CA-GNN: A Competence-Aware Graph Neural Network for Semi-Supervised Learning on Streaming Data

One challenge of learning from streaming data is that only a limited number of labeled examples are available, making semi-supervised learning (SSL) algorithms becoming an efficient tool for streaming data mining. Recently, the graph-based SSL algorithms have been proposed to improve SSL performance...

Celý popis

Uložené v:

Podrobná bibliografia
Vydané v:	IEEE transactions on cybernetics Ročník 55; číslo 2; s. 684 - 697
Hlavní autori:	Yu, Hang, Wen, Jiahao, Sun, Yiping, Wei, Xiao, Lu, Jie
Médium:	Journal Article
Jazyk:	English
Vydavateľské údaje:	United States IEEE 01.02.2025
Predmet:	Adaptation models Competence model Concept drift Correlation Data models graph neural network Graph neural networks Heuristic algorithms Reliability Semantics semi-supervised learning (SSL) Semisupervised learning streaming data Streams
ISSN:	2168-2267, 2168-2275, 2168-2275
On-line prístup:	Získať plný text
Tagy:	Pridať tag Žiadne tagy, Buďte prvý, kto otaguje tento záznam!

Abstract	One challenge of learning from streaming data is that only a limited number of labeled examples are available, making semi-supervised learning (SSL) algorithms becoming an efficient tool for streaming data mining. Recently, the graph-based SSL algorithms have been proposed to improve SSL performance because the graph structure can utilize the interactivity between surrounding nodes. However, graph-based SSL algorithms have two main limitations when applied to streaming data. First, not all the labels of the data in the streaming data may be reliable, and direct classification using a graph can lead to suboptimal performance. Second, graph-based SSL algorithms assume the structure of the graph is static, but the learning environment of streaming data is dynamic. Hence, we propose a competence-aware graph neural network (CA-GNN) to deal with these two limitations. Unlike other models, CA-GNN does not directly rely on graph information that could include mislabeled nodes. Instead, a competence model is used to explore latent semantic correlations in the streaming data and capture the reliability for each data. A streaming learning strategy then evolves CA-GNN's parameters to capture the dynamism of the graph sequences. We conducted experiments using seven real datasets and four synthetic datasets, respectively, and compared the outcomes across various methods. The results demonstrate that CA-GNN classifies streaming data more effectively than the state-of-the-art (SOTA) methods.
AbstractList	One challenge of learning from streaming data is that only a limited number of labeled examples are available, making semi-supervised learning (SSL) algorithms becoming an efficient tool for streaming data mining. Recently, the graph-based SSL algorithms have been proposed to improve SSL performance because the graph structure can utilize the interactivity between surrounding nodes. However, graph-based SSL algorithms have two main limitations when applied to streaming data. First, not all the labels of the data in the streaming data may be reliable, and direct classification using a graph can lead to suboptimal performance. Second, graph-based SSL algorithms assume the structure of the graph is static, but the learning environment of streaming data is dynamic. Hence, we propose a competence-aware graph neural network (CA-GNN) to deal with these