{"id":"https://openalex.org/W4391094970","doi":"https://doi.org/10.1109/bigdata59044.2023.10386952","title":"Multi-label Co-training using a Graph neural network.","display_name":"Multi-label Co-training using a Graph neural network.","publication_year":2023,"publication_date":"2023-12-15","ids":{"openalex":"https://openalex.org/W4391094970","doi":"https://doi.org/10.1109/bigdata59044.2023.10386952"},"language":"en","primary_location":{"id":"doi:10.1109/bigdata59044.2023.10386952","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1109/bigdata59044.2023.10386952","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2023 IEEE International Conference on Big Data (BigData)","raw_type":"proceedings-article"},"type":"conference-paper","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/A5041637548","display_name":"Ragini Kihlman","orcid":null},"institutions":[{"id":"https://openalex.org/I110002522","display_name":"University of Essex","ror":"https://ror.org/02nkf1q06","country_code":"GB","type":"education","lineage":["https://openalex.org/I110002522"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Ragini Kihlman","raw_affiliation_strings":["University of Essex,School of Computer Science and Electronic Engineering,Essex,United Kingdom","School of Computer Science and Electronic Engineering, University of Essex, Essex, United Kingdom"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Essex,School of Computer Science and Electronic Engineering,Essex,United Kingdom","institution_ids":["https://openalex.org/I110002522"]},{"raw_affiliation_string":"School of Computer Science and Electronic Engineering, University of Essex, Essex, United Kingdom","institution_ids":["https://openalex.org/I110002522"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5021136553","display_name":"Maria Fasli","orcid":"https://orcid.org/0000-0001-8831-102X"},"institutions":[{"id":"https://openalex.org/I110002522","display_name":"University of Essex","ror":"https://ror.org/02nkf1q06","country_code":"GB","type":"education","lineage":["https://openalex.org/I110002522"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Maria Fasli","raw_affiliation_strings":["University of Essex,School of Computer Science and Electronic Engineering,Essex,United Kingdom","School of Computer Science and Electronic Engineering, University of Essex, Essex, United Kingdom"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Essex,School of Computer Science and Electronic Engineering,Essex,United Kingdom","institution_ids":["https://openalex.org/I110002522"]},{"raw_affiliation_string":"School of Computer Science and Electronic Engineering, University of Essex, Essex, United Kingdom","institution_ids":["https://openalex.org/I110002522"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I110002522"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":"23","issue":null,"first_page":"5826","last_page":"5834"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11273","display_name":"Advanced Graph Neural Networks","score":0.9998000264167786,"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":0.9998000264167786,"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/T10028","display_name":"Topic Modeling","score":0.9997000098228455,"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/T11550","display_name":"Text and Document Classification Technologies","score":0.9958999752998352,"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/overfitting","display_name":"Overfitting","score":0.8343862295150757},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8072112798690796},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6832186579704285},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.6124638319015503},{"id":"https://openalex.org/keywords/graph","display_name":"Graph","score":0.5636505484580994},{"id":"https://openalex.org/keywords/labeled-data","display_name":"Labeled data","score":0.5459531545639038},{"id":"https://openalex.org/keywords/training-set","display_name":"Training set","score":0.5390298962593079},{"id":"https://openalex.org/keywords/classifier","display_name":"Classifier (UML)","score":0.5268712639808655},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.5174051523208618},{"id":"https://openalex.org/keywords/generalization","display_name":"Generalization","score":0.4501214325428009},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.3282482624053955},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.32734209299087524},{"id":"https://openalex.org/keywords/theoretical-computer-science","display_name":"Theoretical computer science","score":0.09090092778205872}],"concepts":[{"id":"https://openalex.org/C22019652","wikidata":"https://www.wikidata.org/wiki/Q331309","display_name":"Overfitting","level":3,"score":0.8343862295150757},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8072112798690796},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6832186579704285},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.6124638319015503},{"id":"https://openalex.org/C132525143","wikidata":"https://www.wikidata.org/wiki/Q141488","display_name":"Graph","level":2,"score":0.5636505484580994},{"id":"https://openalex.org/C2776145971","wikidata":"https://www.wikidata.org/wiki/Q30673951","display_name":"Labeled