Graph Neural Networks: Architectures, Stability, and Transferability
Graph neural networks (GNNs) are information processing architectures for signals supported on graphs. They are presented here as generalizations of convolutional neural networks (CNNs) in which individual layers contain banks of graph convolutional filters instead of banks of classical convolutiona...
Saved in:
| Published in: | Proceedings of the IEEE Vol. 109; no. 5; pp. 660 - 682 |
|---|---|
| Main Authors: | , , |
| Format: | Journal Article |
| Language: | English |
| Published: |
New York
IEEE
01.05.2021
The Institute of Electrical and Electronics Engineers, Inc. (IEEE) |
| Subjects: | |
| ISSN: | 0018-9219, 1558-2256 |
| Online Access: | Get full text |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| Abstract | Graph neural networks (GNNs) are information processing architectures for signals supported on graphs. They are presented here as generalizations of convolutional neural networks (CNNs) in which individual layers contain banks of graph convolutional filters instead of banks of classical convolutional filters. Otherwise, GNNs operate as CNNs. Filters are composed of pointwise nonlinearities and stacked in layers. It is shown that GNN architectures exhibit equivariance to permutation and stability to graph deformations. These properties help explain the good performance of GNNs that can be observed empirically. It is also shown that if graphs converge to a limit object, a graphon, GNNs converge to a corresponding limit object, a graphon neural network. This convergence justifies the transferability of GNNs across networks with different numbers of nodes. Concepts are illustrated by the application of GNNs to recommendation systems, decentralized collaborative control, and wireless communication networks. |
|---|---|
| AbstractList | Graph neural networks (GNNs) are information processing architectures for signals supported on graphs. They are presented here as generalizations of convolutional neural networks (CNNs) in which individual layers contain banks of graph convolutional filters instead of banks of classical convolutional filters. Otherwise, GNNs operate as CNNs. Filters are composed of pointwise nonlinearities and stacked in layers. It is shown that GNN architectures exhibit equivariance to permutation and stability to graph deformations. These properties help explain the good performance of GNNs that can be observed empirically. It is also shown that if graphs converge to a limit object, a graphon, GNNs converge to a corresponding limit object, a graphon neural network. This convergence justifies the transferability of GNNs across networks with different numbers of nodes. Concepts are illustrated by the application of GNNs to recommendation systems, decentralized collaborative control, and wireless communication networks. |
| Author | Gama, Fernando Ruiz, Luana Ribeiro, Alejandro |
