Research on cross‐hierarchical graph network recommendation algorithm based on random walk and convolutional neural network

Convolutional network (CNN) has been widely used in processing various graphics and network data analysis tasks. Therefore, facing the recommendation problem of large‐scale heterogeneous interaction, some studies have raised the problem of whether graph convolution neural network (GCN) can optimize...

Ausführliche Beschreibung

Gespeichert in:
Bibliographische Detailangaben
Veröffentlicht in:Concurrency and computation
Hauptverfasser: Huang, Meng, Sun, Guohui
Format: Journal Article
Sprache:Englisch
Veröffentlicht: 08.11.2021
ISSN:1532-0626, 1532-0634
Online-Zugang:Volltext
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
Abstract Convolutional network (CNN) has been widely used in processing various graphics and network data analysis tasks. Therefore, facing the recommendation problem of large‐scale heterogeneous interaction, some studies have raised the problem of whether graph convolution neural network (GCN) can optimize the integration of node features and topology in complex graphs with rich information, but GCN may not be able to adaptively learn some deep related information between topology and node features, Therefore, the ability of GCN in some classification tasks may be seriously hindered. Therefore, this article proposes a heterogeneous network recommendation algorithm based on random walk and convolutional neural network (RW‐CNN), which can not only obtain the deep information of network structure but also aggregate the node representation. The core idea is to use the rule items based on meta‐path similarity to constrain the implicit representation of users and goods and make full use of the rich structural and semantic information of heterogeneous information networks. Then, combined with convolution neural network, the cross‐correlation information between project and user nodes is processed, so as to fully mine the semantic features of nodes. Finally, through the attention mechanism and fully connected network, the global user feature vector and project feature vector of path fusion at different levels are obtained. Finally, the two characteristic matrices are multiplied to obtain the prediction score.
AbstractList Convolutional network (CNN) has been widely used in processing various graphics and network data analysis tasks. Therefore, facing the recommendation problem of large‐scale heterogeneous interaction, some studies have raised the problem of whether graph convolution neural network (GCN) can optimize the integration of node features and topology in complex graphs with rich information, but GCN may not be able to adaptively learn some deep related information between topology and node features, Therefore, the ability of GCN in some classification tasks may be seriously hindered. Therefore, this article proposes a heterogeneous network recommendation algorithm based on random walk and convolutional neural network (RW‐CNN), which can not only obtain the deep information of network structure but also aggregate the node representation. The core idea is to use the rule items based on meta‐path similarity to constrain the implicit representation of users and goods and make full use of the rich structural and semantic information of heterogeneous information networks. Then, combined with convolution neural network, the cross‐correlation information between project and user nodes is processed, so as to fully mine the semantic features of nodes. Finally, through the attention mechanism and fully connected network, the global user feature vector and project feature vector of path fusion at different levels are obtained. Finally, the two characteristic matrices are multiplied to obtain the prediction score.
