{"id":"https://openalex.org/W4416251316","doi":"https://doi.org/10.1109/ijcnn64981.2025.11227761","title":"Semi-GD: Graph-Level Consistency Regularization and Dynamic Threshold Boosted Semi-Supervised Learning","display_name":"Semi-GD: Graph-Level Consistency Regularization and Dynamic Threshold Boosted Semi-Supervised Learning","publication_year":2025,"publication_date":"2025-06-30","ids":{"openalex":"https://openalex.org/W4416251316","doi":"https://doi.org/10.1109/ijcnn64981.2025.11227761"},"language":null,"primary_location":{"id":"doi:10.1109/ijcnn64981.2025.11227761","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ijcnn64981.2025.11227761","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 International Joint Conference on Neural Networks (IJCNN)","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":false,"oa_status":"closed","oa_url":null,"any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5017425837","display_name":"RuiXue Wang","orcid":null},"institutions":[{"id":"https://openalex.org/I34949971","display_name":"University of Jinan","ror":"https://ror.org/02mjz6f26","country_code":"CN","type":"education","lineage":["https://openalex.org/I34949971"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"RuiXue Wang","raw_affiliation_strings":["University of Jinan,School of Information Science and Engineering,Jinan,China"],"affiliations":[{"raw_affiliation_string":"University of Jinan,School of Information Science and Engineering,Jinan,China","institution_ids":["https://openalex.org/I34949971"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5001075168","display_name":"Lizhi Peng","orcid":"https://orcid.org/0000-0002-6009-522X"},"institutions":[{"id":"https://openalex.org/I4210136793","display_name":"Peng Cheng Laboratory","ror":"https://ror.org/03qdqbt06","country_code":"CN","type":"facility","lineage":["https://openalex.org/I4210136793"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"LiZhi Peng","raw_affiliation_strings":["Quan Cheng Laboratory,Jinan,China"],"affiliations":[{"raw_affiliation_string":"Quan Cheng Laboratory,Jinan,China","institution_ids":["https://openalex.org/I4210136793"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5065624542","display_name":"Shengbao Li","orcid":null},"institutions":[{"id":"https://openalex.org/I4210087772","display_name":"National Computer Network Emergency Response Technical Team/Coordination Center of Chinar","ror":"https://ror.org/00247dh76","country_code":"CN","type":"nonprofit","lineage":["https://openalex.org/I4210087772"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"ShengBao Li","raw_affiliation_strings":["Shandong Branch of National Computer Network Emergency Response Technical,Jinan,China"],"affiliations":[{"raw_affiliation_string":"Shandong Branch of National Computer Network Emergency Response Technical,Jinan,China","institution_ids":["https://openalex.org/I4210087772"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101715291","display_name":"Kun Zhao","orcid":"https://orcid.org/0000-0002-8483-2511"},"institutions":[{"id":"https://openalex.org/I4210144143","display_name":"Inspur (China)","ror":"https://ror.org/0474p4r72","country_code":"CN","type":"company","lineage":["https://openalex.org/I4210144143"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Kun Zhao","raw_affiliation_strings":["Inspur Comouter Technology Co., Ltd,Jinan,China"],"affiliations":[{"raw_affiliation_string":"Inspur Comouter Technology Co., Ltd,Jinan,China","institution_ids":["https://openalex.org/I4210144143"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5102806557","display_name":"Hua Yang","orcid":"https://orcid.org/0000-0002-2916-3861"},"institutions":[{"id":"https://openalex.org/I4210110931","display_name":"Jinan Institute of Quantum Technology","ror":"https://ror.org/02557nd11","country_code":"CN","type":"facility","lineage":["https://openalex.org/I4210110931"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"HuaWei Yang","raw_affiliation_strings":["Jinan Bosai Network Technology Co., Ltd,Jinan,China"],"affiliations":[{"raw_affiliation_string":"Jinan Bosai Network Technology