Topological Data Analysis in Graph Neural Networks: Surveys and Perspectives

For many years, topological data analysis (TDA) and deep learning (DL) have been considered separate data analysis and representation learning approaches, which have nothing in common. The root cause of this challenge comes from the difficulties in building, extracting, and integrating TDA construct...

Celý popis

Uložené v:
Podrobná bibliografia
Vydané v:IEEE transaction on neural networks and learning systems Ročník 36; číslo 6; s. 9758 - 9776
Hlavní autori: Pham, Phu, Bui, Quang-Thinh, Thanh Nguyen, Ngoc, Kozma, Robert, Yu, Philip S., Vo, Bay
Médium: Journal Article
Jazyk:English
Vydavateľské údaje: United States IEEE 01.06.2025
Predmet:
ISSN:2162-237X, 2162-2388, 2162-2388
On-line prístup:Získať plný text
Tagy: Pridať tag
Žiadne tagy, Buďte prvý, kto otaguje tento záznam!
Abstract For many years, topological data analysis (TDA) and deep learning (DL) have been considered separate data analysis and representation learning approaches, which have nothing in common. The root cause of this challenge comes from the difficulties in building, extracting, and integrating TDA constructs, such as barcodes or persistent diagrams, within deep neural network architectures. Therefore, the powers of these two approaches are still on their islands and have not yet combined to form more powerful tools for dealing with multiple complex data analysis tasks. Fortunately, we have witnessed several remarkable attempts to integrate DL-based architectures with topological learning paradigms in recent years. These topology-driven DL techniques have notably improved data-driven analysis and mining problems, especially within graph datasets. Recently, graph neural networks (GNNs) have emerged as a popular deep neural architecture, demonstrating significant performance in various graph-based analysis and learning problems. Explicitly, within the manifold paradigm, the graph is naturally considered as a topological object (e.g., the topological properties of the given graph can be represented by the edge weights). Therefore, integrating TDA and GNN is considered an excellent combination. Many well-known studies have recently presented the effectiveness of TDA-assisted GNN-based architectures in dealing with complex graph-based data representation analysis and learning problems. Motivated by the successes of recent research, we present systematic literature about this nascent and promising research direction in this article, which includes general taxonomy, preliminaries, and recently proposed state-of-the-art topology-driven GNN models and perspectives.
AbstractList For many years, topological data analysis (TDA) and deep learning (DL) have been considered separate data analysis and representation learning approaches, which have nothing in common. The root cause of this challenge comes from the difficulties in building, extracting, and integrating TDA constructs, such as barcodes or persistent diagrams, within deep neural network architectures. Therefore, the powers of these two approaches are still on their islands and have not yet combined to form more powerful tools for dealing with multiple complex data analysis tasks. Fortunately, we have witnessed several remarkable attempts to integrate DL-based architectures with topological learning paradigms in recent years. These topology-driven DL techniques have notably improved data-driven analysis and mining problems, especially within graph datasets. Recently, graph neural networks (GNNs) have emerged as a popular deep neural architecture, demonstrating significant performance in various graph-based analysis and learning problems. Explicitly, within the manifold paradigm, the graph is naturally considered as a topological object (e.g., the topological properties of the given graph can be represented by the edge weights). Therefore, integrating TDA and GNN is considered an excellent combination. Many well-known studies have recently presented the effectiveness of TDA-assisted GNN-based architectures in dealing with complex graph-based data representation analysis and learning problems. Motivated by the successes of recent research, we present systematic literature about this nascent and promising research direction in this article, which includes general taxonomy, preliminaries, and recently proposed state-of-the-art topology-driven GNN models and perspectives.For many years, topological data analysis (TDA) and deep learning (DL) have been considered separate data analysis and representation learning approaches, which have nothing in common. The root cause of this challenge comes from the difficulties in building, extracting, and integrating TDA constructs, such as barcodes or persistent diagrams, within deep neural network architectures. Therefore, the powers of these two approaches are still on their islands and have not yet combined to form more powerful tools for dealing with multiple complex data analysis tasks. Fortunately, we have witnessed several remarkable attempts to integrate DL-based architectures with topological learning paradigms in recent years. These topology-driven DL techniques have notably improved data-driven analysis and mining problems, especially within graph datasets. Recently, graph neural networks (GNNs) have emerged as a popular deep neural architecture, demonstrating significant performance in various graph-based analysis and learning problems. Explicitly, within the manifold paradigm, the graph is naturally considered as a topological object (e.g., the topological properties of the given graph can be represented by the edge weights). Therefore, integrating TDA and GNN is considered an excellent combination. Many well-known studies have recently presented the effectiveness of TDA-assisted GNN-based architectures in dealing with complex graph-based data representation analysis and learning problems. Motivated by the successes of recent research, we present systematic literature about this nascent and promising research direction in this article, which includes general taxonomy, preliminaries, and recently proposed state-of-the-art topology-driven GNN models and perspectives.