two limitations. Unlike other models, CA-GNN does not directly rely on graph information that could include mislabeled nodes. Instead, a competence model is used to explore latent semantic correlations in the streaming data and capture the reliability for each data. A streaming learning strategy then evolves CA-GNN's parameters to capture the dynamism of the graph sequences. We conducted experiments using seven real datasets and four synthetic datasets, respectively, and compared the outcomes across various methods. The results demonstrate that CA-GNN classifies streaming data more effectively than the state-of-the-art (SOTA) methods. One challenge of learning from streaming data is that only a limited number of labeled examples are available, making semi-supervised learning (SSL) algorithms becoming an efficient tool for streaming data mining. Recently, the graph-based SSL algorithms have been proposed to improve SSL performance because the graph structure can utilize the interactivity between surrounding nodes. However, graph-based SSL algorithms have two main limitations when applied to streaming data. First, not all the labels of the data in the streaming data may be reliable, and direct classification using a graph can lead to suboptimal performance. Second, graph-based SSL algorithms assume the structure of the graph is static, but the learning environment of streaming data is dynamic. Hence, we propose a competence-aware graph neural network (CA-GNN) to deal with these two limitations. Unlike other models, CA-GNN does not directly rely on graph information that could include mislabeled nodes. Instead, a competence model is used to explore latent semantic correlations in the streaming data and capture the reliability for each data. A streaming learning strategy then evolves CA-GNN's parameters to capture the dynamism of the graph sequences. We conducted experiments using seven real datasets and four synthetic datasets, respectively, and compared the outcomes across various methods. The results demonstrate that CA-GNN classifies streaming data more effectively than the state-of-the-art (SOTA) methods.One challenge of learning from streaming data is that only a limited number of labeled examples are available, making semi-supervised learning (SSL) algorithms becoming an efficient tool for streaming data mining. Recently, the graph-based SSL algorithms have been proposed to improve SSL performance because the graph structure can utilize the interactivity between surrounding nodes. However, graph-based SSL algorithms have two main limitations when applied to streaming data. First, not all the labels of the data in the streaming data may be reliable, and direct classification using a graph can lead to suboptimal performance. Second, graph-based SSL algorithms assume the structure of the graph is static, but the learning environment of streaming data is dynamic. Hence, we propose a competence-aware graph neural network (CA-GNN) to deal with these two limitations. Unlike other models, CA-GNN does not directly rely on graph information that could include mislabeled nodes. Instead, a competence model is used to explore latent semantic correlations in the streaming data and capture the reliability for each data. A streaming learning strategy then evolves CA-GNN's parameters to capture the dynamism of the graph sequences. We conducted experiments using seven real datasets and four synthetic datasets, respectively, and compared the outcomes across various methods. The results demonstrate that CA-GNN classifies streaming data more effectively than the state-of-the-art (SOTA) methods.
