Graph convolutional autoencoders with co-learning of graph structure and node attributes

•We propose a novel end-to-end graph autoencoders model for the attributed graph.•The proposed model can reconstruct both the graph structure and node attributes.•The graph encoder is a completely low-pass filter.•The graph decoder is a completely high-pass filter.•Show the effectiveness of the prop...

Celý popis

Uloženo v:
Podrobná bibliografie
Vydáno v:Pattern recognition Ročník 121; s. 108215
Hlavní autoři: Wang, Jie, Liang, Jiye, Yao, Kaixuan, Liang, Jianqing, Wang, Dianhui
Médium: Journal Article
Jazyk:angličtina
Vydáno: Elsevier Ltd 01.01.2022
Témata:
ISSN:0031-3203, 1873-5142
On-line přístup:Získat plný text
Tagy: Přidat tag
Žádné tagy, Buďte první, kdo vytvoří štítek k tomuto záznamu!
Abstract •We propose a novel end-to-end graph autoencoders model for the attributed graph.•The proposed model can reconstruct both the graph structure and node attributes.•The graph encoder is a completely low-pass filter.•The graph decoder is a completely high-pass filter.•Show the effectiveness of the proposed model. Recently, graph representation learning based on autoencoders has received much attention. However, these methods suffer from two limitations. First, most graph autoencoders ignore the reconstruction of either the graph structure or the node attributes, which often leads to a poor latent representation of the graph-structured data. Second, for existing graph autoencoders models, the encoder and decoder are mainly composed of an initial graph convolutional network (GCN) or its variants. These traditional GCN-based graph autoencoders more or less encounter the problem of incomplete filtering, which causes these models to be unstable in practical applications. To address the above issues, this paper proposes the Graph convolutional Autoencoders with co-learning of graph Structure and Node attributes (GASN) based on variational autoencoders. Specifically, the proposed GASN encodes and decodes the node attributes and graph structure comprehensively in the graph-structured data. Furthermore, we design a completely low-pass graph encoder and a high-pass graph decoder. The experimental results on real-world datasets demonstrate that the proposed GASN achieves state-of-the-art performance on node clustering, link prediction, and visualization tasks.
AbstractList •We propose a novel end-to-end graph autoencoders model for the attributed graph.•The proposed model can reconstruct both the graph structure and node attributes.•The graph encoder is a completely low-pass filter.•The graph decoder is a completely high-pass filter.•Show the effectiveness of the proposed model. Recently, graph representation learning based on autoencoders has received much attention. However, these methods suffer from two limitations. First, most graph autoencoders ignore the reconstruction of either the graph structure or the node attributes, which often leads to a poor latent representation of the graph-structured data. Second, for existing graph autoencoders models, the encoder and decoder are mainly composed of an initial graph convolutional network (GCN) or its variants. These traditional GCN-based graph autoencoders more or less encounter the problem of incomplete filtering, which causes these models to be unstable in practical applications. To address the above issues, this paper proposes the Graph convolutional Autoencoders with co-learning of graph Structure and Node attributes (GASN) based on variational autoencoders. Specifically, the proposed GASN encodes and decodes the node attributes and graph structure comprehensively in the graph-structured data. Furthermore, we design a completely low-pass graph encoder and a high-pass graph decoder. The experimental results on real-world datasets demonstrate that the proposed GASN achieves state-of-the-art performance on node clustering, link prediction, and visualization tasks.
ArticleNumber 108215
Author Liang, Jianqing
Wang, Dianhui