| Author_xml | – sequence: 1 givenname: Luana orcidid: 0000-0002-9666-1211 surname: Ruiz fullname: Ruiz, Luana email: rubruiz@seas.upenn.edu organization: Department of Electrical and Systems Engineering, University of Pennsylvania, Philadelphia, PA, USA – sequence: 2 givenname: Fernando orcidid: 0000-0001-6117-8193 surname: Gama fullname: Gama, Fernando email: fgama@berkeley.edu organization: Electrical Engineering and Computer Sciences Department, University of California at Berkeley, Berkeley, CA, USA – sequence: 3 givenname: Alejandro orcidid: 0000-0003-4230-9906 surname: Ribeiro fullname: Ribeiro, Alejandro email: aribeiro@seas.upenn.edu organization: Department of Electrical and Systems Engineering, University of Pennsylvania, Philadelphia, PA, USA |
| BookMark | eNp9kEFLw0AQhRepYFv9A3oJeG3qzG42yXorVatSrGg9h00yoakxqbsbpP_e1BYPHjw9GN73Br4B69VNTYydI4wRQV09Pr8spmMOHMcCpAwAjlgfpYx9zmXYY30AjH3FUZ2wgbVrABAyFH12MzN6s_KeqDW66sJ9NebdXnsTk61KR5lrDdmR9-p0Wlal2448Xefe0ujaFmQOx1N2XOjK0tkhh-zt7nY5vffni9nDdDL3M66k8wlRRXmhA5lFeRpBqgWiJJRBXMQ5FxRkIUmRYxgFgaQgopCLUBGmIAHiWAzZ5X53Y5rPlqxL1k1r6u5lwiUqFUGsVNeK963MNNYaKpKsdNqVTe2MLqsEIdk5S36cJTtnycFZh_I_6MaUH9ps_4cu9lBJRL-A6vwiD8U3UPR4gA |
| CODEN | IEEPAD |
| CitedBy_id | crossref_primary_10_1109_TSP_2023_3324221 crossref_primary_10_1109_TSP_2025_3534685 crossref_primary_10_1016_j_acha_2025_101773 crossref_primary_10_1016_j_dsp_2024_104528 crossref_primary_10_1016_j_ejor_2025_04_018 crossref_primary_10_1109_TSP_2021_3106857 crossref_primary_10_1109_MSP_2023_3262906 crossref_primary_10_1016_j_ins_2023_119001 crossref_primary_10_1109_LRA_2023_3280806 crossref_primary_10_1155_2021_5100809 crossref_primary_10_1109_TIM_2025_3545526 crossref_primary_10_1137_24M1651526 crossref_primary_10_1109_TSP_2022_3192606 crossref_primary_10_3390_su16219239 crossref_primary_10_1109_TSIPN_2021_3139336 crossref_primary_10_1109_TSP_2022_3223217 crossref_primary_10_2174_0115748936289520240828050951 crossref_primary_10_1109_TSP_2024_3378379 crossref_primary_10_1016_j_inffus_2022_11_018 crossref_primary_10_3390_app132212421 crossref_primary_10_1016_j_segan_2024_101469 crossref_primary_10_1109_TCCN_2024_3360517 crossref_primary_10_1109_TIM_2023_3241976 crossref_primary_10_1109_TSP_2023_3256536 crossref_primary_10_1109_JSTSP_2024_3350508 crossref_primary_10_1016_j_acha_2022_11_008 crossref_primary_10_1016_j_compchemeng_2023_108403 crossref_primary_10_1109_JIOT_2025_3547422 crossref_primary_10_1155_2021_9923364 crossref_primary_10_1109_TSP_2023_3300632 crossref_primary_10_1109_TWC_2022_3204794 crossref_primary_10_1109_ACCESS_2021_3084599 crossref_primary_10_1109_TSP_2022_3166401 crossref_primary_10_1109_ACCESS_2023_3269297 crossref_primary_10_1109_TPAMI_2023_3311912 crossref_primary_10_1109_TSP_2022_3159393 crossref_primary_10_1088_1361_6501_ad73fa crossref_primary_10_1007_s43154_021_00046_5 crossref_primary_10_1016_j_comcom_2021_12_015 crossref_primary_10_1016_j_ins_2024_120422 crossref_primary_10_1109_JPROC_2024_3369017 crossref_primary_10_1109_TSP_2023_3340009 crossref_primary_10_1007_s13042_023_01822_9 crossref_primary_10_1016_j_engappai_2024_108959 crossref_primary_10_1109_TCSS_2023_3312395 crossref_primary_10_1016_j_comnet_2022_109358 crossref_primary_10_1016_j_epsr_2023_109903 crossref_primary_10_1016_j_apacoust_2024_109929 crossref_primary_10_1109_TAI_2025_3550458 crossref_primary_10_1051_ita_2024014 crossref_primary_10_1109_TSG_2023_3239740 crossref_primary_10_3390_sym15020535 crossref_primary_10_1007_s41109_021_00438_8 crossref_primary_10_1631_FITEE_2300009 crossref_primary_10_1002_aisy_202300036 crossref_primary_10_1109_JSAC_2023_3242703 crossref_primary_10_1007_s10479_023_05623_9 crossref_primary_10_1016_j_knosys_2024_112311 crossref_primary_10_1109_TSIPN_2023_3239695 crossref_primary_10_1109_TSP_2024_3349788 |