Author	Wen, Jiahao Lu, Jie Sun, Yiping Wei, Xiao Yu, Hang
Author_xml	– sequence: 1 givenname: Hang orcidid: 0000-0003-3444-9992 surname: Yu fullname: Yu, Hang email: yuhang@shu.edu.cn organization: School of Computer Engineering and Science, Shanghai University, Shanghai, China – sequence: 2 givenname: Jiahao orcidid: 0000-0001-6550-7927 surname: Wen fullname: Wen, Jiahao email: wenjh@shu.edu.cn organization: School of Computer Engineering and Science, Shanghai University, Shanghai, China – sequence: 3 givenname: Yiping orcidid: 0009-0005-3411-6823 surname: Sun fullname: Sun, Yiping email: syp2021@shu.edu.cn organization: School of Computer Engineering and Science, Shanghai University, Shanghai, China – sequence: 4 givenname: Xiao orcidid: 0000-0002-6258-6129 surname: Wei fullname: Wei, Xiao email: xwei@shu.edu.cn organization: School of Computer Engineering and Science, Shanghai University, Shanghai, China – sequence: 5 givenname: Jie orcidid: 0000-0003-0690-4732 surname: Lu fullname: Lu, Jie email: Jie.Lu@uts.edu.au organization: Australian Artificial Intelligence Institute, University of Technology Sydney, Sydney, NSW, Australia
BackLink	https://www.ncbi.nlm.nih.gov/pubmed/40030368$$D View this record in MEDLINE/PubMed
BookMark	eNp9kE1v1DAQhi3UipbSH4CEkI9csvXXxg63JcBSabUcthy4EE2dMRiSOLUdKv49We22QhywRhqP9bxj6XlGToYwICEvOFtwzqqrm_rL24VgQi2kMlXJlk_IueClKYTQy5PHe6nPyGVKP9h8zPxUmafkTDEmmSzNOflar4r1dvuGrmgd-hEzDhaL1T1EpOsI43e6xSlCN7d8H-JP6kKkO-x9sZtGjL98wpZuEOLgh280DHSXI0K_H95Bhufk1EGX8PLYL8jnD-9v6o_F5tP6ul5tCiuFyEVblcCBCV1yq91cXAku1VJVTN5C5VzLjEXkpkKjK4tOCWMdIErmWgdaXpDXh71jDHcTptz0PlnsOhgwTKmRXJdSMW7UjL46otNtj20zRt9D_N08OJkBfgBsDClFdI8IZ81efbNX3-zVN0f1c0b_k7E-Q_ZhyBF899_ky0PSI-JfP-lSG2XkHxpQj3o
CODEN	ITCEB8
CitedBy_id	crossref_primary_10_1109_TCYB_2025_3587025 crossref_primary_10_1142_S0218126625503670 crossref_primary_10_1016_j_asoc_2025_113422
Cites_doi	10.1109/TCYB.2023.3339242 10.1016/j.artint.2014.01.001 10.1016/j.ins.2019.08.050 10.1109/TSMCA.2007.904745 10.1145/347090.347107 10.1109/TNNLS.2013.2277712 10.1109/TBDATA.2023.3234529 10.1016/j.patcog.2022.109113 10.1109/TCYB.2021.3070420 10.1007/s10994-017-5642-8 10.1016/j.ins.2021.05.057 10.1109/TNNLS.2020.3008445 10.1007/BFb0056334 10.1109/CVPR.2019.00521 10.1109/TCYB.2024.3429459 10.1109/IROS.2018.8593901 10.1109/ICDM.2009.76 10.1007/978-3-642-28931-6_50 10.1109/MCI.2015.2471196 10.1145/3394486.3406474 10.1109/TNNLS.2019.2947658 10.1007/978-1-4419-8020-5 10.1007/s12530-012-9059-0 10.1109/TCYB.2023.3241171 10.1016/j.neucom.2008.06.011 10.1007/978-3-031-01571-7 10.1609/aaai.v37i4.25596 10.1007/s10489-019-01585-3 10.1145/3209978.3210006 10.1007/s10489-018-1149-7 10.1137/1.9781611972771.42 10.1109/TSMC.2023.3293462 10.1109/MSP.2012.2211477 10.1109/CVPR.2019.01157 10.1016/j.ins.2020.03.052 10.1145/3589334.3645453 10.1109/TCYB.2021.3071860 10.1109/TCYB.2021.3054161 10.1007/s10115-011-0447-8 10.1109/IJCNN52387.2021.9533412 10.1016/j.ins.2022.07.022 10.1016/j.ins.2023.119235 10.1109/TCYB.2022.3164696 10.1609/aaai.v34i04.5984 10.1145/3639054 10.1016/j.ins.2021.10.068 10.1609/aaai.v30i1.10283 10.1111/0824-7935.00142
ContentType	Journal Article
DBID	97E RIA RIE AAYXX CITATION NPM 7X8
DOI	10.1109/TCYB.2024.3489605
