Learning deep neural networks for node classification

•Propose a novel deep neural network method for node classification.•The model could overcome the existing problem of only getting the suboptimal solution.•A superior performance of results demonstrates the effectiveness of proposed approach. Deep Neural Network (DNN) has made great leaps in image c...

Ausführliche Beschreibung

Gespeichert in:
Bibliographische Detailangaben
Veröffentlicht in:Expert systems with applications Jg. 137; S. 324 - 334
Hauptverfasser: Li, Bentian, Pi, Dechang
Format: Journal Article
Sprache:Englisch
Veröffentlicht: New York Elsevier Ltd 15.12.2019
Elsevier BV
Schlagworte:
ISSN:0957-4174, 1873-6793
Online-Zugang:Volltext
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
Abstract •Propose a novel deep neural network method for node classification.•The model could overcome the existing problem of only getting the suboptimal solution.•A superior performance of results demonstrates the effectiveness of proposed approach. Deep Neural Network (DNN) has made great leaps in image classification and speech recognition in recent years. However, employing DNN for node classification such as in social network remains to be a non-trivial problem. Moreover, the current advanced method of implementing node classification tasks usually takes two steps, i.e. firstly, the embedding vector of the node is obtained through network embedding and then the classifier such as SVM is leveraged to do the task. Distinctly, this may only get the suboptimal solution of the problem. To settle the above issues, a novel Deep Neural Network method for node classification named DNNNC is proposed in the framework of Deep Learning. Specifically, we first get the positive pointwise mutual information (PPMI) matrix from the given adjacency matrix. Then, the data is fed to deep neural network composed of deep stacked sparse autoencoders and softmax layer, which could learn the node representation while encoding the rich nonlinear structural and semantic information and could be well trained for node classification under the DNN framework. Extensive experiments are conducted on real-world network datasets for node classification task and have shown that the proposed model DNNNC outperforms the state-of-the-art method in the view of superior performance.
AbstractList •Propose a novel deep neural network method for node classification.•The model could overcome the existing problem of only getting the suboptimal solution.•A superior performance of results demonstrates the effectiveness of proposed approach. Deep Neural Network (DNN) has made great leaps in image classification and speech recognition in recent years. However, employing DNN for node classification such as in social network remains to be a non-trivial problem. Moreover, the current advanced method of implementing node classification tasks usually takes two steps, i.e. firstly, the embedding vector of the node is obtained through network embedding and then the classifier such as SVM is leveraged to do the task. Distinctly, this may only get the suboptimal solution of the problem. To settle the above issues, a novel Deep Neural Network method for node classification named DNNNC is proposed in the framework of Deep Learning. Specifically, we first get the positive pointwise mutual information (PPMI) matrix from the given adjacency matrix. Then, the data is fed to deep neural network composed of deep stacked sparse autoencoders and softmax layer, which could learn the node representation while encoding the rich nonlinear structural and semantic information and could be well trained for node classification under the DNN framework. Extensive experiments are conducted on real-world network datasets for node classification task and have shown that the proposed model DNNNC outperforms the state-of-the-art method in the view of superior performance.
Deep Neural Network (DNN) has made great leaps in image classification and speech recognition in recent years. However, employing DNN for node classification such as in social network remains to be a non-trivial problem. Moreover, the current advanced method of implementing node classification tasks usually takes two steps, i.e. firstly, the embedding vector of the node is obtained through network embedding and then the classifier such as SVM is leveraged to do the task. Distinctly, this may only get the suboptimal solution of the problem. To settle the above issues, a novel Deep Neural Network method for node classification named DNNNC is proposed in the framework of Deep Learning. Specifically, we first get the positive pointwise mutual information (PPMI) matrix from the given adjacency matrix. Then, the data is fed to deep neural network composed of deep stacked sparse autoencoders and softmax layer, which could learn the node representation while encoding the rich nonlinear structural and semantic information and could be well trained for node classification under the DNN framework. Extensive experiments are conducted on real-world network datasets for node classification task and have shown that the proposed model DNNNC outperforms the state-of-the-art method in the view of superior performance.
