLDINGS
ATWAV
BEFXN
BFFAM
BGNUA
BKEBE
BPEOZ
EBS
EJD
IFIPE
IPLJI
JAVBF
M43
MS~
O9-
OCL
PQQKQ
RIA
RIE
RNS
AAYXX
CITATION
CGR
CUY
CVF
ECM
EIF
NPM
RIG
7QF
7QO
7QP
7QQ
7QR
7SC
7SE
7SP
7SR
7TA
7TB
7TK
7U5
8BQ
8FD
F28
FR3
H8D
JG9
JQ2
KR7
L7M
L~C
L~D
P64
7X8
ID FETCH-LOGICAL-c351t-97c06ba9ca973316e72a5bd3cb655ba1afd57e1b00cea6ad60cb457d88b986803
IEDL.DBID RIE
ISICitedReferencesCount 53
ISICitedReferencesURI http://www.webofscience.com/api/gateway?GWVersion=2&SrcApp=Summon&SrcAuth=ProQuest&DestLinkType=CitingArticles&DestApp=WOS_CPL&KeyUT=000732095200001&url=https%3A%2F%2Fcvtisr.summon.serialssolutions.com%2F%23%21%2Fsearch%3Fho%3Df%26include.ft.matches%3Dt%26l%3Dnull%26q%3D
ISSN 2162-237X
2162-2388
IngestDate Sun Sep 28 10:59:37 EDT 2025
Sun Nov 09 06:46:10 EST 2025
Thu Jan 02 22:53:12 EST 2025
Sat Nov 29 01:40:13 EST 2025
Tue Nov 18 22:12:50 EST 2025
Wed Aug 27 02:18:29 EDT 2025
IsPeerReviewed false
IsScholarly true
Issue 12
Language English
License https://ieeexplore.ieee.org/Xplorehelp/downloads/license-information/IEEE.html
https://doi.org/10.15223/policy-029
https://doi.org/10.15223/policy-037
LinkModel DirectLink
MergedId FETCHMERGED-LOGICAL-c351t-97c06ba9ca973316e72a5bd3cb655ba1afd57e1b00cea6ad60cb457d88b986803
Notes ObjectType-Article-1
SourceType-Scholarly Journals-1
ObjectType-Feature-2
content type line 14
content type line 23
ORCID 0000-0002-1915-4179
0000-0002-4761-9973
0000-0003-0794-527X
0000-0003-1174-7241
0000-0002-0415-8556
0000-0003-1049-1002
0000-0001-8569-4192
PMID 34106869
PQID 2742703061
PQPubID 85436
PageCount 14
ParticipantIDs ieee_primary_9449483
pubmed_primary_34106869
proquest_miscellaneous_2539888441
proquest_journals_2742703061
crossref_primary_10_1109_TNNLS_2021_3084957
crossref_citationtrail_10_1109_TNNLS_2021_3084957
PublicationCentury 2000
PublicationDate 2022-12-01
PublicationDateYYYYMMDD 2022-12-01
PublicationDate_xml – month: 12
  year: 2022
  text: 2022-12-01
  day: 01
PublicationDecade 2020
PublicationPlace United States
PublicationPlace_xml – name: United States
– name: Piscataway
PublicationTitle IEEE transaction on neural networks and learning systems
PublicationTitleAbbrev TNNLS
PublicationTitleAlternate IEEE Trans Neural Netw Learn Syst
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 ref13
ref56
ref12
ref59
ref15
ref58
ref14
ref53
ref52
ref55
ref10
ref17
ref16
kipf (ref30) 2016
ref19
ref18
nguyen (ref46) 2048
freeman (ref2) 2000; 1
ref51
trivedi (ref40) 2017; 70
ref45
maheshwari (ref43) 2019
ref48
ref47
ref42
kipf (ref38) 2017
ref41
ref44
ref8
ref7
rossi (ref50) 2020
ref9
ref4
ref3
ref6
ref35
kazemi (ref24) 2020; 21
ref34
ref37
ref36
ref31
ref33
xu (ref49) 2020
mehran kazemi (ref23) 2019
ref39
goyal (ref29) 2018
theocharidis (ref1) 2009; 4
kingma (ref57) 2014
zhang (ref21) 2020
ref26
ref20
chen (ref54) 2018
ji (ref11) 2021
ref22
hamilton (ref5) 2017; 40
ref28
ref27
veli?kovi? (ref32) 2018
marinka (ref60) 2018; 34
hamilton (ref25) 2017
ref61