Author Sun, Guohui
Huang, Meng
Author_xml – sequence: 1
  givenname: Meng
  orcidid: 0000-0002-2830-022X
  surname: Huang
  fullname: Huang, Meng
  organization: College of Software Jilin University Changchun China
– sequence: 2
  givenname: Guohui
  surname: Sun
  fullname: Sun, Guohui
  organization: Hangzhou Xinhe Shengshi Technology Co., Ltd Hangzhou China
BookMark eNplkM1Kw0AUhQdRsK2CjzBLN6nzl7-lFP-gIIiuw-3MTTM2mSmT1OJC8BF8Rp_EJIoLXd3D5ZwPzpmSQ-cdEnLG2ZwzJi70FudJytQBmfBYioglUh3-apEck2nbPjPGOZN8Qt4esEUIuqLeUR18236-f1QWw_CzGmq6DrCtqMNu78OGBtS-adAZ6GyfgHrtg-2qhq6gRTNAAjjjG7qHekN7SbV3L77eDfae5nAXxjPiTshRCXWLpz93Rp6urx4Xt9Hy_uZucbmMtBBpF6HRMcY87ruwzORxWQKmCkRm0lzGiZKQaoR8xTk3muUcM8OUZEasRKaUKeWMnH9zx4YBy2IbbAPhteCsGGYr-tmKYbbeOv9j1bYby3YBbP0_8AWM53ZG
CitedBy_id crossref_primary_10_1109_ACCESS_2023_3323353
Cites_doi 10.1109/TBIOM.2021.3104014
10.1016/j.displa.2021.102053
10.1109/TKDE.2018.2833443
10.1145/3097983.3098063
10.1145/2556195.2556259
10.1145/2959100.2959165
10.1109/ICDM.2010.127
10.1145/3097983.3098096
10.1109/ICWS49710.2020.00073
10.1145/2939672.2939754
10.1145/3219819.3219890
10.1145/2623330.2623732
10.1016/j.knosys.2021.107456
10.1145/2481244.2481248
10.1109/ACCESS.2019.2925778
10.1109/ACCESS.2019.2950698
10.24963/ijcai.2017/435
10.1109/TCSVT.2020.3043026
10.1145/3132847.3132963
10.1016/j.displa.2021.102022
10.24963/ijcai.2018/471
10.1145/3109859.3109890
10.1145/3097983.3098036
10.1002/cpe.6177
10.3390/s19122749
10.1587/transinf.2019EDL8103
10.1109/TCYB.2020.2999492
10.1109/LSP.2020.3032277
10.1145/2339530.2339729
10.1145/3178876.3186070
10.1145/3132847.3132953
10.1016/j.neucom.2020.05.106
10.1587/transinf.2018EDL8239
10.1145/2736277.2741093
10.1109/MC.2009.263
ContentType Journal Article
DBID AAYXX
CITATION
DOI 10.1002/cpe.6704
DatabaseName CrossRef
DatabaseTitle CrossRef
DatabaseTitleList CrossRef
DeliveryMethod fulltext_linktorsrc
Discipline Computer Science
EISSN 1532-0634
ExternalDocumentID 10_1002_cpe_6704
GroupedDBID .3N
.DC
.GA
05W
0R~
10A
1L6
1OC
33P
3SF
3WU
4.4
50Y
50Z
51W
51X
52M
52N
52O
52P
52S
52T
52U
52W
52X
5GY
5VS
66C
702
7PT
8-0
8-1
8-3
8-4
8-5
8UM
930
A03
AAESR
AAEVG
AAHQN
AAMNL
AANLZ
AAONW
AAXRX
AAYCA
AAYXX
AAZKR
ABCQN
ABCUV
ABEML
ABIJN
ACAHQ
ACCZN
ACPOU
ACSCC
ACXBN
ACXQS
ADBBV
ADEOM
ADIZJ
ADKYN
ADMGS
ADMLS
ADOZA
ADXAS
ADZMN
AEIGN
AEIMD
AEUYR
AEYWJ
AFBPY
AFFPM
AFGKR
AFWVQ
AGHNM
AGYGG
AHBTC
AITYG
AIURR
AJXKR
ALMA_UNASSIGNED_HOLDINGS
ALVPJ
AMBMR
AMYDB
ATUGU
AUFTA
AZBYB
BAFTC
BDRZF
BFHJK
BHBCM
BMNLL
BROTX
BRXPI
BY8
CITATION
CS3
D-E
D-F
DCZOG
DPXWK
DR2
DRFUL
DRSTM
EBS
F00
F01
F04
F5P
G-S
G.N
GNP
GODZA
HGLYW
HHY
HZ~
IX1
JPC
KQQ
LATKE
LAW
LC2
LC3
LEEKS
LH4
LITHE
LOXES
LP6
LP7
LUTES
LYRES
MEWTI
MK4
MRFUL
MRSTM
MSFUL
MSSTM
MXFUL
MXSTM
N04
N05
N9A
O66
O8X
O9-
OIG
P2W
P2X
P4D
PQQKQ
Q.N
Q11