Author Li, Bentian
Pi, Dechang
Author_xml – sequence: 1
  givenname: Bentian
  orcidid: 0000-0001-6504-3851
  surname: Li
  fullname: Li, Bentian
  email: lbt@nuaa.edu.cn
  organization: College of Computer Science and Technology, Nanjing University of Aeronautics and Astronautics, Nanjing 211106, China
– sequence: 2
  givenname: Dechang
  surname: Pi
  fullname: Pi, Dechang
  email: dc.pi@nuaa.edu.cn
  organization: College of Computer Science and Technology, Nanjing University of Aeronautics and Astronautics, Nanjing 211106, China
BookMark eNp9kD1PwzAQhi1UJNrCH2CKxJxwthM7kVhQxZdUiQVmy7XPyKHYxU6p-PeklImhw-ld7rmPZ0YmIQYk5JJCRYGK677CvNMVA9pVICsAcUKmtJW8FLLjEzKFrpFlTWV9RmY59wBUAsgpaZaoU_DhrbCImyLgNun1GMMupvdcuJiKEC0WZq1z9s4bPfgYzsmp0-uMF385J6_3dy-Lx3L5_PC0uF2WhrN2KJ2QDlummeZ1K8BwDQ0DjWDHctqZRpiVYXVjVoB11xomNLW2k1yjtqLjc3J1mLtJ8XOLeVB93KYwrlSMg6ilACnGrvbQZVLMOaFTxg-_dw5J-7WioPaSVK_2ktRekgKpRkkjyv6hm-Q_dPo-Dt0cIBxf__KYVDYeg0HrE5pB2eiP4T-iu4M6
CitedBy_id crossref_primary_10_1016_j_knosys_2022_108699
crossref_primary_10_1016_j_knosys_2021_107345
crossref_primary_10_1007_s00521_021_06617_z
crossref_primary_10_1007_s11633_023_1470_4
crossref_primary_10_1016_j_eswa_2021_114655
crossref_primary_10_1016_j_isatra_2020_10_033
crossref_primary_10_1016_j_eswa_2021_114895
crossref_primary_10_1109_TKDE_2023_3312358
crossref_primary_10_1007_s10489_025_06818_2
crossref_primary_10_1016_j_eswa_2021_115063
crossref_primary_10_1016_j_eswa_2025_127292
crossref_primary_10_1016_j_neucom_2025_131368
crossref_primary_10_1177_01655515221111002
crossref_primary_10_1007_s11042_024_19525_w
crossref_primary_10_1109_MCI_2022_3222049
crossref_primary_10_1016_j_eswa_2020_113957
crossref_primary_10_3390_e23111542
crossref_primary_10_3390_e26020149
crossref_primary_10_1007_s13042_025_02626_9
crossref_primary_10_3390_app12189290
crossref_primary_10_3390_app112311447
crossref_primary_10_1016_j_knosys_2021_107438
crossref_primary_10_1007_s40747_023_01211_3
crossref_primary_10_1371_journal_pone_0302327
crossref_primary_10_1016_j_petrol_2022_110323
crossref_primary_10_1007_s40747_022_00641_9
crossref_primary_10_1007_s00521_020_04908_5
crossref_primary_10_1007_s11227_022_04767_y
crossref_primary_10_1016_j_optcom_2020_126243
crossref_primary_10_3390_math11173680
crossref_primary_10_1108_DTA_06_2022_0247
crossref_primary_10_1016_j_ins_2022_06_088
crossref_primary_10_1093_comjnl_bxae060
crossref_primary_10_1007_s11408_021_00391_7
Cites_doi 10.1371/journal.pone.0200600
10.1016/S0893-6080(05)80056-5
10.1007/s10618-017-0533-y
10.1109/TPAMI.2013.50
10.1109/TPAMI.2007.250598
10.1016/j.eswa.2016.10.024
10.1126/science.290.5500.2323
10.1109/TKDE.2018.2807452
10.1038/nature14539
10.1038/nrn2575
10.1109/TNNLS.2015.2479223
10.1109/MNET.2018.1700282
10.1109/TKDE.2018.2807840
10.3758/BF03193020
10.1126/science.290.5500.2319
ContentType Journal Article
Copyright 2019 Elsevier Ltd
Copyright Elsevier BV Dec 15, 2019
Copyright_xml – notice: 2019 Elsevier Ltd
– notice: Copyright Elsevier BV Dec 15, 2019
DBID AAYXX
CITATION
7SC
8FD
JQ2
L7M
L~C
L~D
DOI 10.1016/j.eswa.2019.07.006
DatabaseName CrossRef
Computer and Information Systems 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
DatabaseTitle CrossRef
Computer and Information Systems Abstracts
Technology Research Database
Computer and Information Systems Abstracts – Academic
Advanced Technologies Database with Aerospace
ProQuest Computer Science Collection
Computer and Information Systems Abstracts Professional
DatabaseTitleList
Computer and Information Systems Abstracts
DeliveryMethod fulltext_linktorsrc
Discipline Computer Science
EISSN 1873-6793
EndPage 334
ExternalDocumentID 10_1016_j_eswa_2019_07_006
S0957417419304853
GroupedDBID --K
--M
.DC
.~1
0R~
13V
1B1
1RT
1~.
1~5
4.4
457
4G.
5GY
5VS
7-5
71M
8P~
9JN
9JO
AAAKF
AABNK
AACTN
AAEDT
AAEDW
AAIAV
AAIKJ
AAKOC
AALRI
AAOAW
AAQFI
AARIN
AAXUO
AAYFN
ABBOA
ABFNM
ABMAC
ABMVD
ABUCO
ABYKQ
ACDAQ
ACGFS
ACHRH
ACNTT
ACRLP
ACZNC
ADBBV
ADEZE
ADTZH
AEBSH
AECPX
AEKER
AENEX
AFKWA
AFTJW
AGHFR
AGJBL
AGUBO
AGUMN
AGYEJ
AHHHB
AHJVU
AHZHX
AIALX
AIEXJ
AIKHN
AITUG
AJOXV
ALEQD
ALMA_UNASSIGNED_HOLDINGS
AMFUW
AMRAJ
AOUOD
APLSM
AXJTR
BJAXD
BKOJK
BLXMC
BNSAS
CS3
DU5
EBS
EFJIC
EFLBG
EJD
EO8
EO9
EP2
EP3
F5P
FDB
FIRID
FNPLU
FYGXN
G-Q
GBLVA
GBOLZ
HAMUX
IHE
J1W
JJJVA
KOM
LG9
LY1
LY7
M41
MO0
N9A
O-L
O9-
OAUVE
OZT
P-8
P-9
P2P
PC.
