Symmetric Graph Convolutional Autoencoder for Unsupervised Graph Representation Learning

We propose a symmetric graph convolutional autoencoder which produces a low-dimensional latent representation from a graph. In contrast to the existing graph autoencoders with asymmetric decoder parts, the proposed autoencoder has a newly designed decoder which builds a completely symmetric autoenco...

Ausführliche Beschreibung

Gespeichert in:
Bibliographische Detailangaben
Veröffentlicht in:Proceedings / IEEE International Conference on Computer Vision S. 6518 - 6527
Hauptverfasser: Park, Jiwoong, Lee, Minsik, Chang, Hyung Jin, Lee, Kyuewang, Choi, Jin Young
Format: Tagungsbericht
Sprache:Englisch
Veröffentlicht: IEEE 01.10.2019
Schlagworte:
ISSN:2380-7504
Online-Zugang:Volltext
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
Abstract We propose a symmetric graph convolutional autoencoder which produces a low-dimensional latent representation from a graph. In contrast to the existing graph autoencoders with asymmetric decoder parts, the proposed autoencoder has a newly designed decoder which builds a completely symmetric autoencoder form. For the reconstruction of node features, the decoder is designed based on Laplacian sharpening as the counterpart of Laplacian smoothing of the encoder, which allows utilizing the graph structure in the whole processes of the proposed autoencoder architecture. In order to prevent the numerical instability of the network caused by the Laplacian sharpening introduction, we further propose a new numerically stable form of the Laplacian sharpening by incorporating the signed graphs. In addition, a new cost function which finds a latent representation and a latent affinity matrix simultaneously is devised to boost the performance of image clustering tasks. The experimental results on clustering, link prediction and visualization tasks strongly support that the proposed model is stable and outperforms various state-of-the-art algorithms.
AbstractList We propose a symmetric graph convolutional autoencoder which produces a low-dimensional latent representation from a graph. In contrast to the existing graph autoencoders with asymmetric decoder parts, the proposed autoencoder has a newly designed decoder which builds a completely symmetric autoencoder form. For the reconstruction of node features, the decoder is designed based on Laplacian sharpening as the counterpart of Laplacian smoothing of the encoder, which allows utilizing the graph structure in the whole processes of the proposed autoencoder architecture. In order to prevent the numerical instability of the network caused by the Laplacian sharpening introduction, we further propose a new numerically stable form of the Laplacian sharpening by incorporating the signed graphs. In addition, a new cost function which finds a latent representation and a latent affinity matrix simultaneously is devised to boost the performance of image clustering tasks. The experimental results on clustering, link prediction and visualization tasks strongly support that the proposed model is stable and outperforms various state-of-the-art algorithms.
Author Chang, Hyung Jin
Lee, Minsik
Choi, Jin Young
Park, Jiwoong
Lee, Kyuewang
Author_xml – sequence: 1
  givenname: Jiwoong
  surname: Park
  fullname: Park, Jiwoong
  organization: Seoul National University
– sequence: 2
  givenname: Minsik
  surname: Lee
  fullname: Lee, Minsik
  organization: Hanyang University
– sequence: 3
  givenname: Hyung Jin
  surname: Chang
  fullname: Chang, Hyung Jin
  organization: University of Birmingham
– sequence: 4
  givenname: Kyuewang
  surname: Lee
  fullname: Lee, Kyuewang
  organization: Seoul National University
– sequence: 5
  givenname: Jin Young
  surname: Choi
  fullname: Choi, Jin Young
  organization: Seoul National University
BookMark eNotjEFLwzAYQKMouM2dPXjpH2j9ki9tkuMoOgcFQZ14G2n7VSNbUtJusH8_xZ3e5b03ZVc-eGLsjkPGOZiHVVl-ZAK4yQCKQlywuVGaK6G51ID6kk0EakhVDvKGTYfhBwCN0MWEfb4ddzsao2uSZbT9d1IGfwjb_eiCt9tksR8D-Sa0FJMuxGTth31P8eAGas_BK_WRBvKj_WuSimz0zn_dsuvObgeanzlj66fH9_I5rV6Wq3JRpQ45jGkuWmmsBVULSdTlvOkAW8NRoGgAbWdQUANa5bXUopa_Ms87RVrzBhXWOGP3_19HRJs-up2Nx40BDgAST5X3VDY
ContentType Conference Proceeding
