{"id":"https://openalex.org/W4220825043","doi":"https://doi.org/10.1109/tnnls.2022.3157688","title":"Self-Paced Co-Training of Graph Neural Networks for Semi-Supervised Node Classification","display_name":"Self-Paced Co-Training of Graph Neural Networks for Semi-Supervised Node Classification","publication_year":2022,"publication_date":"2022-03-21","ids":{"openalex":"https://openalex.org/W4220825043","doi":"https://doi.org/10.1109/tnnls.2022.3157688","pmid":"https://pubmed.ncbi.nlm.nih.gov/35312623"},"language":"en","primary_location":{"id":"doi:10.1109/tnnls.2022.3157688","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tnnls.2022.3157688","pdf_url":null,"source":{"id":"https://openalex.org/S4210175523","display_name":"IEEE Transactions on Neural Networks and Learning Systems","issn_l":"2162-237X","issn":["2162-237X","2162-2388"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Neural Networks and Learning Systems","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","pubmed"],"open_access":{"is_oa":false,"oa_status":"closed","oa_url":null,"any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":null,"display_name":"Maoguo Gong","orcid":"https://orcid.org/0000-0002-0415-8556"},"institutions":[{"id":"https://openalex.org/I149594827","display_name":"Xidian University","ror":"https://ror.org/05s92vm98","country_code":"CN","type":"education","lineage":["https://openalex.org/I149594827"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Maoguo Gong","raw_affiliation_strings":["School of Electronic Engineering, Xidian University, Xi’an, China"],"raw_orcid":"https://orcid.org/0000-0002-0415-8556","affiliations":[{"raw_affiliation_string":"School of Electronic Engineering, Xidian University, Xi’an, China","institution_ids":["https://openalex.org/I149594827"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Hui Zhou","orcid":"https://orcid.org/0000-0002-0690-7856"},"institutions":[{"id":"https://openalex.org/I149594827","display_name":"Xidian University","ror":"https://ror.org/05s92vm98","country_code":"CN","type":"education","lineage":["https://openalex.org/I149594827"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Hui Zhou","raw_affiliation_strings":["School of Electronic Engineering, Xidian University, Xi’an, China"],"raw_orcid":"https://orcid.org/0000-0002-0690-7856","affiliations":[{"raw_affiliation_string":"School of Electronic Engineering, Xidian University, Xi’an, China","institution_ids":["https://openalex.org/I149594827"]}]},{"author_position":"middle","author":{"id":null,"display_name":"A. K. Qin","orcid":"https://orcid.org/0000-0001-6631-1651"},"institutions":[{"id":"https://openalex.org/I57093077","display_name":"Swinburne University of Technology","ror":"https://ror.org/031rekg67","country_code":"AU","type":"education","lineage":["https://openalex.org/I57093077"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"A. K. Qin","raw_affiliation_strings":["Department of Computing Technologies, Swinburne University of Technology, Melbourne, VIC, Australia"],"raw_orcid":"https://orcid.org/0000-0001-6631-1651","affiliations":[{"raw_affiliation_string":"Department of Computing Technologies, Swinburne University of Technology, Melbourne, VIC, Australia","institution_ids":["https://openalex.org/I57093077"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Wenfeng Liu","orcid":null},"institutions":[{"id":"https://openalex.org/I149594827","display_name":"Xidian University","ror":"https://ror.org/05s92vm98","country_code":"CN","type":"education","lineage":["https://openalex.org/I149594827"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Wenfeng Liu","raw_affiliation_strings":["School of Electronic Engineering, Xidian University, Xi’an, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Electronic Engineering, Xidian University, Xi’an, China","institution_ids":["https://openalex.org/I149594827"]}]},{"author_position":"last","author":{"id":null,"display_name":"Zhongying Zhao","orcid":"https://orcid.org/0000-0002-5880-0225"},"institutions":[{"id":"https://openalex.org/I80143920","display_name":"Shandong University of Science and