PQQKQ
Q38
RIG
ROL
RPZ
SDF
SDG
SDP
SDS
SES
SPC
SPCBC
SSB
SSD
SSL
SST
SSV
SSZ
T5K
TN5
~G-
29G
9DU
AAAKG
AAQXK
AATTM
AAXKI
AAYWO
AAYXX
ABJNI
ABKBG
ABUFD
ABWVN
ABXDB
ACLOT
ACNNM
ACRPL
ACVFH
ADCNI
ADJOM
ADMUD
ADNMO
AEIPS
AEUPX
AFJKZ
AFPUW
AGQPQ
AIGII
AIIUN
AKBMS
AKRWK
AKYEP
ANKPU
APXCP
ASPBG
AVWKF
AZFZN
CITATION
EFKBS
FEDTE
FGOYB
G-2
HLZ
HVGLF
HZ~
R2-
SBC
SET
SEW
WUQ
XPP
ZMT
~HD
7SC
8FD
JQ2
L7M
L~C
L~D
ID FETCH-LOGICAL-c328t-f67fe82a2a34860c3a0520ae0dae0fafc56cbc245cb0e498c26a1dd973aead693
ISICitedReferencesCount 36
ISICitedReferencesURI http://www.webofscience.com/api/gateway?GWVersion=2&SrcApp=Summon&SrcAuth=ProQuest&DestLinkType=CitingArticles&DestApp=WOS_CPL&KeyUT=000487167500021&url=https%3A%2F%2Fcvtisr.summon.serialssolutions.com%2F%23%21%2Fsearch%3Fho%3Df%26include.ft.matches%3Dt%26l%3Dnull%26q%3D
ISSN 0957-4174
IngestDate Sun Nov 09 05:50:57 EST 2025
Sat Nov 29 07:04:10 EST 2025
Tue Nov 18 22:43:31 EST 2025
Fri Feb 23 02:24:25 EST 2024
IsPeerReviewed true
IsScholarly true
Keywords Deep learning
Deep neural network
Network embedding
Node classification
Language English
LinkModel OpenURL
MergedId FETCHMERGED-LOGICAL-c328t-f67fe82a2a34860c3a0520ae0dae0fafc56cbc245cb0e498c26a1dd973aead693
Notes ObjectType-Article-1
SourceType-Scholarly Journals-1
ObjectType-Feature-2
content type line 14
ORCID 0000-0001-6504-3851
PQID 2306476076
PQPubID 2045477
PageCount 11
ParticipantIDs proquest_journals_2306476076
crossref_citationtrail_10_1016_j_eswa_2019_07_006
crossref_primary_10_1016_j_eswa_2019_07_006
elsevier_sciencedirect_doi_10_1016_j_eswa_2019_07_006
PublicationCentury 2000
PublicationDate 2019-12-15
PublicationDateYYYYMMDD 2019-12-15
PublicationDate_xml – month: 12
  year: 2019
  text: 2019-12-15
  day: 15
PublicationDecade 2010
PublicationPlace New York
PublicationPlace_xml – name: New York
PublicationTitle Expert systems with applications
PublicationYear 2019
Publisher Elsevier Ltd
Elsevier BV
Publisher_xml – name: Elsevier Ltd
– name: Elsevier BV
References Perozzi, Al-Rfou, Skiena (bib0026) 2014
Rumelhart, Hinton, Williams (bib0028) 1988
Vincent, Larochelle, Lajoie, Bengio, Manzagol (bib0033) 2010; 11
Zheleva, Getoor (bib0041) 2009
Mikolov, Chen, Corrado, Dean (bib0022) 2013
Møller (bib0025) 1993; 6
Levy, Goldberg (bib0019) 2014
Bengio, Courville, Vincent (bib0003) 2013; 35
Wang, Wang, Wang, Zhao, Zhang, Zhang (bib0035) 2018
Yang, Liu, Zhao, Sun, Chang (bib0039) 2015
Huang, Li, Hu (bib0015) 2017
Li, Zhu, Zhang (bib0021) 2016
Bullinaria, Levy (bib0004) 2007; 39
Cai, Zheng, Chang (bib0006) 2018; 30
Defferrard, Bresson, Vandergheynst (bib0010) 2016
Jian, Li, Liu (bib0016) 2018; 32
Mikolov, Sutskever, Chen, Corrado, Dean (bib0023) 2013
Grover, Leskovec (bib0012) 2016
Goodfellow, Pouget-Abadie, Mirza, Xu, Warde-Farley, Ozair (bib0011) 2014
Tang, Qu, Wang, Zhang, Yan, Mei (bib0031) 2015
Wang, Cui, Zhu (bib0034) 2016
Xiaofei, Partha (bib0037) 2003
Roweis, Saul (bib0027) 2000; 290
Tang, Aggarwal, Liu (bib0030) 2016
Hinton, Zemel (bib0013) 1993
Kipf, Welling (bib0017) 2017
Tenenbaum, Silva, Langford (bib0032) 2000; 290
Lecun, Bengio, Hinton (bib0018) 2015; 521
Bullmore, Sporns (bib0005) 2009; 10
Ahmed, Shervashidze, Narayanamurthy, Josifovski, Smola (bib0001) 2013
Dai, Li, Tang, Wang (bib0009) 2018
Church, Hanks (bib0008) 1990; 16
Hosseini-Asl, Zurada, Nasraoui (bib0014) 2016; 27
Zheng, Han, Sun (bib0042) 2018; 30
Mnih, Hinton (bib0024) 2008
Wang, Cui, Wang, Pei, Zhu, Yang (bib0036) 2017
Cao, Lu, Xu (bib0007) 2016
Yan, Xu, Zhang, Zhang, Yang, Lin (bib0038) 2007; 29
Zhang, Li, Gao, Bian, Song, Dong (bib0040) 2018; 32
Belkin, Niyogi (bib0002) 2002
Li, Pi (bib0020) 2018; 13
Seo, Kim, Lee, Baik (bib0029) 2017; 69
Defferrard (10.1016/j.eswa.2019.07.006_bib0010) 2016
Hinton (10.1016/j.eswa.2019.07.006_bib0013) 1993
Li (10.1016/j.eswa.2019.07.006_bib0020) 2018; 13
Huang (10.1016/j.eswa.2019.07.006_bib0015) 2017
Møller (10.1016/j.eswa.2019.07.006_bib0025) 1993; 6
Wang (10.1016/j.eswa.2019.07.006_bib0036) 2017
Cai (10.1016/j.eswa.2019.07.006_bib0006) 2018; 30
Xiaofei (10.1016/j.eswa.2019.07.006_bib0037) 2003
Roweis (10.1016/j.eswa.2019.07.006_bib0027) 2000; 290
Levy (10.1016/j.eswa.2019.07.006_bib0019) 2014