Liang, Jiye
Yao, Kaixuan
Wang, Jie
Author_xml – sequence: 1
  givenname: Jie
  surname: Wang
  fullname: Wang, Jie
  email: wangjie_reg@163.com
  organization: Key Laboratory of Computational Intelligence and Chinese Information Processing of Ministry of Education, School of Computer and Information Technology, Shanxi University, Shanxi, Taiyuan 030006, China
– sequence: 2
  givenname: Jiye
  surname: Liang
  fullname: Liang, Jiye
  email: ljy@sxu.edu.cn
  organization: Key Laboratory of Computational Intelligence and Chinese Information Processing of Ministry of Education, School of Computer and Information Technology, Shanxi University, Shanxi, Taiyuan 030006, China
– sequence: 3
  givenname: Kaixuan
  surname: Yao
  fullname: Yao, Kaixuan
  email: yaokx2@gmail.com
  organization: Key Laboratory of Computational Intelligence and Chinese Information Processing of Ministry of Education, School of Computer and Information Technology, Shanxi University, Shanxi, Taiyuan 030006, China
– sequence: 4
  givenname: Jianqing
  surname: Liang
  fullname: Liang, Jianqing
  email: liangjq@sxu.edu.cn
  organization: Key Laboratory of Computational Intelligence and Chinese Information Processing of Ministry of Education, School of Computer and Information Technology, Shanxi University, Shanxi, Taiyuan 030006, China
– sequence: 5
  givenname: Dianhui
  surname: Wang
  fullname: Wang, Dianhui
  email: dh.wang@latrobe.edu.au
  organization: Department of Computer Science and Information Technology, La Trobe University, Melbourne, VIC 3086, Australia
BookMark eNqFkM1KAzEURoNUsK2-gYu8wNT8TDoZF4IUrULBjYK7kLnJ1JQxKUmm4ts7Y1250NWF-93zwT0zNPHBW4QuKVlQQpdXu8VeZwjbBSOMDivJqDhBUyorXghasgmaEsJpwRnhZ2iW0o4QWg3BFL2uo96_YQj-ELo-u-B1h3Wfg_UQjI0Jf7g85kVndfTOb3Fo8fYbSjn2kPtosfYG--Ec65yja_ps0zk6bXWX7MXPnKOX-7vn1UOxeVo_rm43BXCyzAVUvNaaiopB09ZtzUAyJsGUkkhdVWC04FUjWMMqaUsjhSSga8GNqJcCKOdzdH3shRhSirZV4LIeH8lRu05RokZHaqeOjtToSB0dDXD5C95H967j53_YzRGzw2MHZ6NK4AZh1rhoISsT3N8FX0mphlw
CitedBy_id crossref_primary_10_3390_math12050697
crossref_primary_10_1007_s10618_025_01106_6
crossref_primary_10_1109_ACCESS_2024_3399883
crossref_primary_10_1007_s00607_024_01279_w
crossref_primary_10_1155_2022_8081177
crossref_primary_10_1007_s40747_023_01250_w
crossref_primary_10_1109_JIOT_2025_3553250
crossref_primary_10_1016_j_patcog_2022_108872
crossref_primary_10_1007_s10044_024_01366_w
crossref_primary_10_1007_s10462_024_11068_8
crossref_primary_10_1109_TETCI_2024_3369849
crossref_primary_10_1016_j_patcog_2022_108977
crossref_primary_10_1016_j_ins_2024_120792
crossref_primary_10_1016_j_patcog_2023_109537
crossref_primary_10_3390_e25040567
crossref_primary_10_1016_j_patcog_2024_111020
crossref_primary_10_1016_j_patrec_2025_04_032
Cites_doi 10.1016/j.patcog.2017.03.014
10.1109/TKDE.2018.2807452
10.1109/TIP.2018.2877335
10.1145/3158369
10.1016/j.neunet.2020.04.028
10.1016/j.patcog.2017.10.013
10.1109/TIT.1982.1056489
10.1109/MSP.2012.2235192
ContentType Journal Article
Copyright 2021 Elsevier Ltd
Copyright_xml – notice: 2021 Elsevier Ltd
DBID AAYXX
CITATION
DOI 10.1016/j.patcog.2021.108215
DatabaseName CrossRef
DatabaseTitle CrossRef
DatabaseTitleList
DeliveryMethod fulltext_linktorsrc
Discipline Computer Science
EISSN 1873-5142
ExternalDocumentID 10_1016_j_patcog_2021_108215
S0031320321003964
GroupedDBID --K
--M
-D8
-DT
-~X
.DC
.~1
0R~
123
1B1
1RT
1~.
1~5
29O
4.4
457
4G.
53G
5VS
7-5
71M
8P~
9JN
AABNK
AACTN
AAEDT
AAEDW
AAIAV
AAIKJ
AAKOC
AALRI
AAOAW
AAQFI
AAQXK
AAXUO
AAYFN
ABBOA
ABEFU
ABFNM
ABFRF
ABHFT
ABJNI
ABMAC
ABTAH
ABXDB
ABYKQ
ACBEA
ACDAQ
ACGFO
ACGFS
ACNNM
ACRLP
ACZNC
ADBBV
ADEZE
ADJOM
ADMUD
ADMXK
ADTZH
AEBSH
AECPX
AEFWE
AEKER
AENEX
AFKWA
AFTJW
AGHFR
AGUBO
AGYEJ
AHHHB
AHJVU
AHZHX
AIALX
AIEXJ
AIKHN
AITUG
AJBFU
AJOXV
ALMA_UNASSIGNED_HOLDINGS
AMFUW
AMRAJ
AOUOD
ASPBG
AVWKF
AXJTR
AZFZN
BJAXD
BKOJK
BLXMC
CS3
DU5
EBS
EFJIC
EFLBG
EJD
EO8
EO9
EP2
EP3
F0J
F5P
FD6
FDB
FEDTE
FGOYB
FIRID
FNPLU
FYGXN
G-Q
G8K
GBLVA
GBOLZ
HLZ
HVGLF
HZ~
H~9
IHE
J1W
JJJVA
KOM
KZ1
LG9
LMP
LY1
M41
MO0
N9A
O-L
O9-
OAUVE
OZT
P-8
P-9
P2P
PC.