QB0
QRW
R.K
ROL
RX1
SUPJJ
TN5
UB1
V2E
W8V
W99
WBKPD
WIH
WIK
WOHZO
WQJ
WXSBR
WYISQ
WZISG
XG1
XV2
~IA
~WT
ID FETCH-LOGICAL-c227t-edc5e51506308d95ffae74a28d7935643a7cea9b111dc091e8d0430d2b2844df3
ISICitedReferencesCount 1
ISICitedReferencesURI http://www.webofscience.com/api/gateway?GWVersion=2&SrcApp=Summon&SrcAuth=ProQuest&DestLinkType=CitingArticles&DestApp=WOS_CPL&KeyUT=000715585000001&url=https%3A%2F%2Fcvtisr.summon.serialssolutions.com%2F%23%21%2Fsearch%3Fho%3Df%26include.ft.matches%3Dt%26l%3Dnull%26q%3D
ISSN 1532-0626
IngestDate Tue Nov 18 21:47:06 EST 2025
Sat Nov 29 01:41:27 EST 2025
IsPeerReviewed true
IsScholarly true
Language English
LinkModel OpenURL
MergedId FETCHMERGED-LOGICAL-c227t-edc5e51506308d95ffae74a28d7935643a7cea9b111dc091e8d0430d2b2844df3
ORCID 0000-0002-2830-022X
ParticipantIDs crossref_primary_10_1002_cpe_6704
crossref_citationtrail_10_1002_cpe_6704
PublicationCentury 2000
PublicationDate 2021-11-08
PublicationDateYYYYMMDD 2021-11-08
PublicationDate_xml – month: 11
  year: 2021
  text: 2021-11-08
  day: 08
PublicationDecade 2020
PublicationTitle Concurrency and computation
PublicationYear 2021
References e_1_2_7_5_1
e_1_2_7_3_1
e_1_2_7_7_1
e_1_2_7_19_1
e_1_2_7_15_1
e_1_2_7_13_1
e_1_2_7_11_1
e_1_2_7_47_1
e_1_2_7_26_1
e_1_2_7_49_1
e_1_2_7_28_1
Ning X (e_1_2_7_4_1) 2020; 6147
Yan C (e_1_2_7_43_1) 2021
e_1_2_7_50_1
e_1_2_7_25_1
e_1_2_7_31_1
e_1_2_7_52_1
e_1_2_7_23_1
e_1_2_7_33_1
e_1_2_7_54_1
e_1_2_7_21_1
e_1_2_7_35_1
e_1_2_7_37_1
e_1_2_7_39_1
e_1_2_7_6_1
e_1_2_7_8_1
Cai W (e_1_2_7_45_1) 2021; 69
e_1_2_7_18_1
e_1_2_7_16_1
e_1_2_7_40_1
e_1_2_7_2_1
e_1_2_7_14_1
e_1_2_7_42_1
e_1_2_7_12_1
e_1_2_7_44_1
e_1_2_7_10_1
e_1_2_7_46_1
e_1_2_7_48_1
e_1_2_7_27_1
e_1_2_7_29_1
Yizhou S (e_1_2_7_17_1) 2011; 11
e_1_2_7_51_1
e_1_2_7_30_1
e_1_2_7_53_1
e_1_2_7_24_1
e_1_2_7_32_1
Wang G (e_1_2_7_9_1) 2021
e_1_2_7_22_1
e_1_2_7_34_1
e_1_2_7_20_1
e_1_2_7_36_1
e_1_2_7_38_1
Zhang Y (e_1_2_7_41_1) 2020
References_xml – ident: e_1_2_7_39_1
  doi: 10.1109/TBIOM.2021.3104014
– ident: e_1_2_7_44_1
  doi: 10.1016/j.displa.2021.102053
– ident: e_1_2_7_20_1
– ident: e_1_2_7_51_1
– start-page: 1
  year: 2021
  ident: e_1_2_7_43_1
  article-title: Beyond triplet loss: person re‐identification with fine‐grained difference‐aware pairwise loss
  publication-title: IEEE Trans Multimedia
– ident: e_1_2_7_35_1
  doi: 10.1109/TKDE.2018.2833443
– ident: e_1_2_7_54_1
  doi: 10.1145/3097983.3098063
– ident: e_1_2_7_48_1
– ident: e_1_2_7_53_1
  doi: 10.1145/2556195.2556259
– ident: e_1_2_7_47_1
  doi: 10.1145/2959100.2959165
– ident: e_1_2_7_52_1
  doi: 10.1109/ICDM.2010.127
– ident: e_1_2_7_28_1
  doi: 10.1145/3097983.3098096
– ident: e_1_2_7_29_1
  doi: 10.1109/ICWS49710.2020.00073
– ident: e_1_2_7_32_1
  doi: 10.1145/2939672.2939754