For many years, topological data analysis (TDA) and deep learning (DL) have been considered separate data analysis and representation learning approaches, which have nothing in common. The root cause of this challenge comes from the difficulties in building, extracting, and integrating TDA constructs, such as barcodes or persistent diagrams, within deep neural network architectures. Therefore, the powers of these two approaches are still on their islands and have not yet combined to form more powerful tools for dealing with multiple complex data analysis tasks. Fortunately, we have witnessed several remarkable attempts to integrate DL-based architectures with topological learning paradigms in recent years. These topology-driven DL techniques have notably improved data-driven analysis and mining problems, especially within graph datasets. Recently, graph neural networks (GNNs) have emerged as a popular deep neural architecture, demonstrating significant performance in various graph-based analysis and learning problems. Explicitly, within the manifold paradigm, the graph is naturally considered as a topological object (e.g., the topological properties of the given graph can be represented by the edge weights). Therefore, integrating TDA and GNN is considered an excellent combination. Many well-known studies have recently presented the effectiveness of TDA-assisted GNN-based architectures in dealing with complex graph-based data representation analysis and learning problems. Motivated by the successes of recent research, we present systematic literature about this nascent and promising research direction in this article, which includes general taxonomy, preliminaries, and recently proposed state-of-the-art topology-driven GNN models and perspectives.
Author Pham, Phu
Vo, Bay
Bui, Quang-Thinh
Kozma, Robert
Yu, Philip S.
Thanh Nguyen, Ngoc
Author_xml – sequence: 1
  givenname: Phu
  orcidid: 0000-0002-8599-8126
  surname: Pham
  fullname: Pham, Phu
  email: pta.phu@hutech.edu.vn
  organization: Faculty of Information Technology, HUTECH University, Ho Chi Minh City, Vietnam
– sequence: 2
  givenname: Quang-Thinh
  surname: Bui
  fullname: Bui, Quang-Thinh
  email: vd.bay@hutech.edu.vn
  organization: Faculty of Education and Basic Sciences, Tien Giang University, My Tho City, Vietnam
– sequence: 3
  givenname: Ngoc
  orcidid: 0000-0002-3247-2948
  surname: Thanh Nguyen
  fullname: Thanh Nguyen, Ngoc
  email: ngoc-thanh.nguyen@pwr.edu.pl
  organization: Department of Applied Informatics, Wrocław University of Science and Technology, Wrocław, Poland
– sequence: 4
  givenname: Robert
  orcidid: 0000-0001-7011-5768
  surname: Kozma
  fullname: Kozma, Robert
  email: rkozma@memphis.edu
  organization: Department of Mathematics, University of Memphis, Memphis, TN, USA
– sequence: 5
  givenname: Philip S.
  orcidid: 0000-0002-3491-5968
  surname: Yu
  fullname: Yu, Philip S.