Q38
R2-
RIG
RNS
ROL
RPZ
SBC
SDF
SDG
SDP
SDS
SES
SEW
SPC
SPCBC
SST
SSV
SSZ
T5K
TN5
UNMZH
VOH
WUQ
XJE
XPP
ZMT
ZY4
~G-
9DU
AATTM
AAXKI
AAYWO
AAYXX
ABDPE
ABWVN
ACLOT
ACRPL
ACVFH
ADCNI
ADNMO
AEIPS
AEUPX
AFJKZ
AFPUW
AGQPQ
AIGII
AIIUN
AKBMS
AKRWK
AKYEP
ANKPU
APXCP
CITATION
EFKBS
~HD
ID FETCH-LOGICAL-c306t-c739aa1572cbf9f92c8228cd4808a77cda537b52b278e4d8580ca953d5965c133
ISICitedReferencesCount 25
ISICitedReferencesURI http://www.webofscience.com/api/gateway?GWVersion=2&SrcApp=Summon&SrcAuth=ProQuest&DestLinkType=CitingArticles&DestApp=WOS_CPL&KeyUT=000701175900008&url=https%3A%2F%2Fcvtisr.summon.serialssolutions.com%2F%23%21%2Fsearch%3Fho%3Df%26include.ft.matches%3Dt%26l%3Dnull%26q%3D
ISSN 0031-3203
IngestDate Tue Nov 18 21:53:52 EST 2025
Sat Nov 29 07:28:24 EST 2025
Fri Feb 23 02:43:53 EST 2024
IsPeerReviewed true
IsScholarly true
Keywords Graph representation learning
Graph filter
Graph convolutional autoencoders
Language English
LinkModel OpenURL
MergedId FETCHMERGED-LOGICAL-c306t-c739aa1572cbf9f92c8228cd4808a77cda537b52b278e4d8580ca953d5965c133
ParticipantIDs crossref_citationtrail_10_1016_j_patcog_2021_108215
crossref_primary_10_1016_j_patcog_2021_108215
elsevier_sciencedirect_doi_10_1016_j_patcog_2021_108215
PublicationCentury 2000
PublicationDate January 2022
2022-01-00
PublicationDateYYYYMMDD 2022-01-01
PublicationDate_xml – month: 01
  year: 2022
  text: January 2022
PublicationDecade 2020
PublicationTitle Pattern recognition
PublicationYear 2022
Publisher Elsevier Ltd
Publisher_xml – name: Elsevier Ltd
References Cai, Zheng, Chang (bib0013) 2018; 30
Wu, Zhang, Souza, Fifty, Yu, Weinberger (bib0029) 2019
Zhu, Ghahramani, Lafferty (bib0001) 2003
Zhang, Cui, Zhu (bib0012) 2020
Kingma, Ba (bib0038) 2015
Ng, Jordan, Weiss (bib0010) 2002
Huang, Zhang, Rong, Huang (bib0042) 2018
Li, Muller, Thabet, Ghanem (bib0030) 2019
Grover, Leskovec (bib0020) 2016
Meng, Liang, Bao, Zhang (bib0031) 2019
Salha, Hennequin, Tran, Vazirgiannis (bib0041) 2019
Li, Ma, Wang, Zhuang (bib0004) 2020; 128
Zhu, Zhang, Cui, Zhu (bib0036) 2019
Z. Wu, S. Pan, F. Chen, G. Long, C. Zhang, P.S. Yu, A comprehensive survey on graph neural networks
Qiu, Dong, Ma, Li, Wang, Tang (bib0024) 2017
Zhang, Yao, Sun, Tay (bib0009) 2019; 52
Lin, Liao, Sun, Chen, Zhao (bib0003) 2017; 68
Kipf, Welling (bib0002) 2017
Wang, Chen, Li (bib0008) 2017
Hamilton, Ying, Leskovec (bib0026) 2017
Li, Rong, Cheng, Meng, Huang, Huang (bib0006) 2019
Abadi, Barham, Chen, Chen, Davis, Dean, Devin, Ghemawat, Irving, Isard (bib0037) 2016
Lloyd (bib0039) 1982; 28
Tang, Qu, Wang, Zhang, Yan, Mei (bib0021) 2015
Wang, Cui, Wang, Pei, Zhu, Yang (bib0023) 2017
Park, Lee, Chang, Lee, Choi (bib0017) 2019
Shuman, Narang, Frossard, Ortega, Vandergheynst (bib0034) 2013; 30
Zhan, Nie, Wang, Yang (bib0011) 2018; 28
T.N. Kipf, M. Welling, Variational graph auto-encoders
Gu, Wang, Kuen, Ma, Shahroudy, Shuai, Liu, Wang, Wang, Cai (bib0032) 2018; 77
Ying, He, Chen, Eksombatchai, Hamilton, Leskovec (bib0043) 2018
Hamilton, Ying, Leskovec (bib0014) 2017; 40
Velickovic, Cucurull, Casanova, Romero, Lio, Bengio (bib0027) 2018
Perozzi, Al-Rfou, Skiena (bib0019) 2014
Li, Wu, Liu, Zhang, Guan (bib0018) 2019
Ou, Cui, Pei, Zhang, Zhu (bib0022) 2016
Wang, Li, Ma, Montufar, Zhuang, Fan (bib0007) 2020
(2019).