– ident: e_1_2_7_49_1
  doi: 10.1145/3219819.3219890
– ident: e_1_2_7_16_1
– ident: e_1_2_7_13_1
– ident: e_1_2_7_24_1
– ident: e_1_2_7_19_1
– ident: e_1_2_7_30_1
  doi: 10.1145/2623330.2623732
– ident: e_1_2_7_7_1
  doi: 10.1016/j.knosys.2021.107456
– ident: e_1_2_7_11_1
  doi: 10.1145/2481244.2481248
– ident: e_1_2_7_34_1
  doi: 10.1109/ACCESS.2019.2925778
– ident: e_1_2_7_40_1
  doi: 10.1109/ACCESS.2019.2950698
– ident: e_1_2_7_26_1
  doi: 10.24963/ijcai.2017/435
– ident: e_1_2_7_42_1
  doi: 10.1109/TCSVT.2020.3043026
– ident: e_1_2_7_23_1
  doi: 10.1145/3132847.3132963
– ident: e_1_2_7_5_1
  doi: 10.1016/j.displa.2021.102022
– ident: e_1_2_7_21_1
  doi: 10.24963/ijcai.2018/471
– ident: e_1_2_7_27_1
  doi: 10.1145/3109859.3109890
– ident: e_1_2_7_36_1
  doi: 10.1145/3097983.3098036
– ident: e_1_2_7_2_1
  doi: 10.1002/cpe.6177
– ident: e_1_2_7_22_1
– ident: e_1_2_7_46_1
  doi: 10.3390/s19122749
– ident: e_1_2_7_10_1
  doi: 10.1587/transinf.2019EDL8103
– ident: e_1_2_7_6_1
  doi: 10.1109/TCYB.2020.2999492
– volume: 11
  start-page: 992
  issue: 4
  year: 2011
  ident: e_1_2_7_17_1
  article-title: PathSim: meta‐path‐based top‐k similarity search in heterogeneous information networks
  publication-title: VLDB Endowment
– ident: e_1_2_7_38_1
  doi: 10.1109/LSP.2020.3032277
– ident: e_1_2_7_14_1
  doi: 10.1145/2339530.2339729
– ident: e_1_2_7_25_1
  doi: 10.1145/3178876.3186070
– ident: e_1_2_7_37_1
  doi: 10.1145/3132847.3132953
– ident: e_1_2_7_8_1
  doi: 10.1016/j.neucom.2020.05.106
– start-page: e5697
  year: 2020
  ident: e_1_2_7_41_1
  article-title: AGCNN: adaptive Gabor convolutional neural networks with receptive fields for vein biometric recognition
  publication-title: Concurr Comput Pract Exp
– start-page: 1
  year: 2021
  ident: e_1_2_7_9_1
  article-title: Encoder‐X: solving unknown coefficients automatically in polynomial fitting by using an autoencoder
  publication-title: IEEE Trans Neural Netw Learn Syst
– ident: e_1_2_7_18_1
– ident: e_1_2_7_3_1
  doi: 10.1587/transinf.2018EDL8239
– ident: e_1_2_7_33_1
  doi: 10.1145/2736277.2741093
– ident: e_1_2_7_12_1
– ident: e_1_2_7_50_1
  doi: 10.1109/MC.2009.263
– ident: e_1_2_7_31_1
– volume: 69
  issue: 1
  year: 2021
  ident: e_1_2_7_45_1
  article-title: Voxel‐based three‐view hybrid parallel network for 3D object classification
  publication-title: Displays
– volume: 6147
  start-page: e6147
  year: 2020
  ident: e_1_2_7_4_1
  article-title: Multi‐view frontal face image generation: a survey
  publication-title: Concurr Comput Pract Exp
– ident: e_1_2_7_15_1
SSID ssj0011031
Score 2.283498
Snippet Convolutional network (CNN) has been widely used in processing various graphics and network data analysis tasks. Therefore, facing the recommendation problem...