Technology","ror":"https://ror.org/04gtjhw98","country_code":"CN","type":"education","lineage":["https://openalex.org/I80143920"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhongying Zhao","raw_affiliation_strings":["School of Computer Science and Engineering, Shandong University of Science and Technology, Qingdao, China"],"raw_orcid":"https://orcid.org/0000-0002-5880-0225","affiliations":[{"raw_affiliation_string":"School of Computer Science and Engineering, Shandong University of Science and Technology, Qingdao, China","institution_ids":["https://openalex.org/I80143920"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":5.3798,"has_fulltext":false,"cited_by_count":45,"citation_normalized_percentile":{"value":0.96221029,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":100},"biblio":{"volume":"34","issue":"11","first_page":"9234","last_page":"9247"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11273","display_name":"Advanced Graph Neural Networks","score":0.9821000099182129,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},"topics":[{"id":"https://openalex.org/T11273","display_name":"Advanced Graph Neural Networks","score":0.9821000099182129,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T12292","display_name":"Graph Theory and Algorithms","score":0.0052999998442828655,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T13702","display_name":"Machine Learning in Healthcare","score":0.0010999999940395355,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/training-set","display_name":"Training set","score":0.6481999754905701},{"id":"https://openalex.org/keywords/graph","display_name":"Graph","score":0.5792999863624573},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.5145999789237976},{"id":"https://openalex.org/keywords/labeled-data","display_name":"Labeled data","score":0.46860000491142273},{"id":"https://openalex.org/keywords/node","display_name":"Node (physics)","score":0.4235000014305115},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.4041999876499176},{"id":"https://openalex.org/keywords/data-set","display_name":"Data set","score":0.40400001406669617},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.3912999927997589}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7921000123023987},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.6481999754905701},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.5892000198364258},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5807999968528748},{"id":"https://openalex.org/C132525143","wikidata":"https://www.wikidata.org/wiki/Q141488","display_name":"Graph","level":2,"score":0.5792999863624573},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.5145999789237976},{"id":"https://openalex.org/C2776145971","wikidata":"https://www.wikidata.org/wiki/Q30673951","display_name":"Labeled data","level":2,"score":0.46860000491142273},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.46059998869895935},{"id":"https://openalex.org/C62611344","wikidata":"https://www.wikidata.org/wiki/Q1062658","display_name":"Node (physics)","level":2,"score":0.4235000014305115},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.4041999876499176},{"id":"https://openalex.org/C58489278","wikidata":"https://www.wikidata.org/wiki/Q1172284","display_name":"Data set","level":2,"score":0.40400001406669617},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.3912999927997589},{"id":"https://openalex.org/C67186912","wikidata":"https://www.wikidata.org/wiki/Q367664","display_name":"Data modeling","level":2,"score":0.38440001010894775},{"id":"https://openalex.org/C2777211547","wikidata":"https://www.wikidata.org/wiki/Q17141490","display_name":"Training (meteorology)","level":2,"score":0.3644999861717224},{"id":"https://openalex.org/C24756922","wikidata":"https://www.wikidata.org/wiki/Q1757694","display_name":"Data quality","level":3,"score":0.310699999332428},{"id":"https://openalex.org/C190839683","wikidata":"https://www.wikidata.org/wiki/Q2448197","display_name":"Train","level":2,"score":0.2996000051498413},{"id":"https://openalex.org/C2775924081","wikidata":"https://www.wikidata.org/wiki/Q55608371","display_name":"Control (management)","level":2,"score":0.28690001368522644},{"id":"https://openalex.org/C2984842247","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep neural networks","level":3,"score":0.271699994802475},{"id":"https://openalex.org/C2779530757","wikidata":"https://www.wikidata.org/wiki/Q1207505","display_name":"Quality (philosophy)","level":2,"score":0.2614000141620636},{"id":"https://openalex.org/C16910744","wikidata":"https://www.wikidata.org/wiki/Q7705759","display_name":"Test data","level":2,"score":0.25209999084472656}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/tnnls.2022.3157688","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tnnls.2022.3157688","pdf_url":null,"source":{"id":"https://openalex.org/S4210175523","display_name":"IEEE Transactions on Neural Networks and Learning Systems","issn_l":"2162-237X","issn":["2162-237X","2162-2388"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Neural Networks and Learning Systems","raw_type":"journal-article"},{"id":"pmid:35312623","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/35312623","pdf_url":null,"source":{"id":"https://openalex.org/S4306525036","display_name":"PubMed","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1299303238","host_organization_name":"National Institutes of Health","host_organization_lineage":["https://openalex.org/I1299303238"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE transactions on neural networks and learning systems","raw_type":null}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G1949608614","display_name":null,"funder_award_id":"62036006","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G2159723965","display_name":"Data-driven Traffic Analytics for Incident Analysis and Management","funder_award_id":"LP180100114","funder_id":"https://openalex.org/F4320334704","funder_display_name":"Australian Research Council"},{"id":"https://openalex.org/G3698760113","display_name":"Next-generation Intelligent Explorations of Geo-located Data ","funder_award_id":"DP200102611","funder_id":"https://openalex.org/F4320334704","funder_display_name":"Australian Research Council"},{"id":"https://openalex.org/G8154874561","display_name":"\u590d\u6742\u5c5e\u6027\u7f51\u7edc\u7684\u591a\u89c6\u89d2\u8868\u793a\u5b66\u4e60\u5173\u952e\u6280\u672f\u7814\u7a76","funder_award_id":"62072288","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"},{"id":"https://openalex.org/F4320326185","display_name":"Taishan Scholar Foundation of Shandong Province","ror":null},{"id":"https://openalex.org/F4320334704","display_name":"Australian Research Council","ror":"https://ror.org/05mmh0f86"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":61,"referenced_works":["https://openalex.org/W1888005072","https://openalex.org/W1902027874","https://openalex.org/W1908728294","https://openalex.org/W1983320747","https://openalex.org/W2017475521","https://openalex.org/W2048679005","https://openalex.org/W2079359777","https://openalex.org/W2095727900","https://openalex.org/W2103024562","https://openalex.org/W2103147398","https://openalex.org/W2111700528","https://openalex.org/W2132549764","https://openalex.org/W2133556223","https://openalex.org/W2141125852","https://openalex.org/W2154851992","https://openalex.org/W2165396616","https://openalex.org/W2256388387","https://openalex.org/W2407712691","https://openalex.org/W2411855254","https://openalex.org/W2558460151","https://openalex.org/W2743493499","https://openalex.org/W2751968371","https://openalex.org/W2788730644","https://openalex.org/W2808424844","https://openalex.org/W2808466528","https://openalex.org/W2809001617","https://openalex.org/W2809503262","https://openalex.org/W2907492528","https://openalex.org/W2949435814","https://openalex.org/W2954497554","https://openalex.org/W2962756421","https://openalex.org/W2966567766","https://openalex.org/W2990720125","https://openalex.org/W3006463092","https://openalex.org/W3013514766","https://openalex.org/W3019166713","https://openalex.org/W3046214831","https://openalex.org/W3092206109","https://openalex.org/W3118327669","https://openalex.org/W4210997624","https://openalex.org/W6631190155","https://openalex.org/W6631654266","https://openalex.org/W6636883489","https://openalex.org/W