Co., Ltd,Jinan,China","institution_ids":["https://openalex.org/I4210110931"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5017425837"],"corresponding_institution_ids":["https://openalex.org/I34949971"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.19462574,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"8"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11273","display_name":"Advanced Graph Neural Networks","score":0.48660001158714294,"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":0.48660001158714294,"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":0.11559999734163284,"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/T11719","display_name":"Data Quality and Management","score":0.08460000157356262,"subfield":{"id":"https://openalex.org/subfields/1803","display_name":"Management Science and Operations Research"},"field":{"id":"https://openalex.org/fields/18","display_name":"Decision Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/regularization","display_name":"Regularization (linguistics)","score":0.6212000250816345},{"id":"https://openalex.org/keywords/thresholding","display_name":"Thresholding","score":0.5914000272750854},{"id":"https://openalex.org/keywords/graph","display_name":"Graph","score":0.5009999871253967},{"id":"https://openalex.org/keywords/consistency","display_name":"Consistency (knowledge bases)","score":0.477400004863739},{"id":"https://openalex.org/keywords/matching","display_name":"Matching (statistics)","score":0.40560001134872437},{"id":"https://openalex.org/keywords/local-consistency","display_name":"Local consistency","score":0.3472000062465668},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.33090001344680786},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.32420000433921814}],"concepts":[{"id":"https://openalex.org/C2776135515","wikidata":"https://www.wikidata.org/wiki/Q17143721","display_name":"Regularization (linguistics)","level":2,"score":0.6212000250816345},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5934000015258789},{"id":"https://openalex.org/C191178318","wikidata":"https://www.wikidata.org/wiki/Q2256906","display_name":"Thresholding","level":3,"score":0.5914000272750854},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5182999968528748},{"id":"https://openalex.org/C132525143","wikidata":"https://www.wikidata.org/wiki/Q141488","display_name":"Graph","level":2,"score":0.5009999871253967},{"id":"https://openalex.org/C2776436953","wikidata":"https://www.wikidata.org/wiki/Q5163215","display_name":"Consistency (knowledge bases)","level":2,"score":0.477400004863739},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.42879998683929443},{"id":"https://openalex.org/C165064840","wikidata":"https://www.wikidata.org/wiki/Q1321061","display_name":"Matching (statistics)","level":2,"score":0.40560001134872437},{"id":"https://openalex.org/C137105694","wikidata":"https://www.wikidata.org/wiki/Q3407510","display_name":"Local consistency","level":4,"score":0.3472000062465668},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.33309999108314514},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.33090001344680786},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.32420000433921814},{"id":"https://openalex.org/C115178988","wikidata":"https://www.wikidata.org/wiki/Q772067","display_name":"Laplacian matrix","level":3,"score":0.321399986743927},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.3167000114917755},{"id":"https://openalex.org/C192209626","wikidata":"https://www.wikidata.org/wiki/Q190909","display_name":"Focus (optics)","level":2,"score":0.3122999966144562},{"id":"https://openalex.org/C58973888","wikidata":"https://www.wikidata.org/wiki/Q1041418","display_name":"Semi-supervised learning","level":2,"score":0.302700012922287},{"id":"https://openalex.org/C2776145971","wikidata":"https://www.wikidata.org/wiki/Q30673951","display_name":"Labeled data","level":2,"score":0.2996000051498413},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.29120001196861267},{"id":"https://openalex.org/C93361087","wikidata":"https://www.wikidata.org/wiki/Q4426698","display_name":"Data