SourceID crossref
SourceType Enrichment Source
Index Database
Title Research on cross‐hierarchical graph network recommendation algorithm based on random walk and convolutional neural network
WOSCitedRecordID wos000715585000001&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: PRVWIB
  databaseName: Wiley Online Library Full Collection 2020
  customDbUrl:
  eissn: 1532-0634
  dateEnd: 99991231
  omitProxy: false
  ssIdentifier: ssj0011031
  issn: 1532-0626
  databaseCode: DRFUL
  dateStart: 20010101
  isFulltext: true
  titleUrlDefault: https://onlinelibrary.wiley.com
  providerName: Wiley-Blackwell
link http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwtV1Lb9QwELZgy4EL5SnaAjISEocokDrJOjmiQukBVQi1Um8rxw-66m6y2m76OFTiJ_Ab-SXM-JEm7aUcuGQjy5nd5Mt6xp7x9xHyzqQmrySKZmgDE5RUm7iQ2zLmKbhLzbVKTWXFJvj-fnF0VH73mq2nVk6A13VxcVEu_ivU0AZg49bZf4C7MwoNcA6gwxFgh-OdgA-1dJgGcKLooZ4BZa9t4gBxsUzVUe2qwCOcF8_n2issRWL2s1lOV8fzCL2cQlPg01Qzj87F7MTvhavP_H2ANaTFtB_WXD_i3WlqaTmg5GXYQ7doh_n_vdYvWmOJ7XWWyo6HX9vmuJ321ybYtt2kNxxOWZyMmSe77re5JcxbA7gjhJUL_WHMnS7xkCP7hu_qKgod-zKbwJUTvPI-WWM8L4sRWfv8Y_fwW5dZQlkLx6HrflkgJE7Yx_CtvRClF2scPCaP_CSBfnLgPiH3dP2UrAcBDurH42fkKmBNm5paY39-_e6jTC3K1MNChyjTDmVqUUYjDmWKKFM4pQOUqUM5mHtODne_HOzsxV5PI5aM8VWslcx1jpSSaVKoMjdGaJ4JVigYpHMITQWXWpQVuD8lIY7UhUJGOMUqiGEyZdIXZFQ3tX5JKPyVM1VmXCVCZJwp5EFUKhkrWY1zI_IN8j48won0ZPOoeTKb3ARqg7ztei4cwcqtPpt36LNFHl6_ga_IaLVs9WvyQJ6tpqfLN_4t-AvD23i4
linkProvider Wiley-Blackwell
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=Research+on+cross%E2%80%90hierarchical+graph+network+recommendation+algorithm+based+on+random+walk+and+convolutional+neural+network&rft.jtitle=Concurrency+and+computation&rft.au=Huang%2C+Meng&rft.au=Sun%2C+Guohui&rft.date=2021-11-08&rft.issn=1532-0626&rft.eissn=1532-0634&rft_id=info:doi/10.1002%2Fcpe.6704&rft.externalDBID=n%2Fa&rft.externalDocID=10_1002_cpe_6704
thumbnail_l http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/lc.gif&issn=1532-0626&client=summon
thumbnail_m http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/mc.gif&issn=1532-0626&client=summon
thumbnail_s http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/sc.gif&issn=1532-0626&client=summon