DatabaseName	IEEE All-Society Periodicals Package (ASPP) 2005–Present IEEE All-Society Periodicals Package (ASPP) 1998–Present IEEE Xplore CrossRef PubMed MEDLINE - Academic
DatabaseTitle	CrossRef PubMed MEDLINE - Academic
DatabaseTitleList	PubMed MEDLINE - Academic
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/IET Electronic Library (IEL) (UW System Shared) 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	Sciences (General)
EISSN	2168-2275
EndPage	697
ExternalDocumentID	40030368 10_1109_TCYB_2024_3489605 10767848
Genre	orig-research Journal Article
GroupedDBID	0R~ 4.4 6IK 97E AAJGR AARMG AASAJ AAWTH ABAZT ABQJQ ABVLG ACIWK AENEX AGQYO AGSQL AHBIQ AKJIK AKQYR ALMA_UNASSIGNED_HOLDINGS ATWAV BEFXN BFFAM BGNUA BKEBE BPEOZ EBS EJD HZ~ IFIPE IPLJI JAVBF M43 O9- OCL PQQKQ RIA RIE RNS AAYXX CITATION NPM 7X8
ID	FETCH-LOGICAL-c322t-d96a1a02761c7fc7f14213454903ba9ffd08cee189e879cef428cfaee30fdfa73
IEDL.DBID	RIE
ISICitedReferencesCount	8
ISICitedReferencesURI	http://www.webofscience.com/api/gateway?GWVersion=2&SrcApp=Summon&SrcAuth=ProQuest&DestLinkType=CitingArticles&DestApp=WOS_CPL&KeyUT=001367308500001&url=https%3A%2F%2Fcvtisr.summon.serialssolutions.com%2F%23%21%2Fsearch%3Fho%3Df%26include.ft.matches%3Dt%26l%3Dnull%26q%3D
ISSN	2168-2267 2168-2275
IngestDate	Thu Oct 02 18:01:00 EDT 2025 Mon Jul 21 05:51:02 EDT 2025 Sat Nov 29 02:02:42 EST 2025 Tue Nov 18 22:23:13 EST 2025 Wed Aug 27 01:53:11 EDT 2025
IsPeerReviewed	true
IsScholarly	true
Issue	2
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-c322t-d96a1a02761c7fc7f14213454903ba9ffd08cee189e879cef428cfaee30fdfa73
Notes	ObjectType-Article-1 SourceType-Scholarly Journals-1 ObjectType-Feature-2 content type line 23
ORCID	0000-0003-0690-4732 0000-0003-3444-9992 0009-0005-3411-6823 0000-0002-6258-6129 0000-0001-6550-7927
PMID	40030368
PQID	3176340184
PQPubID	23479
PageCount	14
ParticipantIDs	ieee_primary_10767848 crossref_primary_10_1109_TCYB_2024_3489605 pubmed_primary_40030368 crossref_citationtrail_10_1109_TCYB_2024_3489605 proquest_miscellaneous_3176340184
PublicationCentury	2000
PublicationDate	2025-02-01
PublicationDateYYYYMMDD	2025-02-01
PublicationDate_xml	– month: 02 year: 2025 text: 2025-02-01 day: 01
PublicationDecade	2020
PublicationPlace	United States
PublicationPlace_xml	– name: United States
PublicationTitle	IEEE transactions on cybernetics
PublicationTitleAbbrev	TCYB
PublicationTitleAlternate	IEEE Trans Cybern
PublicationYear	2025
Publisher	IEEE
Publisher_xml	– name: IEEE
References	ref13 ref57 ref12 ref56 ref15 Wagner (ref53) ref14 ref52 ref11 ref55 ref10 ref54 ref17 ref16 ref19 ref18 Li (ref38) 2023 ref51 ref50 ref46 ref45 ref47 ref42 Kipf (ref37) 2017 ref43 Maas (ref48) ref49 ref8 ref7 Kingma (ref59) 2017 ref4 ref3 ref6 ref5 ref40 ref35 ref34 Aguilar (ref36) 2023 ref31 ref30 ref33 ref32 ref2 ref1 Velivcković (ref44) 2018 ref24 Glorot (ref58) ref23 ref26 ref25 ref20 Smyth (ref41) ref22 ref21 ref28 ref27 ref29 Sharma (ref39) Song (ref9)
References_xml	– ident: ref20 doi: 10.1109/TCYB.2023.3339242 – start-page: 5095 volume-title: Proc. Int. Conf. Mach. Learn. ident: ref53 article-title: Semi-supervised learning on data streams via temporal label propagation – year: 2017 ident: ref37 article-title: Semi-supervised classification with graph convolutional networks publication-title: arXiv:1609.02907 – ident: ref22 doi: 10.1016/j.artint.2014.01.001 – ident: ref4 doi: 10.1016/j.ins.2019.08.050 – ident: ref23 doi: 10.1109/TSMCA.2007.904745 – ident: ref25 doi: 