  email: psyu@uic.edu
  organization: Department of Computer Science, University of Illinois Chicago, Chicago, IL, USA
– sequence: 6
  givenname: Bay
  orcidid: 0000-0002-9246-4587
  surname: Vo
  fullname: Vo, Bay
  email: vd.bay@hutech.edu.vn
  organization: Faculty of Information Technology, HUTECH University, Ho Chi Minh City, Vietnam
BackLink https://www.ncbi.nlm.nih.gov/pubmed/40030848$$D View this record in MEDLINE/PubMed
BookMark eNp9kE1PwkAQhjcGI4j8AWNMj17A_Wp38UZQ0aRBEzDx1my3g66Wbt1tMfx7iyAxHpzLTDLPO5M8x6hV2AIQOiV4QAgeXs6n03g2oJjyAQspJlwcoA4lEe1TJmVrP4vnNup5_4abinAY8eERanOMGZZcdlA8t6XN7YvRKg-uVaWCUaHytTc-MEUwcap8DaZQu2Y7herTund_Fcxqt4K1D1SRBY_gfAm6MivwJ-hwoXIPvV3voqfbm_n4rh8_TO7Ho7ivGeVVf8FJpjgRTAHwNCVMRKlgmQ4zwlmGUxkKoTDXTAsSCsY5wWkkszQVYTTUVLEuutjeLZ39qMFXydJ4DXmuCrC1T1hzm2M2jHCDnu_QOl1ClpTOLJVbJz8GGoBuAe2s9w4We4TgZGM6-TadbEwnO9NNSP4JaVOpytiicsrk_0fPtlEDAL9-SRqFkrEv8kOKeg
CODEN ITNNAL
CitedBy_id crossref_primary_10_1016_j_knosys_2025_113125
crossref_primary_10_1002_minf_202400335
crossref_primary_10_3389_fimmu_2025_1615278
crossref_primary_10_1007_s40745_025_00633_9
crossref_primary_10_1016_j_compbiolchem_2025_108548
crossref_primary_10_1109_TASE_2025_3580658
crossref_primary_10_1002_for_70012
Cites_doi 10.1109/TNNLS.2021.3104901
10.1109/MSP.2017.2693418
10.1109/TPAMI.2020.3013679
10.1109/TCYB.2022.3233819
10.1111/j.1467-8659.2009.01515.x
10.3389/fgene.2021.690049
10.1561/2200000096
10.1109/TNNLS.2021.3060872
10.3389/fdata.2021.680535
10.48550/arXiv.1606.09375
10.1109/TKDE.2024.3374701
10.1609/aaai.v32i1.11782
10.1090/jams/852
10.1109/TKDE.2020.3045924
10.1016/j.ddtec.2020.11.009
10.24963/ijcai.2019/267
10.1109/TNNLS.2020.2978386
10.1007/978-3-030-43408-3_5
10.1016/j.jbi.2022.104082
10.1609/aaai.v37i6.25866
10.1109/TKDE.2022.3148299
10.1016/j.cag.2010.03.007
10.1145/3535101
10.48550/ARXIV.1706.03762
10.1073/pnas.2019994118
10.1016/j.eswa.2020.113790
10.1007/s00454-004-1146-y
10.1145/3447548.3467442
10.1145/3234150
10.1109/TNNLS.2021.3070843
10.1007/978-3-030-43036-8_6
10.1109/TNNLS.2021.3137396
10.1007/s10462-022-10265-7
10.1140/epjds/s13688-017-0109-5
10.3389/frai.2021.681108
10.1609/aaai.v38i13.29328
10.1145/3326362
10.1016/j.eswa.2022.117921
10.1016/j.aiopen.2021.01.001
10.1016/j.ins.2022.11.085
10.1007/s10462-024-10710-9
10.1109/TKDE.2021.3101356
10.1145/3565973
10.1145/3292500.3330982
10.1090/s0273-0979-09-01249-x
10.1038/s42256-019-0087-3
10.1007/s10462-022-10146-z
10.1109/TKDE.2016.2598561
ContentType Journal Article
DBID 97E
RIA
RIE
AAYXX
CITATION
NPM
7X8
DOI 10.1109/TNNLS.2024.3520147
DatabaseName IEEE Xplore (IEEE)
IEEE All-Society Periodicals Package (ASPP) 1998–Present
IEEE/IET Electronic Library (IEL) (UW System Shared)
CrossRef
PubMed
MEDLINE - Academic
DatabaseTitle CrossRef
PubMed
MEDLINE - Academic
DatabaseTitleList MEDLINE - Academic
PubMed

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 9776