Seo (10.1016/j.eswa.2019.07.006_bib0029) 2017; 69
Dai (10.1016/j.eswa.2019.07.006_bib0009) 2018
Belkin (10.1016/j.eswa.2019.07.006_bib0002) 2002
Bullinaria (10.1016/j.eswa.2019.07.006_bib0004) 2007; 39
Hosseini-Asl (10.1016/j.eswa.2019.07.006_bib0014) 2016; 27
Tang (10.1016/j.eswa.2019.07.006_bib0030) 2016
Mikolov (10.1016/j.eswa.2019.07.006_bib0022) 2013
Grover (10.1016/j.eswa.2019.07.006_bib0012) 2016
Rumelhart (10.1016/j.eswa.2019.07.006_bib0028) 1988
Wang (10.1016/j.eswa.2019.07.006_bib0035) 2018
Cao (10.1016/j.eswa.2019.07.006_bib0007) 2016
Ahmed (10.1016/j.eswa.2019.07.006_bib0001) 2013
Yang (10.1016/j.eswa.2019.07.006_bib0039) 2015
Lecun (10.1016/j.eswa.2019.07.006_bib0018) 2015; 521
Mikolov (10.1016/j.eswa.2019.07.006_bib0023) 2013
Li (10.1016/j.eswa.2019.07.006_bib0021) 2016
Zheleva (10.1016/j.eswa.2019.07.006_bib0041) 2009
Bullmore (10.1016/j.eswa.2019.07.006_bib0005) 2009; 10
Perozzi (10.1016/j.eswa.2019.07.006_bib0026) 2014
Mnih (10.1016/j.eswa.2019.07.006_bib0024) 2008
Wang (10.1016/j.eswa.2019.07.006_bib0034) 2016
Jian (10.1016/j.eswa.2019.07.006_bib0016) 2018; 32
Zheng (10.1016/j.eswa.2019.07.006_bib0042) 2018; 30
Vincent (10.1016/j.eswa.2019.07.006_bib0033) 2010; 11
Yan (10.1016/j.eswa.2019.07.006_bib0038) 2007; 29
Tang (10.1016/j.eswa.2019.07.006_bib0031) 2015
Church (10.1016/j.eswa.2019.07.006_bib0008) 1990; 16
Bengio (10.1016/j.eswa.2019.07.006_bib0003) 2013; 35
Goodfellow (10.1016/j.eswa.2019.07.006_bib0011) 2014
Kipf (10.1016/j.eswa.2019.07.006_bib0017) 2017
Tenenbaum (10.1016/j.eswa.2019.07.006_bib0032) 2000; 290
Zhang (10.1016/j.eswa.2019.07.006_bib0040) 2018; 32
References_xml – volume: 35
  start-page: 1798
  year: 2013
  end-page: 1828
  ident: bib0003
  article-title: Representation learning: A review and new perspectives
  publication-title: IEEE Transactions on Pattern Analysis and Machine Intelligence
– volume: 39
  start-page: 510
  year: 2007
  end-page: 526
  ident: bib0004
  article-title: Extracting semantic representations from word co-occurrence statistics: A computational study
  publication-title: Behavior Research Methods
– year: 2018
  ident: bib0035
  article-title: Graphgan: Graph representation learning with generative adversarial nets
  publication-title: Proceedings of the thirty-second AAAI conference on artificial intelligence
– volume: 30
  start-page: 1616
  year: 2018
  end-page: 1637
  ident: bib0006
  article-title: A comprehensive survey of graph embedding: Problems, techniques and applications
  publication-title: IEEE Transactions on Knowledge & Data Engineering
– start-page: 3844
  year: 2016
  end-page: 3852
  ident: bib0010
  article-title: Convolutional neural networks on graphs with fast localized spectral filtering
  publication-title: Advances in neural information processing systems
– volume: 13
  start-page: e0200600
  year: 2018
  ident: bib0020
  article-title: Analysis of global stock index data during crisis period via complex network approach
  publication-title: Plos One
– start-page: 2177
  year: 2014
  end-page: 2185
  ident: bib0019
  article-title: Neural word embedding as implicit matrix factorization
  publication-title: Advances in neural information processing systems
– start-page: 1004
  year: 2016
  end-page: 1013
  ident: bib0021
  article-title: Discriminative deep random walk for network classification
  publication-title: Meeting of the association for computational linguistics
– start-page: 531
  year: 2009
  end-page: 540
  ident: bib0041
  article-title: To join or not to join: The illusion of privacy in social networks with mixed public and private user profiles
  publication-title: International world wide web conferences
– start-page: 37
  year: 2013
  end-page: 48
  ident: bib0001
  article-title: Distributed large-scale natural graph factorization
  publication-title: Proceedings of the 22nd international conference on world wide web
– start-page: 2672
  year: 2014
  end-page: 2680
  ident: bib0011
  article-title: Generative adversarial nets
  publication-title: International conference on neural information processing systems
– year: 2013
  ident: bib0022
  article-title: Efficient estimation of word representations in vector space