10.1145/347090.347107 – year: 2017 ident: ref59 article-title: Adam: A method for stochastic optimization publication-title: arXiv:1412.6980 – ident: ref50 doi: 10.1109/TNNLS.2013.2277712 – ident: ref16 doi: 10.1109/TBDATA.2023.3234529 – start-page: 1900 volume-title: Proc. 39th Conf. Uncertain. Artif. Intell. ident: ref39 article-title: Efficiently learning the graph for semi-supervised learning – start-page: 249 volume-title: Proc. 13th Int. Conf. Artif. Intell. Stat. ident: ref58 article-title: Understanding the difficulty of training deep feedforward neural networks – start-page: 1 volume-title: Proc. Adv. Neural Inf. Process. Syst. ident: ref9 article-title: Optimal block-wise asymmetric graph construction for graph-based semi-supervised learning – ident: ref18 doi: 10.1016/j.patcog.2022.109113 – ident: ref31 doi: 10.1109/TCYB.2021.3070420 – ident: ref54 doi: 10.1007/s10994-017-5642-8 – ident: ref35 doi: 10.1016/j.ins.2021.05.057 – ident: ref17 doi: 10.1109/TNNLS.2020.3008445 – ident: ref43 doi: 10.1007/BFb0056334 – ident: ref12 doi: 10.1109/CVPR.2019.00521 – ident: ref30 doi: 10.1109/TCYB.2024.3429459 – ident: ref52 doi: 10.1109/IROS.2018.8593901 – ident: ref27 doi: 10.1109/ICDM.2009.76 – ident: ref24 doi: 10.1007/978-3-642-28931-6_50 – ident: ref1 doi: 10.1109/MCI.2015.2471196 – ident: ref13 doi: 10.1145/3394486.3406474 – ident: ref28 doi: 10.1109/TNNLS.2019.2947658 – ident: ref2 doi: 10.1007/978-1-4419-8020-5 – ident: ref3 doi: 10.1007/s12530-012-9059-0 – ident: ref32 doi: 10.1109/TCYB.2023.3241171 – ident: ref40 doi: 10.1016/j.neucom.2008.06.011 – ident: ref11 doi: 10.1007/978-3-031-01571-7 – ident: ref29 doi: 10.1609/aaai.v37i4.25596 – ident: ref5 doi: 10.1007/s10489-019-01585-3 – ident: ref46 doi: 10.1145/3209978.3210006 – ident: ref6 doi: 10.1007/s10489-018-1149-7 – year: 2023 ident: ref36 article-title: The strongly Leibniz property and the Gromov–Hausdorff propinquity publication-title: arXiv:2301.05692 – ident: ref26 doi: 10.1137/1.9781611972771.42 – ident: ref34 doi: 10.1109/TSMC.2023.3293462 – ident: ref49 doi: 10.1109/MSP.2012.2211477 – ident: ref8 doi: 10.1109/CVPR.2019.01157 – start-page: 377 volume-title: Proc. 14th Int. Joint Conf. Artif. Intell. ident: ref41 article-title: Remembering to forget – ident: ref47 doi: 10.1016/j.ins.2020.03.052 – ident: ref10 doi: 10.1145/3589334.3645453 – start-page: 142 volume-title: Proc. 49th Annu. Meeting Assoc. Comput. Linguist., Human Lang. Technol. ident: ref48 article-title: Learning word vectors for sentiment analysis – ident: ref14 doi: 10.1109/TCYB.2021.3071860 – year: 2018 ident: ref44 article-title: Graph attention networks publication-title: arXiv:1710.10903 – year: 2023 ident: ref38 article-title: Learning on graphs with graph convolution – ident: ref21 doi: 10.1109/TCYB.2021.3054161 – ident: ref7 doi: 10.1007/s10115-011-0447-8 – ident: ref56 doi: 10.1109/IJCNN52387.2021.9533412 – ident: ref19 doi: 10.1016/j.ins.2022.07.022 – ident: ref33 doi: 10.1016/j.ins.2023.119235 – ident: ref15 doi: 10.1109/TCYB.2022.3164696 – ident: ref45 doi: 10.1609/aaai.v34i04.5984 – ident: ref57 doi: 10.1145/3639054 – ident: ref51 doi: 10.1016/j.ins.2021.10.068 – ident: ref55 doi: 10.1609/aaai.v30i1.10283 – ident: ref42 doi: 10.1111/0824-7935.00142
SSID	ssj0000816898
Score	2.426197
Snippet	One challenge of learning from streaming data is that only a limited number of labeled examples are available, making semi-supervised learning (SSL) algorithms...