Chen, Ma, Xiao (bib0028) 2018
(2016).
Van der, Hinton (bib0040) 2008; 9
Pan, Hu, Long, Jiang, Yao, Zhang (bib0016) 2018
Kudo, Maeda, Matsumoto (bib0005) 2005
Grover, Zweig, Ermon (bib0033) 2019
Kingma, Welling (bib0035) 2014
Hamilton (10.1016/j.patcog.2021.108215_bib0014) 2017; 40
10.1016/j.patcog.2021.108215_bib0025
Qiu (10.1016/j.patcog.2021.108215_bib0024) 2017
Cai (10.1016/j.patcog.2021.108215_bib0013) 2018; 30
Li (10.1016/j.patcog.2021.108215_bib0004) 2020; 128
Park (10.1016/j.patcog.2021.108215_bib0017) 2019
Wang (10.1016/j.patcog.2021.108215_bib0023) 2017
Li (10.1016/j.patcog.2021.108215_bib0018) 2019
Tang (10.1016/j.patcog.2021.108215_bib0021) 2015
Van der (10.1016/j.patcog.2021.108215_bib0040) 2008; 9
Abadi (10.1016/j.patcog.2021.108215_bib0037) 2016
Wang (10.1016/j.patcog.2021.108215_bib0007) 2020
Zhan (10.1016/j.patcog.2021.108215_bib0011) 2018; 28
Kingma (10.1016/j.patcog.2021.108215_bib0038) 2015
Shuman (10.1016/j.patcog.2021.108215_bib0034) 2013; 30
Zhang (10.1016/j.patcog.2021.108215_bib0012) 2020
Pan (10.1016/j.patcog.2021.108215_bib0016) 2018
Kingma (10.1016/j.patcog.2021.108215_bib0035) 2014
Wu (10.1016/j.patcog.2021.108215_bib0029) 2019
Li (10.1016/j.patcog.2021.108215_bib0006) 2019
Ying (10.1016/j.patcog.2021.108215_bib0043) 2018
Perozzi (10.1016/j.patcog.2021.108215_bib0019) 2014
Meng (10.1016/j.patcog.2021.108215_bib0031) 2019
Kipf (10.1016/j.patcog.2021.108215_bib0002) 2017
Zhang (10.1016/j.patcog.2021.108215_bib0009) 2019; 52
Grover (10.1016/j.patcog.2021.108215_bib0020) 2016
Lloyd (10.1016/j.patcog.2021.108215_bib0039) 1982; 28
Chen (10.1016/j.patcog.2021.108215_bib0028) 2018
Huang (10.1016/j.patcog.2021.108215_bib0042) 2018
Ng (10.1016/j.patcog.2021.108215_bib0010) 2002
Ou (10.1016/j.patcog.2021.108215_bib0022) 2016
10.1016/j.patcog.2021.108215_bib0015
Zhu (10.1016/j.patcog.2021.108215_bib0001) 2003
Salha (10.1016/j.patcog.2021.108215_bib0041) 2019
Lin (10.1016/j.patcog.2021.108215_bib0003) 2017; 68
Wang (10.1016/j.patcog.2021.108215_bib0008) 2017
Hamilton (10.1016/j.patcog.2021.108215_bib0026) 2017
Li (10.1016/j.patcog.2021.108215_bib0030) 2019
Kudo (10.1016/j.patcog.2021.108215_bib0005) 2005
Zhu (10.1016/j.patcog.2021.108215_bib0036) 2019
Gu (10.1016/j.patcog.2021.108215_bib0032) 2018; 77
Grover (10.1016/j.patcog.2021.108215_bib0033) 2019
Velickovic (10.1016/j.patcog.2021.108215_bib0027) 2018
References_xml – volume: 9
  start-page: 2579
  year: 2008
  end-page: 2605
  ident: bib0040
  article-title: Visualizing data using t-SNE
  publication-title: J. Mach. Learn. Res.