  publication-title: International conference on learning representations
– start-page: 701
  year: 2014
  end-page: 710
  ident: bib0026
  article-title: Deepwalk: Online learning of social representations
  publication-title: The 20th ACM SIGKDD international conference on knowledge discovery and data mining
– start-page: 3
  year: 1993
  end-page: 10
  ident: bib0013
  article-title: Autoencoders, minimum description length and helmholtz free energy
  publication-title: International conference on neural information processing systems
– start-page: 1081
  year: 2008
  end-page: 1088
  ident: bib0024
  article-title: A scalable hierarchical distributed language model
  publication-title: International conference on neural information processing systems
– volume: 521
  start-page: 436
  year: 2015
  end-page: 444
  ident: bib0018
  article-title: Deep learning
  publication-title: Nature
– volume: 69
  start-page: 135
  year: 2017
  end-page: 148
  ident: bib0029
  article-title: Personalized recommender system based on friendship strength in social network services
  publication-title: Expert Systems with Applications
– start-page: 1145
  year: 2016
  end-page: 1152
  ident: bib0007
  article-title: Deep neural networks for learning graph representations
  publication-title: Thirtieth AAAI conference on artificial intelligence
– start-page: 1225
  year: 2016
  end-page: 1234
  ident: bib0034
  article-title: Structural deep network embedding
  publication-title: ACM SIGKDD international conference on knowledge discovery and data mining
– start-page: 1067
  year: 2015
  end-page: 1077
  ident: bib0031
  article-title: Line: Large-scale information network embedding
  publication-title: International world wide web conferences
– start-page: 673
  year: 1988
  end-page: 695
  ident: bib0028
  article-title: Neurocomputing: Foundations of research
– volume: 16
  start-page: 22
  year: 1990
  end-page: 29
  ident: bib0008
  article-title: Word association norms, mutual information, and lexicography
  publication-title: Computational Linguistics
– start-page: 186
  year: 2003
  end-page: 197
  ident: bib0037
  article-title: Locality preserving projections
  publication-title: Advances in neural information processing systems
– start-page: 855
  year: 2016
  end-page: 864
  ident: bib0012
  article-title: node2vec: Scalable feature learning for networks
  publication-title: Proceedings of the 22nd ACM SIGKDD international conference on knowledge discovery and data mining
– volume: 290
  start-page: 2319
  year: 2000
  end-page: 2323
  ident: bib0032
  article-title: A global geometric framework for nonlinear dimensionality reduction
  publication-title: Science
– start-page: 2111
  year: 2015
  end-page: 2117
  ident: bib0039
  article-title: Network representation learning with rich text information
  publication-title: Proceedings of the twenty-fourth international joint conference on artificial intelligence
– year: 2018
  ident: bib0009
  article-title: Adversarial network embedding
  publication-title: Proceedings of the thirty-second AAAI conference on artificial intelligence
– volume: 32
  start-page: 231
  year: 2018
  end-page: 257
  ident: bib0016
  article-title: Toward online node classification on streaming networks
  publication-title: Data Mining and Knowledge Discovery
– volume: 10
  start-page: 186
  year: 2009
  end-page: 198
  ident: bib0005
  article-title: Complex brain networks: graph theoretical analysis of structural and functional systems
  publication-title: Nature Reviews Neuroscience
– volume: 11
  start-page: 3371
  year: 2010
  end-page: 3408
  ident: bib0033
  article-title: Stacked denoising autoencoders: Learning useful representations in a deep network with a local denoising criterion
  publication-title: Journal of Machine Learning Research
– volume: 30
  start-page: 1652
  year: 2018
  end-page: 1671
  ident: bib0042
  article-title: A survey of location prediction on twitter
  publication-title: IEEE Transactions on Knowledge and Data Engineering
– start-page: 633
  year: 2017
  end-page: 641
  ident: bib0015
  article-title: Accelerated attributed network embedding.