| Cites_doi | 10.1109/JPROC.2018.2820126 10.1109/TSP.2016.2614793 10.1007/978-3-319-66182-7_54 10.1109/DSW.2018.8439904 10.1145/3328526.3329638 10.1093/biomet/20A.1-2.32 10.1016/j.acha.2010.04.005 10.1002/cpa.21413 10.1007/978-3-030-03574-7_9 10.1109/TSP.2015.2424203 10.1109/TNSE.2018.2884235 10.4007/annals.2012.176.1.2 10.1016/j.acha.2019.06.003 10.1109/CDC.2003.1272911 10.1109/ICASSP.2011.5946304 10.1109/TSP.2017.2703660 10.1109/TSP.2018.2864654 10.1109/ICASSP.2019.8682836 10.1145/2827872 10.1109/MSP.2020.3014594 10.1016/j.crhy.2019.08.003 10.1016/B978-0-12-813677-5.00011-0 10.1109/TSP.2020.3033962 10.1137/1.9781611970104 10.1109/TSP.2020.3026980 10.1109/WI.2005.67 10.1109/CVPR.2019.00943 10.1109/TSP.2019.2904925 10.1109/ICASSP40776.2020.9054357 10.1109/TSP.2013.2238935 10.1007/978-3-030-04167-0_33 10.1109/TSP.2020.2988255 10.1109/MSP.2012.2235192 10.1109/TSP.2014.2321121 10.1109/TSP.2019.2955832 10.23919/EUSIPCO.2017.8081230 10.1109/TSP.2018.2887403 10.1109/ICASSP40776.2020.9053140 10.1145/3219819.3219890 10.1109/LRA.2019.2903261 |
| ContentType | Journal Article |
| Copyright | Copyright The Institute of Electrical and Electronics Engineers, Inc. (IEEE) 2021 |
| Copyright_xml | – notice: Copyright The Institute of Electrical and Electronics Engineers, Inc. (IEEE) 2021 |
| DBID | 97E RIA RIE AAYXX CITATION 7SP 8FD L7M |
| DOI | 10.1109/JPROC.2021.3055400 |
| DatabaseName | IEEE Xplore (IEEE) IEEE All-Society Periodicals Package (ASPP) 1998–Present IEEE Electronic Library (IEL) CrossRef Electronics & Communications Abstracts Technology Research Database Advanced Technologies Database with Aerospace |
| DatabaseTitle | CrossRef Technology Research Database Advanced Technologies Database with Aerospace Electronics & Communications Abstracts |
| DatabaseTitleList | Technology Research Database |
| Database_xml | – sequence: 1 dbid: RIE name: IEEE Electronic Library (IEL) url: https://ieeexplore.ieee.org/ sourceTypes: Publisher |
| DeliveryMethod | fulltext_linktorsrc |
| Discipline | Engineering |
| EISSN | 1558-2256 |
| EndPage | 682 |
| ExternalDocumentID | 10_1109_JPROC_2021_3055400 9356126 |
| Genre | orig-research |
| GrantInformation_xml | – fundername: NSF HDR TRIPODS grantid: #1934960 |
| GroupedDBID | -DZ -~X .DC 0R~ 123 1OL 29P 3EH 4.4 6IK 85S 97E 9M8 AAJGR AAWTH ABAZT ABFSI ABJNI ABQJQ ABVLG ACBEA ACGFS AENEX AETEA AETIX AFOGA AGNAY AGQYO AGSQL AHBIQ AIBXA ALLEH ALMA_UNASSIGNED_HOLDINGS AZLTO BEFXN BFFAM BGNUA BKEBE BPEOZ CS3 DU5 EBS EJD FA8 HZ~ H~9 IAAWW IBMZZ ICLAB IDIHD IFIPE IFJZH IPLJI JAVBF LAI M43 MVM O9- OCL RIA RIE RIU RNS TAE TN5 TWZ UDY UHB UKR UQL VOH WHG XJT XOL YNT ZCA ZXP ZY4 ~02 AAYXX CITATION 7SP 8FD L7M |