SourceID	proquest pubmed crossref ieee
SourceType	Aggregation Database Index Database Enrichment Source Publisher
StartPage	684
SubjectTerms	Adaptation models Competence model Concept drift Correlation Data models graph neural network Graph neural networks Heuristic algorithms Reliability Semantics semi-supervised learning (SSL) Semisupervised learning streaming data Streams
Title	CA-GNN: A Competence-Aware Graph Neural Network for Semi-Supervised Learning on Streaming Data
URI	https://ieeexplore.ieee.org/document/10767848 https://www.ncbi.nlm.nih.gov/pubmed/40030368 https://www.proquest.com/docview/3176340184
Volume	55
WOSCitedRecordID	wos001367308500001&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/IET Electronic Library (IEL) (UW System Shared) customDbUrl: eissn: 2168-2275 dateEnd: 99991231 omitProxy: false ssIdentifier: ssj0000816898 issn: 2168-2267 databaseCode: RIE dateStart: 20130101 isFulltext: true titleUrlDefault: https://ieeexplore.ieee.org/ providerName: IEEE
link	http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwlV1LSwMxEA5aPHhRq1Xro0TwoEJqdjduEm-12npaBCvUi0uazUrBbksf-vedZGPRg4KwhywkIWQymW8yyTcInWphifa4JFwZSsBCDIgIs5BQxcA4xyxmSrtkEzxJRL8vH_xjdfcWxhjjLp-Zpi26WH421gt7VAYazmFvZWIVrXIel4-1lgcqLoOEy30bQoEArOA-ihlQedlrP9-ANxiyZsQEoParH3bIJVb5HWM6W9PZ_Ocot9CGB5W4Va6CKloxxTaqerWd4TPPLX2-g17aLdJNkmvcwu0lYiatDzU1uGu5q7Fl64C-kvJ6OAZMix_NaEgeFxO7rcxMhj0n6yseF9hGtdXI_tyquaqhp85dr31PfIoFokGT5ySTsQoUuKZxoHkOX8AsxRs4jTQaKJnnGRVgRgMhjeBSmxy8FZ0rYyKaZ7ni0S6qFOPC7CMsw1BCPao4y8HnlgqADtg-mWUDKRhjdUS_JjzVnn_cpsF4S50fQmVqZZRaGaVeRnV0sWwyKck3_qpcs7L4VrEUQx2dfIk1BdWx8RBVmPFilgJ0iiPwLwWMba-U97I1s7tfFIuDX3o9ROuhzQTs7m8focp8ujDHaE2_z4ezaQPWZ1803Pr8BAtM3Ww
linkProvider	IEEE
linkToHtml	http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwlV3dSxwxEB-qLdiXWr_as35E6IMK0exu3CS-nefHlV6Xwp2gLy65bFYE3ZP70H-_k2w89OEKwj5kIQkhk8n8JpP8BuCnkY5oTygqtGUULUSfyriIKdMcjXPKU66NTzYhskxeXam_4bG6fwtjrfWXz-yBK_pYfjEwE3dUhhoucG_lcg4-HnEes_q51vRIxeeQ8NlvYyxQBBYixDEjpg57resT9AdjfpBwibj96I0l8qlVZqNMb23OF985zq_wJcBK0qzXwRJ8sNUyLAXFHZHdwC69twI3rSa9yLJj0iStKWamzWc9tOTCsVcTx9eBfWX1BXGCqJZ07cMd7U4e3cYysgUJrKy3ZFARF9fWD-7nVI_1Klyen_VabRqSLFCDujymhUp1pNE5TSMjSvwi7kje0G1kSV-rsiyYREMaSWWlUMaW6K-YUlubsLIotUjWYL4aVPY7EBXHCusxLXiJXrfSCHXQ-qmi6CvJOW8Ae5nw3AQGcpcI4z73nghTuZNR7mSUBxk1YH_a5LGm3_hf5VUni1cVazE0YOdFrDkqj4uI6MoOJqMcwVOaoIcpcWzfanlPW3O3_yWpXJ_R6zYstHt_OnnnV_b7B3yOXV5gf5t7A-bHw4ndhE_maXw3Gm75VfoPgIffyw
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=CA-GNN%3A+A+Competence-Aware+Graph+Neural+Network+for+Semi-Supervised+Learning+on+Streaming+Data&rft.jtitle=IEEE+transactions+on+cybernetics&rft.au=Yu%2C+Hang&rft.au=Wen%2C+Jiahao&rft.au=Sun%2C+Yiping&rft.au=Wei%2C+Xiao&rft.date=2025-02-01&rft.eissn=2168-2275&rft.volume=PP&rft_id=info:doi/10.1109%2FTCYB.2024.3489605&rft_id=info%3Apmid%2F40030368&rft.externalDocID=40030368
thumbnail_l	http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/lc.gif&issn=2168-2267&client=summon
thumbnail_m	http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/mc.gif&issn=2168-2267&client=summon
thumbnail_s	http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/sc.gif&issn=2168-2267&client=summon