DBID 6IE
6IH
CBEJK
RIE
RIO
DOI 10.1109/ICCV.2019.00662
DatabaseName IEEE Electronic Library (IEL) Conference Proceedings
IEEE Proceedings Order Plan (POP) 1998-present by volume
IEEE Xplore All Conference Proceedings
IEEE/IET Electronic Library
IEEE Proceedings Order Plans (POP) 1998-present
DatabaseTitleList
Database_xml – sequence: 1
  dbid: RIE
  name: IEEE
  url: https://ieeexplore.ieee.org/
  sourceTypes: Publisher
DeliveryMethod fulltext_linktorsrc
Discipline Applied Sciences
EISBN 9781728148038
1728148030
EISSN 2380-7504
EndPage 6527
ExternalDocumentID 9010004
Genre orig-research
GroupedDBID 29O
6IE
6IF
6IH
6IK
6IL
6IM
6IN
AAJGR
AAWTH
ACGFS
ADZIZ
ALMA_UNASSIGNED_HOLDINGS
BEFXN
BFFAM
BGNUA
BKEBE
BPEOZ
CBEJK
CHZPO
IPLJI
M43
OCL
RIE
RIL
RIO
RNS
ID FETCH-LOGICAL-i310t-52d49aa07b24eef51cf03d913232c03af932ec0875b482b449a15f7e881c373b3
IEDL.DBID RIE
ISICitedReferencesCount 213
ISICitedReferencesURI http://www.webofscience.com/api/gateway?GWVersion=2&SrcApp=Summon&SrcAuth=ProQuest&DestLinkType=CitingArticles&DestApp=WOS_CPL&KeyUT=000548549201064&url=https%3A%2F%2Fcvtisr.summon.serialssolutions.com%2F%23%21%2Fsearch%3Fho%3Df%26include.ft.matches%3Dt%26l%3Dnull%26q%3D
IngestDate Wed Aug 27 02:44:58 EDT 2025
IsDoiOpenAccess false
IsOpenAccess true
IsPeerReviewed false
IsScholarly true
Language English
LinkModel DirectLink
MergedId FETCHMERGED-LOGICAL-i310t-52d49aa07b24eef51cf03d913232c03af932ec0875b482b449a15f7e881c373b3
OpenAccessLink http://pure-oai.bham.ac.uk/ws/files/73271168/Symmetric_Graph.pdf
PageCount 10
ParticipantIDs ieee_primary_9010004
PublicationCentury 2000
PublicationDate 2019-10-01
PublicationDateYYYYMMDD 2019-10-01
PublicationDate_xml – month: 10
  year: 2019
  text: 2019-10-01
  day: 01
PublicationDecade 2010
PublicationTitle Proceedings / IEEE International Conference on Computer Vision
PublicationTitleAbbrev ICCV
PublicationYear 2019
Publisher IEEE
Publisher_xml – name: IEEE
SSID ssj0039286
Score 2.5794582
Snippet We propose a symmetric graph convolutional autoencoder which produces a low-dimensional latent representation from a graph. In contrast to the existing graph...
SourceID ieee
SourceType Publisher
StartPage 6518
SubjectTerms Chebyshev approximation
Convolution
Decoding
Image reconstruction
Laplace equations
Smoothing methods
Task analysis
Title Symmetric Graph Convolutional Autoencoder for Unsupervised Graph Representation Learning
URI https://ieeexplore.ieee.org/document/9010004
WOSCitedRecordID wos000548549201064&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
link http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwlV3PT8IwFH5B4sETKhjFH-nBo5N13Wh3NETUxBCiQriRtXs1JDII20j87223ih68eFqztFvSX-9r3_e-B3DNGRrcrSNPYaK9EP3IE1EsPRqkFJmWEisFvukzH43EbBaPG3Czi4VBxIp8hre2WPny05Uq7VVZz1IJKvHPPc55Hav1vesaMy_6TrqH-nHvaTCYWuKWVaPs21Q4v3KnVKZj2PrfTw-h8xODR8Y763IEDcyOoeVAI3FLMm_D7PVzubRpsRR5sOLTxLTfuvmUfJC7slhZrcoUN8TgUzLJ8nJt94fcfKVu8FKRYV0MUkac4up7BybD-7fBo-fSJXgLg9EKc6RMwzhJfC6DEFFHVGmfpbE5brJA-SzRBqqhsgr2MhSBDE1lGmmOQlDFOJPsBJrZKsNTIDqUgmomaZ9L60gVaGCiecRmhYtIBWfQth01X9eKGHPXR92_X5_DgR2JmgJ3Ac1iU-Il7Kttscg3V9UwfgE605_o
linkProvider IEEE
linkToHtml http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwlV3PT8IwFG4ImugJFYy_7cGjk3XtWHc0RISIhCgQbmTtXgmJDMI2Ev97262iBy-e1iztlvTX-9r3ve8hdBdQ0Lhb-Y6ESDkMXN_hfigc4sUEqBICCgW-ST8YDPh0Gg4r6H4XCwMABfkMHkyx8OXHK5mbq7KmoRIU4p97PmMeKaO1vvddbeh5y4r3EDds9trtiaFuGT3KlkmG8yt7SmE8OrX__fYINX6i8PBwZ1-OUQWSE1SzsBHbRZnW0fT9c7k0ibEkfjby01i339oZFX3gxzxbGbXKGDZYI1Q8TtJ8bXaIVH-lbPBW0GFtFFKCrebqvIHGnadRu-vYhAnOQqO0TB8qYxZGkRsIjwEon0jl0jjUB07qSZdGSoM1kEbDXjDuCaYrE18FwDmRNKCCnqJqskrgDGHFBCeKCtIKhHGlctBAUT9Cvca5L71zVDcdNVuXmhgz20cXf7--RQfd0Wt_1u8NXi7RoRmVkhB3harZJodrtC-32SLd3BRD-gW6TqMv
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%3Abook&rft.genre=proceeding&rft.title=Proceedings+%2F+IEEE+International+Conference+on+Computer+Vision&rft.atitle=Symmetric+Graph+Convolutional+Autoencoder+for+Unsupervised+Graph+Representation+Learning&rft.au=Park%2C+Jiwoong&rft.au=Lee%2C+Minsik&rft.au=Chang%2C+Hyung+Jin&rft.au=Lee%2C+Kyuewang&rft.date=2019-10-01&rft.pub=IEEE&rft.eissn=2380-7504&rft.spage=6518&rft.epage=6527&rft_id=info:doi/10.1109%2FICCV.2019.00662&rft.externalDocID=9010004