| ID | FETCH-LOGICAL-c295t-e1197dfa45c7db70ba3115e1548f8d23e4c6e53d167445e47e62369e1b0500883 |
| IEDL.DBID | RIE |
| ISICitedReferencesCount | 90 |
| ISICitedReferencesURI | http://www.webofscience.com/api/gateway?GWVersion=2&SrcApp=Summon&SrcAuth=ProQuest&DestLinkType=CitingArticles&DestApp=WOS_CPL&KeyUT=000645896700004&url=https%3A%2F%2Fcvtisr.summon.serialssolutions.com%2F%23%21%2Fsearch%3Fho%3Df%26include.ft.matches%3Dt%26l%3Dnull%26q%3D |
| ISSN | 0018-9219 |
| IngestDate | Sun Oct 05 00:12:14 EDT 2025 Sat Nov 29 06:01:43 EST 2025 Tue Nov 18 21:14:42 EST 2025 Wed Aug 27 02:29:30 EDT 2025 |
| IsPeerReviewed | true |
| IsScholarly | true |
| Issue | 5 |
| Language | English |
| License | https://doi.org/10.15223/policy-029 https://doi.org/10.15223/policy-037 |
| LinkModel | DirectLink |
| MergedId | FETCHMERGED-LOGICAL-c295t-e1197dfa45c7db70ba3115e1548f8d23e4c6e53d167445e47e62369e1b0500883 |
| Notes | ObjectType-Article-1 SourceType-Scholarly Journals-1 ObjectType-Feature-2 content type line 14 |
| ORCID | 0000-0003-4230-9906 0000-0002-9666-1211 0000-0001-6117-8193 |
| PQID | 2519970899 |
| PQPubID | 85453 |
| PageCount | 23 |
| ParticipantIDs | crossref_primary_10_1109_JPROC_2021_3055400 proquest_journals_2519970899 crossref_citationtrail_10_1109_JPROC_2021_3055400 ieee_primary_9356126 |
| PublicationCentury | 2000 |
| PublicationDate | 2021-05-01 |
| PublicationDateYYYYMMDD | 2021-05-01 |
| PublicationDate_xml | – month: 05 year: 2021 text: 2021-05-01 day: 01 |
| PublicationDecade | 2020 |
| PublicationPlace | New York |
| PublicationPlace_xml | – name: New York |
| PublicationTitle | Proceedings of the IEEE |
| PublicationTitleAbbrev | JPROC |
| PublicationYear | 2021 |
| Publisher | IEEE The Institute of Electrical and Electronics Engineers, Inc. (IEEE) |
| Publisher_xml | – name: IEEE – name: The Institute of Electrical and Electronics Engineers, Inc. (IEEE) |
| References | ref57 xu (ref27) 2019 ref56 ref12 ref59 ref58 ref14 ref53 ref55 ref11 gama (ref42) 2019 ref17 ref18 monti (ref6) 2017 wang (ref35) 2020 ruiz (ref50) 2020 ruiz (ref40) 2020 ref51 veli?kovi? (ref28) 2018 ref46 li (ref9) 2020 ref48 ref41 tolstaya (ref7) 2019; 100 kipf (ref15) 2017 defferrard (ref3) 2016 ref49 ref8 boukli hacene (ref34) 2019 ref4 ref5 assran (ref19) 2020 bishop (ref68) 2006 ref36 ref31 ref30 ref33 duvenaud (ref54) 2015 lovász (ref45) 2012; 60 ref39 ref38 lax (ref69) 2002 chen (ref43) 2019 bresson (ref32) 2017 isufi (ref16) 2020 joachims (ref1) 1997 ref71 du (ref25) 2017 ref70 oppenheim (ref63) 2010 ref24 ref67 ref23 ref26 ref64 ref66 ref22 levie (ref52) 2019 ref65 ref21 goodfellow (ref10) 2016 kingma (ref20) 2015 li (ref37) 2018 ref29 mikolov (ref2) 2013 bruna (ref13) 2014 vignac (ref44) 2020 ref60 wolfe (ref47) 2013 ref62 ref61 |