ExternalDocumentID 40030848
10_1109_TNNLS_2024_3520147
10826583
Genre orig-research
Journal Article
GrantInformation_xml – fundername: Vietnam National Foundation for Science and Technology Development (NAFOSTED)
  grantid: 102.05-2021.08
  funderid: 10.13039/100007224
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
NPM
RIG
7X8
ID FETCH-LOGICAL-c324t-f41da4173aee4bb1376b73dc5d143d0b8577a04c3c715734410b68dbb7569c2a3
IEDL.DBID RIE
ISICitedReferencesCount 12
ISICitedReferencesURI http://www.webofscience.com/api/gateway?GWVersion=2&SrcApp=Summon&SrcAuth=ProQuest&DestLinkType=CitingArticles&DestApp=WOS_CPL&KeyUT=001395152400001&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 Nov 09 12:15:53 EST 2025
Mon Jul 21 05:30:43 EDT 2025
Tue Nov 18 22:27:46 EST 2025
Sat Nov 29 07:48:17 EST 2025
Wed Aug 27 01:52:21 EDT 2025
IsPeerReviewed false
IsScholarly true
Issue 6
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-c324t-f41da4173aee4bb1376b73dc5d143d0b8577a04c3c715734410b68dbb7569c2a3
Notes ObjectType-Article-1
SourceType-Scholarly Journals-1
ObjectType-Feature-2
content type line 23
ORCID 0000-0001-7011-5768
0000-0002-8599-8126
0000-0002-3247-2948
0000-0002-9246-4587
0000-0002-3491-5968
PMID 40030848
PQID 3173403960
PQPubID 23479
PageCount 19
ParticipantIDs crossref_citationtrail_10_1109_TNNLS_2024_3520147
crossref_primary_10_1109_TNNLS_2024_3520147
proquest_miscellaneous_3173403960
ieee_primary_10826583
pubmed_primary_40030848
PublicationCentury 2000
PublicationDate 2025-06-01
PublicationDateYYYYMMDD 2025-06-01
PublicationDate_xml – month: 06
  year: 2025
  text: 2025-06-01
  day: 01
PublicationDecade 2020
PublicationPlace United States
PublicationPlace_xml – name: United States
PublicationTitle IEEE transaction on neural networks and learning systems
PublicationTitleAbbrev TNNLS
PublicationTitleAlternate IEEE Trans Neural Netw Learn Syst
PublicationYear 2025
Publisher IEEE
Publisher_xml – name: IEEE
References ref57
Zhao (ref62); 34
ref52
ref54
Veličković (ref16)
Carrière (ref97)
Topping (ref68)
ref45
ref48
ref47
ref42
ref41
ref44
ref43
Immonen (ref82)
Zhang (ref22)
Sun (ref46)
Zhang (ref86)
ref49
Bianchi (ref55)
ref8
ref7
ref9
Moor (ref29)
ref4
ref3
ref6
Akçora (ref80)
ref5
Togninalli (ref65) 2019; 32
ref40
ref35
ref34
ref37
ref36
Zhang (ref17)
ref30
ref33
Gao (ref21)
Vandaele (ref32) 2020; 21
Kipf (ref14)
ref39
ref38
Wijesinghe (ref64)
Carrière (ref75)
Zhao (ref83)
ref26
ref25
ref28
Zhu (ref23)
ref27
Hofer (ref73); 1
Chami (ref19)
Xu (ref18)
ref13
ref12
Wen (ref88)
Yang (ref50)
Horn (ref74)
ref96
ref11
Maron (ref66); 32
ref10
Ying (ref51)
Lee (ref53)
Solomon (ref98)
Birdal (ref31)
Zaheer (ref79)
Balcılar (ref58)
You (ref99)
Yang (ref59)
ref90
ref89
Gasteiger (ref60)
Trofimov (ref92)
ref81
ref84
de Surrel (ref94)
Kim (ref95); 33
Williams (ref93)
Chen (ref78)
ref77
ref76
Songdechakraiwut (ref87)
ref2