References_xml – year: 2016
  ident: ref30
  article-title: Variational graph auto-encoders
  publication-title: Proc NIPS Workshop Bayesian Deep Learn
– ident: ref4
  doi: 10.1145/980972.980992
– start-page: 969
  year: 2048
  ident: ref46
  article-title: Continuous-time dynamic network embeddings
  publication-title: Proc Companion Web Conf
– ident: ref17
  doi: 10.1109/TNNLS.2019.2920267
– ident: ref10
  doi: 10.1145/2623330.2623733
– ident: ref48
  doi: 10.1145/3292500.3330895
– ident: ref26
  doi: 10.1609/aaai.v32i1.11257
– ident: ref14
  doi: 10.1145/2736277.2741093
– ident: ref15
  doi: 10.1145/2806416.2806512
– ident: ref35
  doi: 10.1007/s11227-017-2225-1
– ident: ref6
  doi: 10.1109/TKDE.2018.2849727
– ident: ref34
  doi: 10.1609/aaai.v31i1.10488
– year: 2020
  ident: ref50
  article-title: Temporal graph networks for deep learning on dynamic graphs
  publication-title: Proc Int Conf Learn Represent
– year: 2017
  ident: ref38
  article-title: Semi-supervised classification with graph convolutional networks
  publication-title: Proc Int Conf Learn Represent
– ident: ref45
  doi: 10.1609/aaai.v35i5.16583
– ident: ref42
  doi: 10.1145/3336191.3371845
– start-page: 1024
  year: 2017
  ident: ref25
  article-title: Inductive representation learning on large graphs
  publication-title: Proc Adv Neural Inf Process Syst
– ident: ref28
  doi: 10.24963/ijcai.2018/288
– start-page: 1
  year: 2018
  ident: ref32
  article-title: Graph attention networks
  publication-title: Proc Int Conf Learn Represent
– ident: ref20
  doi: 10.1109/TBDATA.2018.2850013
– ident: ref19
  doi: 10.1109/TNNLS.2020.2978386
– ident: ref51
  doi: 10.1145/3340531.3411946
– ident: ref58
  doi: 10.1609/aaai.v34i04.5984
– ident: ref16
  doi: 10.1145/2939672.2939751
– volume: 40
  start-page: 52
  year: 2017
  ident: ref5
  article-title: Representation learning on graphs: Methods and applications
  publication-title: IEEE Data Eng Bull
– ident: ref18
  doi: 10.1109/TNNLS.2019.2945869
– ident: ref36
  doi: 10.1145/3442381.3449914
– volume: 34
  start-page: 457i
  year: 2018
  ident: ref60
  article-title: Modeling polypharmacy side effects with graph convolutional networks
  publication-title: Bioinformatics
  doi: 10.1093/bioinformatics/bty294
– volume: 21
  start-page: 1
  year: 2020
  ident: ref24
  article-title: Representation learning for dynamic graphs: A survey
  publication-title: J Mach Learn Res
– start-page: 1
  year: 2019
  ident: ref43
  article-title: DynGAN: Generative adversarial networks for dynamic network embedding
  publication-title: Proc Graph Represent Learn Workshop (NeurIPS)
– ident: ref31
  doi: 10.1145/3363574
– ident: ref33
  doi: 10.1109/TNNLS.2019.2919764
– ident: ref47
  doi: 10.1145/3357384.3357943
– year: 2014
  ident: ref57
  article-title: Auto-encoding variational Bayes
  publication-title: Proc Int Conf Learn Represent
– ident: ref41
  doi: 10.1145/3219819.3220024
– ident: ref53