– start-page: 6519
  year: 2019
  end-page: 6528
  ident: bib0017
  article-title: Symmetric graph convolutional autoencoder for unsupervised graph representation learning
  publication-title: Proceedings of the International Conference on Computer Vision
– start-page: 972
  year: 2019
  end-page: 982
  ident: bib0006
  article-title: Semi-supervised graph classification: a hierarchical graph perspective
  publication-title: Proceedings of the International Conference on World Wide Web
– start-page: 3353
  year: 2019
  end-page: 3359
  ident: bib0041
  article-title: A degeneracy framework for scalable graph autoencoders
  publication-title: Proceedings of the International Joint Association for the Advancement of Artificial Intelligence
– year: 2014
  ident: bib0035
  article-title: Auto-encoding variational bayes
  publication-title: International Conference on Learning Representations
– start-page: 974
  year: 2018
  end-page: 983
  ident: bib0043
  article-title: Graph convolutional neural networks for web-scale recommender systems
  publication-title: Proceedings of the International Conference on Knowledge Discovery and Data Mining
– volume: 28
  start-page: 1261
  year: 2018
  end-page: 1270
  ident: bib0011
  article-title: Multiview consensus graph clustering
  publication-title: IEEE Trans. Image Process.
– start-page: 1399
  year: 2019
  end-page: 1407
  ident: bib0036
  article-title: Robust graph convolutional networks against adversarial attacks
  publication-title: Proceedings of the International Conference on Knowledge Discovery and Data Mining
– start-page: 969
  year: 2017
  end-page: 972
  ident: bib0008
  article-title: Predictive network representation learning for link prediction
  publication-title: Proceedings of the International Conference on Research and Development in Information Retrieval
– year: 2020
  ident: bib0007
  article-title: Haar graph pooling
  publication-title: International Conference on Machine Learning
– reference: (2019).
– start-page: 4558
  year: 2018
  end-page: 4567
  ident: bib0042
  article-title: Adaptive sampling towards fast graph representation learning
  publication-title: Proceedings of the Advances in Neural Information Processing Systems
– volume: 40
  start-page: 52
  year: 2017
  end-page: 74
  ident: bib0014
  article-title: Representation learning on graphs: methods and applications
  publication-title: IEEE Database Eng. Bull.
– reference: Z. Wu, S. Pan, F. Chen, G. Long, C. Zhang, P.S. Yu, A comprehensive survey on graph neural networks,
– start-page: 1
  year: 2020
  end-page: 21
  ident: bib0012
  article-title: Deep learning on graphs: a survey
  publication-title: IEEE Trans. Knowl. Data Eng.
– start-page: 849
  year: 2002
  end-page: 856
  ident: bib0010
  article-title: On spectral clustering: analysis and an algorithm
  publication-title: Proceedings of the Advances in Neural Information Processing Systems
– volume: 30
  start-page: 83
  year: 2013
  end-page: 98
  ident: bib0034
  article-title: The emerging field of signal processing on graphs: extending high-dimensional data analysis to networks and other irregular domains
  publication-title: IEEE Signal Process. Mag.
– start-page: 701
  year: 2014
  end-page: 710
  ident: bib0019
  article-title: DeepWalk: online learning of social representations
  publication-title: Proceedings of the International Conference on Knowledge Discovery and Data Mining
– volume: 77
  start-page: 354
  year: 2018
  end-page: 377
  ident: bib0032
  article-title: Recent advances in convolutional neural networks
  publication-title: Pattern Recognit.
– reference: (2016).
– start-page: 1024
  year: 2017
  end-page: 1034
  ident: bib0026
  article-title: Inductive representation learning on large graphs
  publication-title: Proceedings of the Advances in Neural Information Processing Systems
– start-page: 9582
  year: 2019
  end-page: 9591
  ident: bib0018
  article-title: Label efficient semi-supervised learning via graph filtering
  publication-title: Proceedings of the Conference on Computer Vision and Pattern Recognition
– start-page: 393
  year: 2019
  end-page: 401
  ident: bib0031
  article-title: Co-embedding attributed networks
  publication-title: Proceedings of the International Conference on Web Search and Data Mining
– volume: 30
  start-page: 1616
  year: 2018
  end-page: 1637
  ident: bib0013
  article-title: A comprehensive survey of graph embedding: problems, techniques, and applications
  publication-title: IEEE Trans. Knowl. Data Eng.
– volume: 68
  start-page: 14
  year: 2017
  end-page: 23
  ident: bib0003
  article-title: Dynamic graph fusion label propagation for semi-supervised multi-modality classification
  publication-title: Pattern Recognit.