ref1
Bodnar (ref85)
Wang (ref56); 1
ref70
Barannikov (ref91)
Weisfeiler (ref63) 1968; 2
Yun (ref20); 32
ref67
ref69
Zhang (ref24)
Hofer (ref71)
Hofer (ref72) 2019; 20
Hamilton (ref15)
ref61
References_xml – ident: ref25
  doi: 10.1109/TNNLS.2021.3104901
– ident: ref13
  doi: 10.1109/MSP.2017.2693418
– ident: ref96
  doi: 10.1109/TPAMI.2020.3013679
– ident: ref45
  doi: 10.1109/TCYB.2022.3233819
– ident: ref90
  doi: 10.1111/j.1467-8659.2009.01515.x
– ident: ref9
  doi: 10.3389/fgene.2021.690049
– start-page: 874
  volume-title: Proc. ICML
  ident: ref55
  article-title: Spectral clustering with graph neural networks for graph pooling
– volume-title: Proc. NeurIPS
  ident: ref87
  article-title: Scalable vector representation for topological data analysis based classification
– volume-title: Proc. ICLR
  ident: ref22
  article-title: Capsule graph neural network
– volume-title: Proc. ICML
  ident: ref29
  article-title: Topological autoencoders
– start-page: 27029
  volume-title: Proc. NeurIPS
  ident: ref78
  article-title: Topological relational learning on graphs
– ident: ref39
  doi: 10.1561/2200000096
– volume: 1
  start-page: 9952
  volume-title: Proc. ICML
  ident: ref56
  article-title: Haar graph pooling
– ident: ref4
  doi: 10.1109/TNNLS.2021.3060872
– ident: ref84
  doi: 10.3389/fdata.2021.680535
– ident: ref57
  doi: 10.48550/arXiv.1606.09375
– ident: ref42
  doi: 10.1109/TKDE.2024.3374701
– volume: 32
  start-page: 2153
  volume-title: Proc. NeurIPS
  ident: ref66
  article-title: Provably powerful graph networks
– ident: ref52
  doi: 10.1609/aaai.v32i1.11782
– volume-title: Proc. ICLR
  ident: ref14
  article-title: Semi-supervised classification with graph convolutional networks
– start-page: 3734
  volume-title: Proc. ICML
  ident: ref53
  article-title: Self-attention graph pooling
– volume-title: Proc. ICLR
  ident: ref74
  article-title: Topological graph neural networks
– ident: ref27
  doi: 10.1090/jams/852
– start-page: 1294
  volume-title: Proc. ICML
  ident: ref97
  article-title: Optimizing persistent homology based functions
– volume: 1
  start-page: 4314
  volume-title: Proc. ICML
  ident: ref73
  article-title: Graph filtration learning
– ident: ref48
  doi: 10.1109/TKDE.2020.3045924
– ident: ref10
  doi: 10.1016/j.ddtec.2020.11.009
– start-page: 16962
  volume-title: Proc. NeurIPS
  ident: ref50
  article-title: Self-supervised heterogeneous graph pre-training based on structural clustering
– ident: ref61
  doi: 10.24963/ijcai.2019/267
– start-page: 2786
  volume-title: Proc. AISTATS
  ident: ref75
  article-title: PersLay: A neural network layer for persistence diagrams and new graph topological signatures
– volume-title: Proc. NeurIPS
  ident: ref51
  article-title: Hierarchical graph representation learning with differentiable pooling
– ident: ref1
  doi: 10.1109/TNNLS.2020.2978386