  publication-title: Siam international conference on data mining
– volume: 27
  start-page: 2486
  year: 2016
  end-page: 2498
  ident: bib0014
  article-title: Deep learning of part-based representation of data using sparse autoencoders with nonnegativity constraints
  publication-title: IEEE Transactions on Neural Networks & Learning Systems
– year: 2017
  ident: bib0017
  article-title: Semi-supervised classification with graph convolutional networks
  publication-title: International conference on learning representations
– volume: 290
  start-page: 2323
  year: 2000
  end-page: 2326
  ident: bib0027
  article-title: Nonlinear dimensionality reduction by locally linear embedding.
  publication-title: Science
– start-page: 203
  year: 2017
  end-page: 209
  ident: bib0036
  article-title: Community preserving network embedding
  publication-title: Proceedings of the thirty-first AAAI conference on artificial intelligence
– start-page: 3111
  year: 2013
  end-page: 3119
  ident: bib0023
  article-title: Distributed representations of words and phrases and their compositionality
  publication-title: 27th annual conference on neural information processing systems
– start-page: 585
  year: 2002
  end-page: 591
  ident: bib0002
  article-title: Laplacian eigenmaps and spectral techniques for embedding and clustering
  publication-title: Advances in neural information processing systems
– volume: 6
  start-page: 525
  year: 1993
  end-page: 533
  ident: bib0025
  article-title: A scaled conjugate gradient algorithm for fast supervised learning
  publication-title: Neural networks
– volume: 29
  start-page: 40
  year: 2007
  end-page: 51
  ident: bib0038
  article-title: Graph embedding and extension: A general framework for dimensionality reduction
  publication-title: IEEE Transactions on Pattern Analysis and Machine Intelligence
– start-page: 54
  year: 2016
  end-page: 62
  ident: bib0030
  article-title: Node classification in signed social networks
  publication-title: Proceedings of the 2016 SIAM international conference on data mining, miami, florida, usa, may 5–7, 2016
– volume: 32
  start-page: 146
  year: 2018
  end-page: 153
  ident: bib0040
  article-title: Mobile social big data: Wechat moments dataset, network applications, and opportunities
  publication-title: IEEE Network
– volume: 13
  start-page: e0200600
  issue: 7
  year: 2018
  ident: 10.1016/j.eswa.2019.07.006_bib0020
  article-title: Analysis of global stock index data during crisis period via complex network approach
  publication-title: Plos One
  doi: 10.1371/journal.pone.0200600
– start-page: 54
  year: 2016
  ident: 10.1016/j.eswa.2019.07.006_bib0030
  article-title: Node classification in signed social networks
– start-page: 1067
  year: 2015
  ident: 10.1016/j.eswa.2019.07.006_bib0031
  article-title: Line: Large-scale information network embedding
– start-page: 3111
  year: 2013
  ident: 10.1016/j.eswa.2019.07.006_bib0023
  article-title: Distributed representations of words and phrases and their compositionality
– start-page: 37
  year: 2013
  ident: 10.1016/j.eswa.2019.07.006_bib0001
  article-title: Distributed large-scale natural graph factorization
– start-page: 2111
  year: 2015
  ident: 10.1016/j.eswa.2019.07.006_bib0039
  article-title: Network representation learning with rich text information
– start-page: 3844
  year: 2016
  ident: 10.1016/j.eswa.2019.07.006_bib0010
  article-title: Convolutional neural networks on graphs with fast localized spectral filtering
– year: 2017
  ident: 10.1016/j.eswa.2019.07.006_bib0017
  article-title: Semi-supervised classification with graph convolutional networks
– volume: 6
  start-page: 525
  issue: 4
  year: 1993
  ident: 10.1016/j.eswa.2019.07.006_bib0025
  article-title: A scaled conjugate gradient algorithm for fast supervised learning
  publication-title: Neural networks
  doi: 10.1016/S0893-6080(05)80056-5
– volume: 11
  start-page: 3371
  year: 2010
  ident: 10.1016/j.eswa.2019.07.006_bib0033
  article-title: Stacked denoising autoencoders: Learning useful representations in a deep network with a local denoising criterion
  publication-title: Journal of Machine Learning Research
– volume: 16
  start-page: 22
  issue: 1
  year: 1990
  ident: 10.1016/j.eswa.2019.07.006_bib0008
  article-title: Word association norms, mutual information, and lexicography
  publication-title: Computational Linguistics
– volume: 32
  start-page: 231
  issue: 1
  year: 2018
  ident: 10.1016/j.eswa.2019.07.006_bib0016
  article-title: Toward online node classification on streaming networks
  publication-title: Data Mining and Knowledge Discovery
  doi: 10.1007/s10618-017-0533-y
– start-page: 1081
  year: 2008
  ident: 10.1016/j.eswa.2019.07.006_bib0024
  article-title: A scalable hierarchical distributed language model
– volume: 35
  start-page: 1798
  issue: 8
  year: 2013
  ident: 10.1016/j.eswa.2019.07.006_bib0003
  article-title: Representation learning: A review and new perspectives
  publication-title: IEEE Transactions on Pattern Analysis and Machine Intelligence
  doi: 10.1109/TPAMI.2013.50
– year: 2013
  ident: 10.1016/j.eswa.2019.07.006_bib0022
  article-title: Efficient estimation of word representations in vector space
– year: 2018
  ident: 10.1016/j.eswa.2019.07.006_bib0035
  article-title: Graphgan: Graph representation learning with generative adversarial nets
– volume: 29
  start-page: 40
  issue: 1
  year: 2007
  ident: 10.1016/j.eswa.2019.07.006_bib0038
  article-title: Graph embedding and extension: A general framework for dimensionality reduction
  publication-title: IEEE Transactions on Pattern Analysis and Machine Intelligence
  doi: 10.1109/TPAMI.2007.250598
– start-page: 673
  year: 1988
  ident: 10.1016/j.eswa.2019.07.006_bib0028
– start-page: 633
  year: 2017
  ident: 10.1016/j.eswa.2019.07.006_bib0015
  article-title: Accelerated attributed network embedding.