– start-page: 2609
  year: 2018
  end-page: 2615
  ident: bib0016
  article-title: Adversarially regularized graph autoencoder for graph embedding
  publication-title: Proceedings of the International Joint Conference on Artificial Intelligence
– start-page: 459
  year: 2017
  end-page: 467
  ident: bib0024
  article-title: Network embedding as matrix factorization: unifying deepwalk, LINE, PTE, and node2vec
  publication-title: Proceedings of the International Conference on Web Search and Data Mining
– year: 2018
  ident: bib0028
  article-title: FastGCN: fast learning with graph convolutional networks via importance sampling
  publication-title: International Conference on Learning Representations
– volume: 28
  start-page: 129
  year: 1982
  end-page: 137
  ident: bib0039
  article-title: Least squares quantization in PCM
  publication-title: IEEE Trans. Inf. Theory
– start-page: 1105
  year: 2016
  end-page: 1114
  ident: bib0022
  article-title: Asymmetric transitivity preserving graph embedding
  publication-title: Proceedings of the International Conference on Knowledge Discovery and Data Mining
– start-page: 2434
  year: 2019
  end-page: 2444
  ident: bib0033
  article-title: Graphite: iterative generative modeling of graphs
  publication-title: Proceedings of the International Conference on Machine Learning
– start-page: 912
  year: 2003
  end-page: 919
  ident: bib0001
  article-title: Semi-supervised learning using gaussian fields and harmonic functions
  publication-title: Proceedings of the International Conference on Machine Learning
– start-page: 203
  year: 2017
  end-page: 209
  ident: bib0023
  article-title: Community preserving network embedding
  publication-title: Proceedings of the Association for the Advancement of Artificial Intelligence
– year: 2017
  ident: bib0002
  article-title: Semi-supervised classification with graph convolutional networks
  publication-title: International Conference on Learning Representations
– year: 2015
  ident: bib0038
  article-title: Adam: a method for stochastic optimization
  publication-title: International Conference on Learning Representations
– start-page: 855
  year: 2016
  end-page: 864
  ident: bib0020
  article-title: Node2vec: scalable feature learning for networks
  publication-title: Proceedings of the International Conference on Knowledge Discovery and Data Mining
– volume: 128
  start-page: 188
  year: 2020
  end-page: 198
  ident: bib0004
  article-title: Fast Haar transforms for graph neural networks
  publication-title: Neural Netw.
– reference: T.N. Kipf, M. Welling, Variational graph auto-encoders,
– start-page: 6861
  year: 2019
  end-page: 6871
  ident: bib0029
  article-title: Simplifying graph convolutional networks
  publication-title: Proceedings of the International Conference on Machine Learning
– start-page: 9267
  year: 2019
  end-page: 9276
  ident: bib0030
  article-title: DeepGCNs: can GCNs go as deep as CNNs?
  publication-title: Proceedings of the International Conference on Computer Vision
– start-page: 729
  year: 2005
  end-page: 736
  ident: bib0005
  article-title: An application of boosting to graph classification
  publication-title: Proceedings of the Advances in Neural Information Processing Systems
– start-page: 1067
  year: 2015
  end-page: 1077
  ident: bib0021
  article-title: Line: large-scale information network embedding
  publication-title: Proceedings of the International Conference on World Wide Web
– start-page: 265
  year: 2016
  end-page: 283
  ident: bib0037
  article-title: TensorFlow: a system for large-scale machine learning
  publication-title: Proceedings of the Symposium on Operating Systems Design and Implementation
– year: 2018
  ident: bib0027
  article-title: Graph attention networks
  publication-title: International Conference on Learning Representations
– volume: 52
  start-page: 1
  year: 2019
  end-page: 38
  ident: bib0009
  article-title: Deep learning based recommender system: a survey and new perspectives
  publication-title: ACM Comput. Surv.
– start-page: 849
  year: 2002
  ident: 10.1016/j.patcog.2021.108215_bib0010
  article-title: On spectral clustering: analysis and an algorithm
– volume: 40
  start-page: 52
  issue: 3
  year: 2017
  ident: 10.1016/j.patcog.2021.108215_bib0014
  article-title: Representation learning on graphs: methods and applications
  publication-title: IEEE Database Eng. Bull.
– volume: 68
  start-page: 14
  year: 2017
  ident: 10.1016/j.patcog.2021.108215_bib0003
  article-title: Dynamic graph fusion label propagation for semi-supervised multi-modality classification
  publication-title: Pattern Recognit.
  doi: 10.1016/j.patcog.2017.03.014
– start-page: 1067
  year: 2015
  ident: 10.1016/j.patcog.2021.108215_bib0021
  article-title: Line: large-scale information network embedding
– start-page: 6861
  year: 2019
  ident: 10.1016/j.patcog.2021.108215_bib0029
  article-title: Simplifying graph convolutional networks
– volume: 30
  start-page: 1616
  issue: 9
  year: 2018
  ident: 10.1016/j.patcog.2021.108215_bib0013
  article-title: A comprehensive survey of graph embedding: problems, techniques, and applications
  publication-title: IEEE Trans. Knowl. Data Eng.
  doi: 10.1109/TKDE.2018.2807452
– start-page: 1399
  year: 2019
  ident: 10.1016/j.patcog.2021.108215_bib0036
  article-title: Robust graph convolutional networks against adversarial attacks
– volume: 28
  start-page: 1261
  issue: 3
  year: 2018
  ident: 10.1016/j.patcog.2021.108215_bib0011
  article-title: Multiview consensus graph clustering
  publication-title: IEEE Trans. Image Process.