– ident: ref34
  doi: 10.1007/978-3-030-43408-3_5
– ident: ref38
  doi: 10.1016/j.jbi.2022.104082
– start-page: 96
  volume-title: Proc. Topological, Algebraic Geometric Learn. Workshops
  ident: ref94
  article-title: RipsNet: A general architecture for fast and robust estimation of the persistent homology of point clouds
– ident: ref81
  doi: 10.1609/aaai.v37i6.25866
– ident: ref41
  doi: 10.1109/TKDE.2022.3148299
– ident: ref69
  doi: 10.1016/j.cag.2010.03.007
– ident: ref5
  doi: 10.1145/3535101
– volume-title: Proc. ICLR
  ident: ref92
  article-title: Learning topology-preserving data representations
– start-page: 2083
  volume-title: Proc. ICML
  ident: ref21
  article-title: Graph U-Nets
– ident: ref67
  doi: 10.48550/ARXIV.1706.03762
– volume-title: Proc. NeurIPS
  ident: ref79
  article-title: Deep sets
– ident: ref30
  doi: 10.1073/pnas.2019994118
– ident: ref6
  doi: 10.1016/j.eswa.2020.113790
– volume: 33
  start-page: 15965
  volume-title: Proc. NeurIPS
  ident: ref95
  article-title: PLLay: Efficient topological layer based on persistent landscapes
– volume-title: Proc. ICML
  ident: ref23
  article-title: Deep graph contrastive representation learning
– volume: 32
  start-page: 11960
  volume-title: Proc. NeurIPS
  ident: ref20
  article-title: Graph transformer networks
– ident: ref33
  doi: 10.1007/s00454-004-1146-y
– start-page: 4602
  volume-title: Proc. NeurIPS
  ident: ref99
  article-title: Graph contrastive learning with augmentations
– volume-title: Proc. NeurIPS
  ident: ref82
  article-title: Going beyond persistent homology using persistent homology
– start-page: 16:1
  volume-title: Proc. LoG
  ident: ref86
  article-title: GEFL: Extended filtration learning for graph classification
– start-page: 1
  volume-title: Proc. ICLR
  ident: ref64
  article-title: A new perspective on ’how graph neural networks go beyond Weisfeiler–Lehman?
– volume-title: Proc. ICLR
  ident: ref18
  article-title: How powerful are graph neural networks
– ident: ref76
  doi: 10.1145/3447548.3467442
– volume: 21
  start-page: 1
  issue: 215
  year: 2020
  ident: ref32
  article-title: Mining topological structure in graphs through forest representations
  publication-title: J. Mach. Learn. Res.
– start-page: 6776
  volume-title: Proc. NeurIPS
  ident: ref31
  article-title: Intrinsic dimension, persistent homology and generalization in neural networks
– start-page: 1607
  volume-title: Proc. ICML
  ident: ref91
  article-title: Representation topology divergence: A method for comparing neural network representations
– start-page: 4738
  volume-title: Proc. NeurIPS
  ident: ref93
  article-title: Generalized shape metrics on neural representations
– volume: 20
  start-page: 1
  issue: 126
  year: 2019
  ident: ref72
  article-title: Learning representations of persistence barcodes
  publication-title: J. Mach. Learn. Res.