consistency","level":2,"score":0.28630000352859497},{"id":"https://openalex.org/C67186912","wikidata":"https://www.wikidata.org/wiki/Q367664","display_name":"Data modeling","level":2,"score":0.2838999927043915},{"id":"https://openalex.org/C2780586882","wikidata":"https://www.wikidata.org/wiki/Q7520643","display_name":"Simple (philosophy)","level":2,"score":0.2728999853134155},{"id":"https://openalex.org/C37279795","wikidata":"https://www.wikidata.org/wiki/Q2492305","display_name":"Consistency model","level":3,"score":0.26019999384880066}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/ijcnn64981.2025.11227761","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ijcnn64981.2025.11227761","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 International Joint Conference on Neural Networks (IJCNN)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":16,"referenced_works":["https://openalex.org/W2108598243","https://openalex.org/W2194775991","https://openalex.org/W2963558289","https://openalex.org/W2964137095","https://openalex.org/W2964159205","https://openalex.org/W2966415767","https://openalex.org/W2979805229","https://openalex.org/W3034815148","https://openalex.org/W3035160371","https://openalex.org/W3035293718","https://openalex.org/W3035682985","https://openalex.org/W3091002423","https://openalex.org/W3109620645","https://openalex.org/W4287322212","https://openalex.org/W4312357822","https://openalex.org/W4312421335"],"related_works":[],"abstract_inverted_index":{"The":[0,134],"rapid":[1],"development":[2],"in":[3,13,123],"pseudo-labeling":[4],"and":[5,88,145,166,189,204],"consistency":[6,43,49,94],"regularization":[7,44],"has":[8],"significantly":[9],"advanced":[10],"semi-supervised":[11,65],"learning":[12,66],"computer":[14],"vision.":[15],"However,":[16],"these":[17,73],"methods":[18],"have":[19],"notable":[20],"limitations.":[21],"Pseudo-labeling":[22],"approaches":[23],"suffer":[24],"from":[25,142],"confirmation":[26,132],"bias,":[27],"as":[28],"the":[29,48,55,93,159,167,181,199],"model":[30,176],"trained":[31],"on":[32,47,187],"self-generated":[33],"labels":[34,144,194],"tends":[35],"to":[36,70,109,127,174,207],"perpetuate":[37],"or":[38],"even":[39],"amplify":[40],"inaccuracies.":[41],"Existing":[42],"techniques":[45],"focus":[46],"of":[50,57,80,95,183],"individual":[51,160],"instances,":[52],"but":[53],"overlook":[54],"alignment":[56],"relationships":[58,97],"between":[59],"samples.":[60,100],"We":[61],"propose":[62],"a":[63,111,115],"new":[64],"method":[67,76],"called":[68],"Semi-GD,":[69],"effectively":[71],"address":[72],"challenges.":[74],"Our":[75],"implements":[77],"two":[78,102],"types":[79],"matching:":[81],"prediction":[82,124,164],"matching,":[83,90],"which":[84,91],"enforces":[85,92],"instance":[86],"consistency,":[87],"graph":[89,136,150,172],"affinity":[96],"among":[98],"batch":[99],"These":[101],"matching":[103,125],"processes":[104],"mutually":[105],"reinforce":[106],"each":[107],"other":[108],"achieve":[110],"robust":[112],"model.":[113],"Furthermore,":[114],"simple":[116],"yet":[117],"effective":[118],"thresholding":[119],"strategy":[120],"is":[121,137],"introduced":[122],"process":[126],"select":[128],"high-confidence":[129],"samples,":[130],"alleviating":[131],"bias.":[133],"target":[135],"constructed":[138],"under":[139],"dual":[140],"constraints":[141],"cluster":[143],"pseudo-labels,":[146],"enabling":[147],"more":[148],"accurate":[149],"learning.":[151],"In":[152],"summary,":[153],"Semi-GD":[154,197],"utilizes":[155],"data":[156],"at":[157],"both":[158],"sample":[161],"level":[162,170],"(through":[163,171],"matching)":[165,173],"inter-sample":[168],"relationship":[169],"improve":[175],"performance.":[177],"Extensive":[178],"experiments":[179],"demonstrate":[180],"effectiveness":[182],"our":[184],"method.":[185],"Notably,":[186],"CIFAR10":[188],"CIFAR100":[190],"with":[191],"only":[192],"four":[193],"per":[195],"class,":[196],"reduces":[198],"error":[200],"rate":[201],"by":[202],"8.86%":[203],"11.43%":[205],"compared":[206],"FixMatch,":[208],"respectively.":[209]},"counts_by_year":[],"updated_date":"2026-03-07T16:01:11.037858","created_date":"2025-11-14T00:00:00"}