6637178625","https://openalex.org/W6675038308","https://openalex.org/W6675747103","https://openalex.org/W6679390333","https://openalex.org/W6679629151","https://openalex.org/W6680434193","https://openalex.org/W6682691769","https://openalex.org/W6690230747","https://openalex.org/W6699364125","https://openalex.org/W6720006811","https://openalex.org/W6726873649","https://openalex.org/W6738964360","https://openalex.org/W6742630102","https://openalex.org/W6745537798","https://openalex.org/W6748402259","https://openalex.org/W6752110883","https://openalex.org/W6771625333","https://openalex.org/W6776961436"],"related_works":[],"abstract_inverted_index":{"Graph":[0],"neural":[1],"networks":[2],"(GNNs)":[3],"have":[4],"demonstrated":[5],"great":[6],"success":[7],"in":[8,34,116],"many":[9],"graph":[10],"data-based":[11],"applications.":[12],"The":[13],"impressive":[14],"behavior":[15],"of":[16,23,27,40,71,88,92,102,120,174,205,235,253,277],"GNNs":[17,164],"typically":[18],"relies":[19],"on":[20,61,171,238,259,295],"the":[21,68,80,85,93,100,109,117,121,136,152,166,175,187,193,203,216,232,244,254,264,270,274,278,296,302,309],"availability":[22],"a":[24,37,50,62,148,207,220,260,282,286],"sufficient":[25],"amount":[26,70],"labeled":[28,72,190],"data":[29,73,82,104,138,191,196,240],"for":[30,75,134,139,151,156],"model":[31,78],"training.":[32],"However,":[33],"practice,":[35],"obtaining":[36],"large":[38],"number":[39],"annotations":[41],"is":[42,49,212,257,267],"prohibitively":[43],"labor-intensive":[44],"and":[45,192,242,263],"even":[46],"impossible.":[47],"Co-training":[48],"popular":[51],"semi-supervised":[52,157],"learning":[53],"(SSL)":[54],"paradigm,":[55],"which":[56],"trains":[57,162],"multiple":[58,163],"models":[59,115],"based":[60],"common":[63],"training":[64,76,122,137,177,229,239,246,275],"set":[65],"while":[66],"augmenting":[67,135],"limited":[69],"used":[74,133],"each":[77,252],"via":[79],"pseudolabeled":[81,103,195],"generated":[83,112,197,218],"from":[84,198],"prediction":[86],"results":[87,294],"other":[89,140,199],"models.":[90,141],"Most":[91],"existing":[94],"co-training":[95,150],"works":[96],"do":[97],"not":[98],"control":[99,202],"quality":[101,204],"when":[105,130],"using":[106,185],"them.":[107],"Therefore,":[108],"inaccurate":[110,236],"pseudolabels":[111,217,237],"by":[113,184,285],"immature":[114],"early":[118],"stage":[119],"process":[123,247],"are":[124,132],"likely":[125],"to":[126,214,224,290],"cause":[127],"noticeable":[128],"errors":[129],"they":[131],"To":[142,201,272],"address":[143],"this":[144],"issue,":[145],"we":[146,280],"propose":[147],"self-paced":[149,208],"GNN":[153,180,256],"(SPC-GNN)":[154],"framework":[155,161,304],"node":[158,297],"classification.":[159],"This":[160],"with":[165],"same":[167,176],"or":[168],"different":[169,172],"structures":[170],"representations":[173],"data.":[178],"Each":[179],"carries":[181],"out":[182],"SSL":[183,311],"both":[186],"originally":[188],"available":[189],"augmented":[194],"GNNs.":[200,292],"pseudolabels,":[206],"label":[209],"augmentation":[210],"strategy":[211],"designed":[213],"make":[215],"at":[219],"higher":[221],"confidence":[222],"level":[223],"be":[225,249],"utilized":[226],"earlier":[227],"during":[228],"such":[230],"that":[231,301],"negative":[233],"impact":[234],"augmentation,":[241],"accordingly,":[243],"subsequent":[245],"can":[248],"mitigated.":[250],"Finally,":[251],"trained":[255],"evaluated":[258],"validation":[261],"set,":[262],"best-performing":[265],"one":[266],"chosen":[268],"as":[269],"output.":[271],"improve":[273],"effectiveness":[276],"framework,":[279],"devise":[281],"pretraining":[283],"followed":[284],"two-step":[287],"optimization":[288],"scheme":[289],"train":[291],"Experimental":[293],"classification":[298],"task":[299],"demonstrate":[300],"proposed":[303],"achieves":[305],"significant":[306],"improvement":[307],"over":[308],"state-of-the-art":[310],"methods.":[312]},"counts_by_year":[{"year":2026,"cited_by_count":4},{"year":2025,"cited_by_count":17},{"year":2024,"cited_by_count":14},{"year":2023,"cited_by_count":9},{"year":2022,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2022-04-03T00:00:00"}