– volume: 69
  start-page: 135
  year: 2017
  ident: 10.1016/j.eswa.2019.07.006_bib0029
  article-title: Personalized recommender system based on friendship strength in social network services
  publication-title: Expert Systems with Applications
  doi: 10.1016/j.eswa.2016.10.024
– start-page: 1225
  year: 2016
  ident: 10.1016/j.eswa.2019.07.006_bib0034
  article-title: Structural deep network embedding
– volume: 290
  start-page: 2323
  issue: 5500
  year: 2000
  ident: 10.1016/j.eswa.2019.07.006_bib0027
  article-title: Nonlinear dimensionality reduction by locally linear embedding.
  publication-title: Science
  doi: 10.1126/science.290.5500.2323
– start-page: 203
  year: 2017
  ident: 10.1016/j.eswa.2019.07.006_bib0036
  article-title: Community preserving network embedding
– start-page: 1145
  year: 2016
  ident: 10.1016/j.eswa.2019.07.006_bib0007
  article-title: Deep neural networks for learning graph representations
– start-page: 585
  year: 2002
  ident: 10.1016/j.eswa.2019.07.006_bib0002
  article-title: Laplacian eigenmaps and spectral techniques for embedding and clustering
– volume: 30
  start-page: 1616
  issue: 9
  year: 2018
  ident: 10.1016/j.eswa.2019.07.006_bib0006
  article-title: A comprehensive survey of graph embedding: Problems, techniques and applications
  publication-title: IEEE Transactions on Knowledge & Data Engineering
  doi: 10.1109/TKDE.2018.2807452
– volume: 521
  start-page: 436
  issue: 7553
  year: 2015
  ident: 10.1016/j.eswa.2019.07.006_bib0018
  article-title: Deep learning
  publication-title: Nature
  doi: 10.1038/nature14539
– volume: 10
  start-page: 186
  issue: 3
  year: 2009
  ident: 10.1016/j.eswa.2019.07.006_bib0005
  article-title: Complex brain networks: graph theoretical analysis of structural and functional systems
  publication-title: Nature Reviews Neuroscience
  doi: 10.1038/nrn2575
– start-page: 3
  year: 1993
  ident: 10.1016/j.eswa.2019.07.006_bib0013
  article-title: Autoencoders, minimum description length and helmholtz free energy
– start-page: 531
  year: 2009
  ident: 10.1016/j.eswa.2019.07.006_bib0041
  article-title: To join or not to join: The illusion of privacy in social networks with mixed public and private user profiles
– start-page: 855
  year: 2016
  ident: 10.1016/j.eswa.2019.07.006_bib0012
  article-title: node2vec: Scalable feature learning for networks
– start-page: 2672
  year: 2014
  ident: 10.1016/j.eswa.2019.07.006_bib0011
  article-title: Generative adversarial nets
– volume: 27
  start-page: 2486
  issue: 12
  year: 2016
  ident: 10.1016/j.eswa.2019.07.006_bib0014
  article-title: Deep learning of part-based representation of data using sparse autoencoders with nonnegativity constraints
  publication-title: IEEE Transactions on Neural Networks & Learning Systems
  doi: 10.1109/TNNLS.2015.2479223
– start-page: 2177
  year: 2014
  ident: 10.1016/j.eswa.2019.07.006_bib0019
  article-title: Neural word embedding as implicit matrix factorization
– volume: 32
  start-page: 146
  issue: 3
  year: 2018
  ident: 10.1016/j.eswa.2019.07.006_bib0040
  article-title: Mobile social big data: Wechat moments dataset, network applications, and opportunities
  publication-title: IEEE Network
  doi: 10.1109/MNET.2018.1700282
– start-page: 1004
  year: 2016
  ident: 10.1016/j.eswa.2019.07.006_bib0021
  article-title: Discriminative deep random walk for network classification
– volume: 30
  start-page: 1652
  issue: 9
  year: 2018
  ident: 10.1016/j.eswa.2019.07.006_bib0042
  article-title: A survey of location prediction on twitter
  publication-title: IEEE Transactions on Knowledge and Data Engineering
  doi: 10.1109/TKDE.2018.2807840