| References_xml | – start-page: 3697 year: 2017 ident: ref6 article-title: Geometric matrix completion with recurrent multi-graph neural networks publication-title: Proc 31st Conf Neural Inf Process Syst – ident: ref22 doi: 10.1109/JPROC.2018.2820126 – ident: ref23 doi: 10.1109/TSP.2016.2614793 – ident: ref53 doi: 10.1007/978-3-319-66182-7_54 – start-page: 1 year: 2018 ident: ref28 article-title: Graph attention networks publication-title: Proc Int Conf Learn Represent (ICLR) – ident: ref26 doi: 10.1109/DSW.2018.8439904 – ident: ref49 doi: 10.1145/3328526.3329638 – ident: ref67 doi: 10.1093/biomet/20A.1-2.32 – ident: ref65 doi: 10.1016/j.acha.2010.04.005 – ident: ref18 doi: 10.1002/cpa.21413 – volume: 60 year: 2012 ident: ref45 publication-title: Large Networks and Graph Limits – ident: ref60 doi: 10.1007/978-3-030-03574-7_9 – ident: ref66 doi: 10.1109/TSP.2015.2424203 – ident: ref48 doi: 10.1109/TNSE.2018.2884235 – year: 2010 ident: ref63 publication-title: Discrete-Time Signal Processing – ident: ref46 doi: 10.4007/annals.2012.176.1.2 – ident: ref41 doi: 10.1016/j.acha.2019.06.003 – ident: ref70 doi: 10.1109/CDC.2003.1272911 – start-page: 2224 year: 2015 ident: ref54 article-title: Convolutional networks on graphs for learning molecular fingerprints publication-title: Proc Adv Neural Inf Process Syst – ident: ref71 doi: 10.1109/ICASSP.2011.5946304 – start-page: 143 year: 1997 ident: ref1 article-title: A probabilistic analysis of the Rocchio algorithm with TFIDF for text categorization publication-title: Proc 14th Int Conf Mach Learn – start-page: 1 year: 2014 ident: ref13 article-title: Spectral networks and deep locally connected networks on graphs publication-title: Proc 2nd Int Conf Learn Represent – ident: ref12 doi: 10.1109/TSP.2017.2703660 – ident: ref4 doi: 10.1109/TSP.2018.2864654 – year: 2019 ident: ref34 article-title: Attention based pruning for shift networks publication-title: arXiv 1905 12300 – year: 2017 ident: ref32 article-title: Residual gated graph ConvNets publication-title: arXiv 1711 07553 – ident: ref31 doi: 10.1109/ICASSP.2019.8682836 – ident: ref17 doi: 10.1145/2827872 – ident: ref59 doi: 10.1109/MSP.2020.3014594 – ident: ref62 doi: 10.1016/j.crhy.2019.08.003 – start-page: 1 year: 2017 ident: ref15 article-title: Semi-supervised classification with graph convolutional networks publication-title: Proc Int Conf Learn Represent (ICLR) – ident: ref24 doi: 10.1016/B978-0-12-813677-5.00011-0 – ident: ref30 doi: 10.1109/TSP.2020.3033962 – ident: ref64 doi: 10.1137/1.9781611970104 – ident: ref39 doi: 10.1109/TSP.2020.3026980 – year: 2020 ident: ref35 article-title: Direct multi-hop attention based graph neural network publication-title: arXiv 2009 14332 – start-page: 1 year: 2020 ident: ref9 article-title: Graph neural networks for decentralized multi-robot path planning publication-title: Proc IEEE/RSJ Int Conf Intell Robots and Syst – ident: ref55 doi: 10.1109/WI.2005.67 – year: 2019 ident: ref52 article-title: Transferability of spectral graph convolutional neural networks publication-title: arXiv 1907 12972 – start-page: 1 year: 2020 ident: ref19 article-title: On the convergence of Nesterov's accelerated gradient method in stochastic settings publication-title: Proc 37th Int Conf Mach Learn – year: 2006 ident: ref68 publication-title: Pattern Recognition and Machine Learning – ident: ref36 doi: 10.1109/CVPR.2019.00943 – year: 2002 ident: ref69 publication-title: Functional Analysis – year: 2016 ident: ref10 publication-title: Deep Learning – ident: ref33 doi: 