  doi: 10.1109/TIP.2018.2877335
– start-page: 459
  year: 2017
  ident: 10.1016/j.patcog.2021.108215_bib0024
  article-title: Network embedding as matrix factorization: unifying deepwalk, LINE, PTE, and node2vec
– start-page: 2609
  year: 2018
  ident: 10.1016/j.patcog.2021.108215_bib0016
  article-title: Adversarially regularized graph autoencoder for graph embedding
– start-page: 3353
  year: 2019
  ident: 10.1016/j.patcog.2021.108215_bib0041
  article-title: A degeneracy framework for scalable graph autoencoders
– start-page: 912
  year: 2003
  ident: 10.1016/j.patcog.2021.108215_bib0001
  article-title: Semi-supervised learning using gaussian fields and harmonic functions
– start-page: 2434
  year: 2019
  ident: 10.1016/j.patcog.2021.108215_bib0033
  article-title: Graphite: iterative generative modeling of graphs
– volume: 52
  start-page: 1
  issue: 1
  year: 2019
  ident: 10.1016/j.patcog.2021.108215_bib0009
  article-title: Deep learning based recommender system: a survey and new perspectives
  publication-title: ACM Comput. Surv.
  doi: 10.1145/3158369
– start-page: 855
  year: 2016
  ident: 10.1016/j.patcog.2021.108215_bib0020
  article-title: Node2vec: scalable feature learning for networks
– year: 2020
  ident: 10.1016/j.patcog.2021.108215_bib0007
  article-title: Haar graph pooling
– start-page: 1105
  year: 2016
  ident: 10.1016/j.patcog.2021.108215_bib0022
  article-title: Asymmetric transitivity preserving graph embedding
– year: 2018
  ident: 10.1016/j.patcog.2021.108215_bib0027
  article-title: Graph attention networks
– volume: 128
  start-page: 188
  year: 2020
  ident: 10.1016/j.patcog.2021.108215_bib0004
  article-title: Fast Haar transforms for graph neural networks
  publication-title: Neural Netw.
  doi: 10.1016/j.neunet.2020.04.028
– start-page: 974
  year: 2018
  ident: 10.1016/j.patcog.2021.108215_bib0043
  article-title: Graph convolutional neural networks for web-scale recommender systems
– start-page: 9582
  year: 2019
  ident: 10.1016/j.patcog.2021.108215_bib0018
  article-title: Label efficient semi-supervised learning via graph filtering
– start-page: 701
  year: 2014
  ident: 10.1016/j.patcog.2021.108215_bib0019
  article-title: DeepWalk: online learning of social representations
– volume: 77
  start-page: 354
  year: 2018
  ident: 10.1016/j.patcog.2021.108215_bib0032
  article-title: Recent advances in convolutional neural networks
  publication-title: Pattern Recognit.
  doi: 10.1016/j.patcog.2017.10.013
– start-page: 4558
  year: 2018
  ident: 10.1016/j.patcog.2021.108215_bib0042
  article-title: Adaptive sampling towards fast graph representation learning
– start-page: 393
  year: 2019
  ident: 10.1016/j.patcog.2021.108215_bib0031
  article-title: Co-embedding attributed networks
– start-page: 969
  year: 2017
  ident: 10.1016/j.patcog.2021.108215_bib0008
  article-title: Predictive network representation learning for link prediction
– start-page: 1
  year: 2020
  ident: 10.1016/j.patcog.2021.108215_bib0012
  article-title: Deep learning on graphs: a survey
  publication-title: IEEE Trans. Knowl. Data Eng.
– start-page: 6519
  year: 2019
  ident: 10.1016/j.patcog.2021.108215_bib0017
  article-title: Symmetric graph convolutional autoencoder for unsupervised graph representation learning
– ident: 10.1016/j.patcog.2021.108215_bib0025
– year: 2017
  ident: 10.1016/j.patcog.2021.108215_bib0002
  article-title: Semi-supervised classification with graph convolutional networks
– year: 2014
  ident: 10.1016/j.patcog.2021.108215_bib0035
  article-title: Auto-encoding variational bayes
– start-page: 972
  year: 2019
  ident: 10.1016/j.patcog.2021.108215_bib0006
  article-title: Semi-supervised graph classification: a hierarchical graph perspective
– year: 2018
  ident: 10.1016/j.patcog.2021.108215_bib0028
  article-title: FastGCN: fast learning with graph convolutional networks via importance sampling
– start-page: 203
  year: 2017
  ident: 10.1016/j.patcog.2021.108215_bib0023
  article-title: Community preserving network embedding
– volume: 28
  start-page: 129
  issue: 2
  year: 1982
  ident: 10.1016/j.patcog.2021.108215_bib0039
  article-title: Least squares quantization in PCM
  publication-title: IEEE Trans. Inf. Theory
  doi: 10.1109/TIT.1982.1056489
– start-page: 265
  year: 2016
  ident: 10.1016/j.patcog.2021.108215_bib0037
  article-title: TensorFlow: a system for large-scale machine learning
– volume: 30
  start-page: 83
  issue: 3
  year: 2013
  ident: 10.1016/j.patcog.2021.108215_bib0034
  article-title: The emerging field of signal processing on graphs: extending high-dimensional data analysis to networks and other irregular domains
  publication-title: IEEE Signal Process. Mag.