  doi: 10.1145/1921632.1921636
– year: 2018
  ident: ref54
  article-title: GC-LSTM: Graph convolution embedded lstm for dynamic link prediction
  publication-title: arXiv 1812 04206
– ident: ref22
  doi: 10.1109/TNNLS.2018.2869225
– ident: ref59
  doi: 10.1145/1081870.1081893
– volume: 70
  start-page: 3462
  year: 2017
  ident: ref40
  article-title: Know-evolve: Deep temporal reasoning for dynamic knowledge graphs
  publication-title: Proc 34th Int Conf Mach Learn (JMLR)
– year: 2018
  ident: ref29
  article-title: DynGEM: Deep embedding method for dynamic graphs
  publication-title: arXiv 1805 11273
– ident: ref13
  doi: 10.1145/2623330.2623732
– ident: ref8
  doi: 10.1145/1401890.1401972
– ident: ref12
  doi: 10.1145/2939672.2939754
– ident: ref3
  doi: 10.1109/2945.841119
– ident: ref39
  doi: 10.1145/1217299.1217301
– volume: 1
  start-page: 4
  year: 2000
  ident: ref2
  article-title: Visualizing social networks
  publication-title: J Social Structure
– year: 2020
  ident: ref21
  article-title: Deep learning on graphs: A survey
  publication-title: IEEE Trans Knowl Data Eng
– ident: ref52
  doi: 10.1002/asi.20591
– ident: ref55
  doi: 10.1007/978-3-319-73198-8_10
– ident: ref61
  doi: 10.1016/j.knosys.2019.06.024
– ident: ref9
  doi: 10.1109/MCI.2019.2919396
– year: 2021
  ident: ref11
  article-title: A survey on knowledge graphs: Representation, acquisition, and applications
  publication-title: IEEE Trans Neural Netw Learn Syst
– ident: ref7
  doi: 10.1137/1.9781611972818.31
– year: 2019
  ident: ref23
  article-title: Representation learning for dynamic graphs: A survey
  publication-title: arXiv 1905 11485
– ident: ref56
  doi: 10.1109/TKDE.2016.2591009
– ident: ref37
  doi: 10.1145/2939672.2939753
– start-page: 1
  year: 2020
  ident: ref49
  article-title: Inductive representation learning on temporal graphs
  publication-title: Proc Int Conf Learn Represent
– ident: ref27
  doi: 10.1145/3132847.3132919
– ident: ref44
  doi: 10.24963/ijcai.2019/548
– volume: 4
  start-page: 1535
  year: 2009
  ident: ref1
  article-title: Network visualization and analysis of gene expression data using biolayout express 3D
  publication-title: Nature Protocols
  doi: 10.1038/nprot.2009.177
SSID ssj0000605649
Score 2.5835621
Snippet Network representation learning or embedding aims to project the network into a low-dimensional space that can be devoted to different network tasks. Temporal...
SourceID proquest
pubmed
crossref
ieee
SourceType Aggregation Database
Index Database
Enrichment Source
Publisher
StartPage 7400
SubjectTerms Embedding
Heredity
Inheritances
Learning
Link prediction
Logic gates
Matrix decomposition
Network analysis
Network topologies
Network topology
Neural networks
Neural Networks, Computer
Parameters
Predictive models
Recurrent neural networks
Regularization
Representations
self-attention mechanism
Social networking (online)
Task analysis
temporal network embedding (TNE)