10.1109/TSP.2019.2904925 – start-page: 3844 year: 2016 ident: ref3 article-title: Convolutional neural networks on graphs with fast localized spectral filtering publication-title: Proc 30th Conf Neural Inf Process Syst – ident: ref56 doi: 10.1109/ICASSP40776.2020.9054357 – start-page: 1 year: 2020 ident: ref44 article-title: Building powerful and equivariant graph neural networks with message-passing publication-title: Proc 34th Conf Neural Inf Process Syst – start-page: 1 year: 2020 ident: ref40 article-title: Graphon neural networks and the transferability of graph neural networks publication-title: Proc 34th Conf Neural Inf Process Syst – year: 2020 ident: ref50 article-title: Graphon signal processing publication-title: arXiv 2003 05030 – start-page: 1 year: 2019 ident: ref27 article-title: How powerful are graph neural networks? publication-title: Proc 7th Int Conf Learn Represent – ident: ref11 doi: 10.1109/TSP.2013.2238935 – start-page: 1 year: 2015 ident: ref20 article-title: Adam: A method for stochastic optimization publication-title: Proc Int Conf Learn Represent – ident: ref38 doi: 10.1007/978-3-030-04167-0_33 – start-page: 1 year: 2018 ident: ref37 article-title: Diffusion convolutional recurrent neural network: Data-driven traffic forecasting publication-title: Proc 6th Int Conf Learn Represent – year: 2017 ident: ref25 article-title: Topology adaptive graph convolutional networks publication-title: arXiv 1710 10370 – ident: ref58 doi: 10.1109/TSP.2020.2988255 – ident: ref21 doi: 10.1109/MSP.2012.2235192 – year: 2020 ident: ref16 article-title: EdgeNets: Edge varying graph neural networks publication-title: arXiv 2001 07620 – year: 2013 ident: ref47 article-title: Nonparametric graphon estimation publication-title: arXiv 1309 5936 – ident: ref61 doi: 10.1109/TSP.2014.2321121 – ident: ref29 doi: 10.1109/TSP.2019.2955832 – ident: ref51 doi: 10.23919/EUSIPCO.2017.8081230 – start-page: 1 year: 2019 ident: ref42 article-title: Diffusion scattering transforms on graphs publication-title: Proc 7th Int Conf Learn Represent – start-page: 1 year: 2013 ident: ref2 article-title: Efficient estimation of word representations in vector space publication-title: Proc 1st Int Conf Learn Represent – ident: ref14 doi: 10.1109/TSP.2018.2887403 – ident: ref57 doi: 10.1109/ICASSP40776.2020.9053140 – ident: ref5 doi: 10.1145/3219819.3219890 – ident: ref8 doi: 10.1109/LRA.2019.2903261 – volume: 100 start-page: 1 year: 2019 ident: ref7 article-title: Learning decentralized controllers for robot swarms with graph neural networks publication-title: Proc Conf Robot Learn – start-page: 1 year: 2019 ident: ref43 article-title: On the equivalence between graph isomorphism testing and function approximation with GNNs publication-title: Proc 33rd Conf Neural Inf Process Syst |
| SSID | ssj0003563 |
| Score | 2.6755655 |
| Snippet | Graph neural networks (GNNs) are information processing architectures for signals supported on graphs. They are presented here as generalizations of... |
| SourceID | proquest crossref ieee |
| SourceType | Aggregation Database Enrichment Source Index Database Publisher |
| StartPage | 660 |