– start-page: 186
  year: 2003
  ident: 10.1016/j.eswa.2019.07.006_bib0037
  article-title: Locality preserving projections
– volume: 39
  start-page: 510
  issue: 3
  year: 2007
  ident: 10.1016/j.eswa.2019.07.006_bib0004
  article-title: Extracting semantic representations from word co-occurrence statistics: A computational study
  publication-title: Behavior Research Methods
  doi: 10.3758/BF03193020
– year: 2018
  ident: 10.1016/j.eswa.2019.07.006_bib0009
  article-title: Adversarial network embedding
– volume: 290
  start-page: 2319
  issue: 5500
  year: 2000
  ident: 10.1016/j.eswa.2019.07.006_bib0032
  article-title: A global geometric framework for nonlinear dimensionality reduction
  publication-title: Science
  doi: 10.1126/science.290.5500.2319
– start-page: 701
  year: 2014
  ident: 10.1016/j.eswa.2019.07.006_bib0026
  article-title: Deepwalk: Online learning of social representations
SSID ssj0017007
Score 2.5174956
Snippet •Propose a novel deep neural network method for node classification.•The model could overcome the existing problem of only getting the suboptimal solution.•A...
Deep Neural Network (DNN) has made great leaps in image classification and speech recognition in recent years. However, employing DNN for node classification...
SourceID proquest
crossref
elsevier
SourceType Aggregation Database
Enrichment Source
Index Database
Publisher
StartPage 324
SubjectTerms Artificial neural networks
Classification
Deep learning
Deep neural network
Embedding
Image classification
Machine learning
Network embedding
Neural networks
Node classification
Nodes
Object recognition
Social networks
Speech recognition
Title Learning deep neural networks for node classification
URI https://dx.doi.org/10.1016/j.eswa.2019.07.006
https://www.proquest.com/docview/2306476076
Volume 137
WOSCitedRecordID wos000487167500021&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: 1873-6793
  dateEnd: 99991231
  omitProxy: false
  ssIdentifier: ssj0017007
  issn: 0957-4174
  databaseCode: AIEXJ
  dateStart: 19950101
  isFulltext: true
  titleUrlDefault: https://www.sciencedirect.com
  providerName: Elsevier
link http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwtV1ba9RAFB609cGX1ivWVpkH35YpSSZzyWOVioqUghX2bZhbwEXSZXdt-_N75pZdVywq-JAQQi7DfJMzZ06-cz6E3rTcOi6lJ9qwirRGUmJYbYiuOs9l72ytTRSbEGdncjrtzrPM3TLKCYhhkDc33fy_Qg3nAOyQOvsXcI8PhRNwDKDDHmCH_R8B_7kEO5z380moVwkoDIntHYsvTIZL5yc2uM2BJ7SGZjbS8vxilWs8l-y3jf_cI4cnEgHeBrrReoidp8R1HxOKN0MKddRDSEmVKc5Vcl3WxKIUMBSkrZOmzrFP5lIKSrhIGoejPU1VXLJFpE27MbnSFLn8xW6nEMLs2C-vQzGouosVVautItlx2v0SGhLaAa4nmB9G76PdRrAOrPLuycfT6afxJ5KoUrZ8aXjOmUr0vu03_c4v2Zqho9tx8Qjt5fUCPkk4P0b3_PAE7RctDpxN81PECuw4wI4T7LjAjgF2HGDHP8P-DH19f3rx7gPJkhjE0kauSM9F72WjG02DepilOvCYtK8cbL3uLePW2KZl1lS-7aRtuK6d6wTVYDJ4R5-jneFy8C8Qdpa6VkganNSWOiu1rTwDj9TAktkYdoDq0iHK5nrxQbbkuyrEwJkKnahCJ6oq0Bj4AZqM98xTtZQ7r2aln1X295Ifp2BY3HnfUQFF5Q9vqeJSWvBK8Jf_-NhD9HD9MRyhndXih3-FHtir1bfl4nUeXLeXiISY
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=Learning+deep+neural+networks+for+node+classification&rft.jtitle=Expert+systems+with+applications&rft.au=Li%2C+Bentian&rft.au=Pi%2C+Dechang&rft.date=2019-12-15&rft.pub=Elsevier+Ltd&rft.issn=0957-4174&rft.eissn=1873-6793&rft.volume=137&rft.spage=324&rft.epage=334&rft_id=info:doi/10.1016%2Fj.eswa.2019.07.006&rft.externalDocID=S0957417419304853
thumbnail_l http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/lc.gif&issn=0957-4174&client=summon
thumbnail_m http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/mc.gif&issn=0957-4174&client=summon
thumbnail_s http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/sc.gif&issn=0957-4174&client=summon