Topology
variational autoencoder (VAE)
Title Temporal Network Embedding for Link Prediction via VAE Joint Attention Mechanism
URI https://ieeexplore.ieee.org/document/9449483
https://www.ncbi.nlm.nih.gov/pubmed/34106869
https://www.proquest.com/docview/2742703061
https://www.proquest.com/docview/2539888441
Volume 33
WOSCitedRecordID wos000732095200001&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: 2162-2388
  dateEnd: 99991231
  omitProxy: false
  ssIdentifier: ssj0000605649
  issn: 2162-237X
  databaseCode: RIE
  dateStart: 20120101
  isFulltext: true
  titleUrlDefault: https://ieeexplore.ieee.org/
  providerName: IEEE
link http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwlV1La9wwEB6S0EMvTdv04TYNKvTWOrFlW4_jUjaUkpqFbsPejDTSwkLiLbve_P5q5AcU2kJvBo9ko5mRZjSPD-BDWWlEa_NUGuRp6UqdGm4xJUCUtXEGTWzXdHsj61qtVnpxBJ-mWhjvfUw-85f0GGP5bosHuiq70iU1MymO4VhK0ddqTfcpWbDLRbR2eS54ygu5GmtkMn21rOub78Eb5PllkangFBD4XtjAqUBC_3YkRYyVv5ub8di5Pv2_H34KTwbzks16eXgGR759DqcjdAMbNPkMFsu-JdUdq_s8cDa_t97RQcaCGcvIRWWLHUVxiHPsYWPY7WzOvm43bcdmXddnSbJvniqHN_v7F_Djer78_CUdwBVSLKq8S7XETFij0WiCbRReclNZV6AVVWVNbtaukj4PWoneCONEhraspFPKaiVUVryEk3bb-tfAFFaoZaBHV5YuXytbhIHCepVxjxwTyMf1bXDoPE4AGHdN9EAy3UT2NMSeZmBPAh-nMT_7vhv_pD6jxZ8oh3VP4HxkYzOo5r6h2DRtcyJP4P30OigVRUpM67eHQFMVWikVTMUEXvXsn-YepebNn7_5Fh5zqpCIGS_ncNLtDv4dPMKHbrPfXQTJXamLKLm_AKET6AQ
linkProvider IEEE
linkToHtml http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwlV3db9MwED-NgQQvDBiDwAAj8QbZYid27McKdRrQRZUoU98if1WqtKWoTff343M-JCRA4i1Szk5057PvfB8_gA8FV9YaQ9NSW5YWrlCpZsamCIiy0k5bHds1Xc_KqpLLpZofwKexFsZ7H5PP_Bk-xli-29g9XpWdqwKbmeT34D4vCpZ11VrjjUoWLHMR7V1GBUtZXi6HKplMnS-qavY9-IOMnuWZDG4Bwu-FLRxLJNRvh1JEWfm7wRkPnouj__vlJ_C4NzDJpFsRT-HAN8_gaABvIL0uH8N80TWluiFVlwlOprfGOzzKSDBkCTqpZL7FOA7KjtytNbmeTMnXzbppyaRtuzxJcuWxdni9u30OPy6mi8-XaQ-vkNqc0zZVpc2E0cpqhcCNwpdMc-NyawTnRlO9crz0NOil9VpoJzJrCl46KY2SQmb5CRw2m8a_BCItt6oM9NYVhaMrafIwUBgvM-YtswnQgb-17XuPIwTGTR19kEzVUTw1iqfuxZPAx3HMz67zxj-pj5H5I2XP9wROBzHWvXLuaoxO40YnaALvx9dBrTBWohu_2QcanispZTAWE3jRiX-ce1g1r_78zXfw8HJxNatnX6pvr-ERw3qJmP9yCoftdu_fwAN7165327dx_f4CYZHqYw
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=Temporal+Network+Embedding+for+Link+Prediction+via+VAE+Joint+Attention+Mechanism&rft.jtitle=IEEE+transaction+on+neural+networks+and+learning+systems&rft.au=Jiao%2C+Pengfei&rft.au=Guo%2C+Xuan&rft.au=Xin+Jing&rft.au=He%2C+Dongxiao&rft.date=2022-12-01&rft.pub=The+Institute+of+Electrical+and+Electronics+Engineers%2C+Inc.+%28IEEE%29&rft.issn=2162-237X&rft.eissn=2162-2388&rft.volume=33&rft.issue=12&rft.spage=7400&rft_id=info:doi/10.1109%2FTNNLS.2021.3084957&rft.externalDBID=NO_FULL_TEXT
thumbnail_l http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/lc.gif&issn=2162-237X&client=summon
thumbnail_m http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/mc.gif&issn=2162-237X&client=summon
thumbnail_s http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/sc.gif&issn=2162-237X&client=summon