| SubjectTerms | Artificial neural networks Communication networks Convergence Convolutional neural networks Data processing Deep learning Equivariance Filter banks graph filters Graph neural networks graph neural networks (GNNs) graph signal processing (GSP) graphon neural networks graphons Graphs Information filters Information processing Neural networks Permutations Probability distribution Recommender systems Signal processing Stability Stability analysis Training data transferability Wireless communications Wireless networks |
| Title | Graph Neural Networks: Architectures, Stability, and Transferability |
| URI | https://ieeexplore.ieee.org/document/9356126 https://www.proquest.com/docview/2519970899 |
| Volume | 109 |
| WOSCitedRecordID | wos000645896700004&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: 1558-2256 dateEnd: 99991231 omitProxy: false ssIdentifier: ssj0003563 issn: 0018-9219 databaseCode: RIE dateStart: 19630101 isFulltext: true titleUrlDefault: https://ieeexplore.ieee.org/ providerName: IEEE |
| link | http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwlV3dS8NADA_b8EEf_JridEoffHPd-nHX6_k21Ck-zCEKeyvtNQeCbLJugv-9l2tXBorgW2mTUnLNJbkkvwBcaullxk0WLhpv3GVp7Lkx14FrYueMoUxDFSs7bEKMx_F0KicN6NW9MIhoi8-wT5c2l5_P1YqOygYypFmOUROaQkRlr1a965pHZTbZNwps1HDdIOPJwePk-enGhIKB3yd8K0bdbBtGyE5V-bEVW_sy2vvfl-3DbuVHOsNy4Q-ggbND2NlAF2zD7T2BUTsEv2Eox2W9d3HtDDdyB0XPMe6mLZD96jnpLHes8dK4qG4ewevo7uXmwa2GJrgqkHzpIuUFc50yrkSeCS9LCU8HKTLRcR6EyFSEPMyp-4BxZAKNAxRJ9DOPG38gDo-hNZvP8ASclPsRskhp9ELClJSah4ZF6MxXAcZBB_y1FBNVIYrTYIv3xEYWnkys5BOSfFJJvgNXNc9HiafxJ3WbZF1TVmLuQHe9WEmlckVCLbhSUBbz9HeuM9imd5fVil1oLRcrPIct9bl8KxYX9m_6BvvWxMw |
| linkProvider | IEEE |
| linkToHtml | http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwlV3dS8NADA9zCuqDX1OcTu2Db65bv67t-Tamc-qsQybsrbTXFATpZB-C_72Xa1cGiuBbaRNacs0luSS_AFym3Iilm-zpKL1x3Yl8Q_dZaukydo4d5JEtfKGGTXhB4I_HfFiBZtkLg4iq-AxbdKly-clELOiorM1tmuXorsE6Tc5iebdWue_Kh3k-2ZQqLBVx2SJj8PbD8OW5K4NBy2wRwpVD_WwrZkjNVfmxGSsL09v937ftwU7hSWqdfOn3oYLZAWyv4AvW4OaO4Kg1AuCQlEFe8T271jor2YNZU5MOpyqR_WpqUZZoynylOC1uHsJr73bU7evF2ARdWJzNdaTMYJJGDhNeEntGHBGiDlJskvqJZaMjXGR2Qv0HDkPHQ-kCuRzN2GDSI_DtI6hmkwyPQYuY6aLjihQNm1AlecpsyeKlsSks9K06mEsphqLAFKfRFu-hii0MHirJhyT5sJB8Ha5Kno8cUeNP6hrJuqQsxFyHxnKxwkLpZiE14XKP8pgnv3NdwGZ_9DQIB_fB4yls0Xvy2sUGVOfTBZ7Bhvicv82m5-rP-gZvksgX |
| 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+Neural+Networks%3A+Architectures%2C+Stability%2C+and+Transferability&rft.jtitle=Proceedings+of+the+IEEE&rft.au=Ruiz%2C+Luana&rft.au=Gama%2C+Fernando&rft.au=Ribeiro%2C+Alejandro&rft.date=2021-05-01&rft.pub=The+Institute+of+Electrical+and+Electronics+Engineers%2C+Inc.+%28IEEE%29&rft.issn=0018-9219&rft.eissn=1558-2256&rft.volume=109&rft.issue=5&rft.spage=660&rft_id=info:doi/10.1109%2FJPROC.2021.3055400&rft.externalDBID=NO_FULL_TEXT |
| thumbnail_l | http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/lc.gif&issn=0018-9219&client=summon |
| thumbnail_m | http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/mc.gif&issn=0018-9219&client=summon |
| thumbnail_s | http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/sc.gif&issn=0018-9219&client=summon |