– ident: ref11
  doi: 10.1145/3234150
– start-page: 109
  volume-title: Proc. AISTATS
  ident: ref98
  article-title: A fast and robust method for global topological functional optimization
– volume-title: Proc. ICLR
  ident: ref16
  article-title: Graph attention networks
– start-page: 25046
  volume-title: Proc. NeurIPS
  ident: ref80
  article-title: Reduction algorithms for persistence diagrams of networks: CoralTDA and PrunIT
– start-page: 1026
  volume-title: Proc. ICML
  ident: ref85
  article-title: Weisfeiler and Lehman go topological: Message passing simplicial networks
– volume: 34
  start-page: 23321
  volume-title: Proc. NeurIPS
  ident: ref62
  article-title: Adaptive diffusion in graph neural networks
– start-page: 4330
  volume-title: Proc. AISTATS
  ident: ref88
  article-title: Tensor-view topological graph neural network
– ident: ref7
  doi: 10.1109/TNNLS.2021.3070843
– volume-title: Proc. NeurIPS
  ident: ref15
  article-title: Inductive representation learning on large graphs
– ident: ref77
  doi: 10.1007/978-3-030-43036-8_6
– volume-title: Proc. NeurIPS
  ident: ref71
  article-title: Deep learning with topological signatures
– ident: ref3
  doi: 10.1109/TNNLS.2021.3137396
– volume-title: Proc. ICLR
  ident: ref68
  article-title: Understanding over-squashing and bottlenecks on graphs via curvature
– ident: ref12
  doi: 10.1007/s10462-022-10265-7
– start-page: 25261
  volume-title: Proc. ICML
  ident: ref59
  article-title: A new perspective on the effects of spectrum in graph neural networks
– ident: ref70
  doi: 10.1140/epjds/s13688-017-0109-5
– ident: ref35
  doi: 10.3389/frai.2021.681108
– volume-title: Proc. NeurIPS
  ident: ref60
  article-title: Diffusion improves graph learning
– ident: ref43
  doi: 10.1609/aaai.v38i13.29328
– ident: ref89
  doi: 10.1145/3326362
– volume-title: Proc. NeurIPS
  ident: ref17
  article-title: Link prediction based on graph neural networks
– volume-title: Proc. NeurIPS
  ident: ref19
  article-title: Hyperbolic graph convolutional neural networks
– ident: ref8
  doi: 10.1016/j.eswa.2022.117921
– ident: ref2
  doi: 10.1016/j.aiopen.2021.01.001
– ident: ref44
  doi: 10.1016/j.ins.2022.11.085
– start-page: 12096
  volume-title: Proc. NeurIPS
  ident: ref46
  article-title: Does GNN pretraining help molecular representation?
– volume: 32
  start-page: 6439
  year: 2019
  ident: ref65
  article-title: Wasserstein Weisfeiler–Lehman graph kernels
  publication-title: NeurIPS
– ident: ref36
  doi: 10.1007/s10462-024-10710-9
– volume: 2
  start-page: 12
  issue: 9
  year: 1968
  ident: ref63
  article-title: The reduction of a graph to canonical form and the algebra which appears therein
  publication-title: Nauchno-Technicheskaja Informatsia
– volume-title: Proc. ICLR
  ident: ref58
  article-title: Analyzing the expressive power of graph neural networks in a spectral perspective
– ident: ref49
  doi: 10.1109/TKDE.2021.3101356
– ident: ref37
  doi: 10.1145/3565973
– ident: ref54
  doi: 10.1145/3292500.3330982
– ident: ref26
  doi: 10.1090/s0273-0979-09-01249-x
– ident: ref28
  doi: 10.1038/s42256-019-0087-3
– ident: ref40
  doi: 10.1007/s10462-022-10146-z
– ident: ref47
  doi: 10.1109/TKDE.2016.2598561
– start-page: 2896
  volume-title: Proc. AISTATS
  ident: ref83
  article-title: Persistence enhanced graph neural network
– volume-title: Proc. ICLR
  ident: ref24
  article-title: Graph-less neural networks: Teaching old MLPs new tricks via distillation
SSID ssj0000605649
Score 2.5590553
Snippet For many years, topological data analysis (TDA) and deep learning (DL) have been considered separate data analysis and representation learning approaches,...