  doi: 10.1109/MSP.2012.2235192
– start-page: 729
  year: 2005
  ident: 10.1016/j.patcog.2021.108215_bib0005
  article-title: An application of boosting to graph classification
– ident: 10.1016/j.patcog.2021.108215_bib0015
– start-page: 1024
  year: 2017
  ident: 10.1016/j.patcog.2021.108215_bib0026
  article-title: Inductive representation learning on large graphs
– start-page: 9267
  year: 2019
  ident: 10.1016/j.patcog.2021.108215_bib0030
  article-title: DeepGCNs: can GCNs go as deep as CNNs?
– year: 2015
  ident: 10.1016/j.patcog.2021.108215_bib0038
  article-title: Adam: a method for stochastic optimization
– volume: 9
  start-page: 2579
  issue: 2605
  year: 2008
  ident: 10.1016/j.patcog.2021.108215_bib0040
  article-title: Visualizing data using t-SNE
  publication-title: J. Mach. Learn. Res.
SSID ssj0017142
Score 2.5230134
Snippet •We propose a novel end-to-end graph autoencoders model for the attributed graph.•The proposed model can reconstruct both the graph structure and node...
SourceID crossref
elsevier
SourceType Enrichment Source
Index Database
Publisher
StartPage 108215
SubjectTerms Graph convolutional autoencoders
Graph filter
Graph representation learning
Title Graph convolutional autoencoders with co-learning of graph structure and node attributes
URI https://dx.doi.org/10.1016/j.patcog.2021.108215
Volume 121
WOSCitedRecordID wos000701175900008&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: ScienceDirect database
  customDbUrl:
  eissn: 1873-5142
  dateEnd: 99991231
  omitProxy: false
  ssIdentifier: ssj0017142
  issn: 0031-3203
  databaseCode: AIEXJ
  dateStart: 19950101
  isFulltext: true
  titleUrlDefault: https://www.sciencedirect.com
  providerName: Elsevier
link http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwtV1Lb9QwELag5cCF8lRLAfnArTJK_Fjbx6oqj6qqKlFgOUV-JGirKlnoFi3_vuPYTrYt4iVxiSLLTiLPp8nY_uYbhF6yxklbQ-SmSmFI0Csh1nBFrLYN89x43mfIfTyUR0dqOtXHiTZ23pcTkG2rlks9_6-mhjYwdkid_QtzDw-FBrgHo8MVzA7XPzL8myBB3bPJ02uCGsDFoguKlYG1nNnm5CzvikC82OtW70Qx2Xyk0EL3HbOIJbES1TCFsce9KmfIhEn0o_Ew_1PagD6YDZA5nA1tP4bGz6aLbI7Z8mKFFzR2Ne3X_FtNuxKUXtuVGNJlRm5S735ZSRgtokero8dVkhGI2q665Jg1fcO9x52G01dz-E11X2B1T8tAkqQxI_SacPb7qEtZhCylgukJv43WqRQafN_67rv96cFw2iRLHlXl0-flFMueB3jzXT8PYVbCkpP76F5aT-DdiIMH6FbdPkQbuVYHTq77EZr2sMBXYIFXYYEDLPAKLHDX4B4WeIAFBljgAAs8wuIx-vB6_2TvLUlVNYiD5eGCOMm0MaWQ1NlGN5o6iBFDCStVKCOl80YwaQW1VKqaeyVU4YwWzAs9Ea5k7Alaa7u23kQYwn1jnbJ-ogVnXuqacyuF80F0jnqxhVieqMolyflQ-eSsytzC0ypObxWmt4rTu4XIMGoeJVd-019mG1QpbIzhYAWw-eXIp_88chvdHVH_DK2BHern6I77vpidf3uR8HUJ2OeVuQ
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=Graph+convolutional+autoencoders+with+co-learning+of+graph+structure+and+node+attributes&rft.jtitle=Pattern+recognition&rft.au=Wang%2C+Jie&rft.au=Liang%2C+Jiye&rft.au=Yao%2C+Kaixuan&rft.au=Liang%2C+Jianqing&rft.date=2022-01-01&rft.pub=Elsevier+Ltd&rft.issn=0031-3203&rft.eissn=1873-5142&rft.volume=121&rft_id=info:doi/10.1016%2Fj.patcog.2021.108215&rft.externalDocID=S0031320321003964
thumbnail_l http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/lc.gif&issn=0031-3203&client=summon
thumbnail_m http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/mc.gif&issn=0031-3203&client=summon
thumbnail_s http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/sc.gif&issn=0031-3203&client=summon