SourceID proquest
pubmed
crossref
ieee
SourceType Aggregation Database
Index Database
Enrichment Source
Publisher
StartPage 9758
SubjectTerms Data analysis
Data mining
Data structures
Deep learning (DL)
Electronic mail
Feature extraction
graph filtration
graph neural network (GNN)
Graph neural networks
Learning systems
persistent homology (PH)
Representation learning
Surveys
Taxonomy
topological data analysis (TDA)
topological representation learning
Title Topological Data Analysis in Graph Neural Networks: Surveys and Perspectives
URI https://ieeexplore.ieee.org/document/10826583
https://www.ncbi.nlm.nih.gov/pubmed/40030848
https://www.proquest.com/docview/3173403960
Volume 36
WOSCitedRecordID wos001395152400001&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/eLvHCXMwlV1LS8QwEB5UPHhxfbu-iOBNqmmTNo038XlYiuAqeyt5FQTpyj78_U7SdvWi4K3QpJR8M8k3SWY-gLNKZi7LLY9sJl3EM82iXCc8kpWVVqN35aGW3utAFEU-GsmnNlk95MI458LlM3fhH8NZvh2bud8qQw9HMpzmbBmWhRBNstZiQ4UiMc8C3U3iLIkSJkZdkgyVl8OiGDxjOJjwC6QcGBd49T0eqrV46Z8fa1IQWfmdb4Z15773zz_egPWWYJLrxiI2YcnVW9DrxBtI68vbMBg28ggeJHKrZop09UnIW00efB1r4it34NuiuSo-vSLP88knQk9UbcnTd5rmdAde7u-GN49RK60QGWRQs6jisVU8Fkw5x7WOcZrRglmTWuRPluo8FUJRbpgRcSoYciaqEVKtRZpJkyi2Cyv1uHb7QKhTSrlKSFNRbmmsMyaq2HJbaWQrzPYh7ga3NG3dcS9_8V6G-IPKMmBTemzKFps-nC_6fDRVN_5sveNH_kfLZtD7cNqBWKLT-JMQVbvxfFoiaWKcMoze-rDXoLvo3RnFwS9fPYS1xGsAh52YI1iZTebuGFbN5-xtOjlByxzlJ8EyvwDh4NwK
linkProvider IEEE
linkToHtml http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwlV1NT9wwEB0VWoleSj-gLKXUlXqrAnbsxHFvCEpBTSMkttXeIn9FWgll0X7w-zt2koULSNwiJY4iP0_8xva8B_CtUbnPCycSlyufiNzwpDCpSFTjlDMYXUXU0vtXyqoqJhN11Rerx1oY7308fOaPwmXcy3czuwpLZRjhSIazgm_Ay0yIlHXlWuslFYrUPI-EN2V5mqRcToYyGaqOx1VVXmNCmIojJB2YGQT_PRH1WoL5z4NZKdqsPM4448xzvv3Mb34Lb3qKSU66MfEOXvj2PWwP9g2kj-YPUI47g4QAEznTS00GhRIybcmvoGRNgnYH3q26w-KLH-R6Nb9D8IluHbm6L9Rc7MDf85_j04ukN1dILHKoZdII5rRgkmvvhTEMfzRGcmczhwzKUVNkUmoqLLeSZZIja6IGQTVGZrmyqea7sNnOWr8HhHqttW-ksg0VjjKTc9kwJ1xjkK9wNwI2dG5te-XxYIBxU8cMhKo6YlMHbOoemxF8X7e57XQ3nnx6J_T8gye7Th_B1wHEGsMm7IXo1s9WixppExeUY_42go8duuvWw6DYf-StX2DrYvynrMvL6vcneJ0GR-C4LnMAm8v5yn-GV_ZuOV3MD-P4_A9Nkt5p
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=Topological+Data+Analysis+in+Graph+Neural+Networks%3A+Surveys+and+Perspectives&rft.jtitle=IEEE+transaction+on+neural+networks+and+learning+systems&rft.au=Pham%2C+Phu&rft.au=Bui%2C+Quang-Thinh&rft.au=Thanh+Nguyen%2C+Ngoc&rft.au=Kozma%2C+Robert&rft.date=2025-06-01&rft.issn=2162-237X&rft.eissn=2162-2388&rft.volume=36&rft.issue=6&rft.spage=9758&rft.epage=9776&rft_id=info:doi/10.1109%2FTNNLS.2024.3520147&rft.externalDBID=n%2Fa&rft.externalDocID=10_1109_TNNLS_2024_3520147
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