data","level":2,"score":0.5459531545639038},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.5390298962593079},{"id":"https://openalex.org/C95623464","wikidata":"https://www.wikidata.org/wiki/Q1096149","display_name":"Classifier (UML)","level":2,"score":0.5268712639808655},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.5174051523208618},{"id":"https://openalex.org/C177148314","wikidata":"https://www.wikidata.org/wiki/Q170084","display_name":"Generalization","level":2,"score":0.4501214325428009},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.3282482624053955},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.32734209299087524},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.09090092778205872},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/bigdata59044.2023.10386952","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1109/bigdata59044.2023.10386952","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2023 IEEE International Conference on Big Data (BigData)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G7368362902","display_name":null,"funder_award_id":"ES/S007156/1","funder_id":"https://openalex.org/F4320334630","funder_display_name":"Economic and Social Research Council"},{"id":"https://openalex.org/G8322284704","display_name":null,"funder_award_id":"ES/L011859/1","funder_id":"https://openalex.org/F4320334630","funder_display_name":"Economic and Social Research Council"}],"funders":[{"id":"https://openalex.org/F4320334630","display_name":"Economic and Social Research Council","ror":"https://ror.org/03n0ht308"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":46,"referenced_works":["https://openalex.org/W57680428","https://openalex.org/W1522301498","https://openalex.org/W1980867644","https://openalex.org/W2037851654","https://openalex.org/W2048679005","https://openalex.org/W2139906443","https://openalex.org/W2183182206","https://openalex.org/W2558748708","https://openalex.org/W2560674852","https://openalex.org/W2737925311","https://openalex.org/W2789876780","https://openalex.org/W2885195348","https://openalex.org/W2907492528","https://openalex.org/W2949676527","https://openalex.org/W2962756421","https://openalex.org/W2964015378","https://openalex.org/W2964236337","https://openalex.org/W2984353870","https://openalex.org/W2985169259","https://openalex.org/W3034323190","https://openalex.org/W3113453806","https://openalex.org/W3135053409","https://openalex.org/W3138953622","https://openalex.org/W3139580003","https://openalex.org/W3140854437","https://openalex.org/W3156333129","https://openalex.org/W3160464195","https://openalex.org/W4238866089","https://openalex.org/W4239025696","https://openalex.org/W4289761856","https://openalex.org/W4294558607","https://openalex.org/W4295728955","https://openalex.org/W4309435465","https://openalex.org/W4320024214","https://openalex.org/W6602375370","https://openalex.org/W6631190155","https://openalex.org/W6675134712","https://openalex.org/W6726873649","https://openalex.org/W6738964360","https://openalex.org/W6741450815","https://openalex.org/W6752122265","https://openalex.org/W6753146606","https://openalex.org/W6779733120","https://openalex.org/W6792439368","https://openalex.org/W6803602085","https://openalex.org/W6810682850"],"related_works":["https://openalex.org/W4312531262","https://openalex.org/W4388103534","https://openalex.org/W4318142952","https://openalex.org/W2072070946","https://openalex.org/W2044488462","https://openalex.org/W3204418343","https://openalex.org/W2981877337","https://openalex.org/W3203938600","https://openalex.org/W1560624709","https://openalex.org/W2169074127"],"abstract_inverted_index":{"Text":[0],"data":[1,108,116,150,209,226],"has":[2],"grown":[3],"exponentially":[4],"due":[5],"to":[6,76,110,157,175,216],"social":[7],"media,":[8],"e-commerce,":[9],"and":[10,33,67,207],"online":[11],"reviews.":[12],"Recent":[13],"studies":[14],"have":[15,85],"explored":[16],"graph":[17],"neural":[18,82],"networks":[19,83],"(GNNs)":[20],"for":[21,151,189,210],"text":[22,66,74],"classification,":[23],"since":[24],"they":[25],"are":[26,195],"not":[27],"capable":[28],"of":[29,55,106,132,170,221],"handling":[30],"complex":[31],"structures":[32],"preserving":[34],"global":[35,52,60],"information.":[36],"To":[37,178],"overcome":[38],"these":[39],"issues,":[40],"we":[41,71,182],"propose":[42,183],"a":[43,158,184],"GNN-based":[44],"co-training":[45,131,187],"model":[46,159,172],"that":[47,142],"creates":[48],"graphs":[49],"based":[50],"on":[51,65,87,198,224],"parameters":[53,57],"instead":[54],"single":[56],"It":[58],"retains":[59],"information":[61],"while":[62,97],"eliminating":[63],"dependency":[64],"corpus.":[68],"In":[69,214],"addition,":[70],"use":[72,204],"smaller":[73],"windows":[75],"extract":[77],"more":[78],"local":[79],"features.":[80],"Graph":[81],"(GNN)":[84],"focused":[86],"natural":[88],"language":[89],"processing":[90],"in":[91,167],"recent":[92],"years,":[93],"outperforming":[94],"existing":[95],"models":[96],"consuming":[98],"less":[99],"memory.":[100],"Co-training":[101],"enhances":[102],"the":[103,122,130,133,161,171,199,212,218],"limited":[104],"amount":[105],"labeled":[107,206],"used":[109,147],"train":[111],"each":[112],"classifier":[113],"with":[114],"pseudo-labeled":[115,208],"derived":[117],"from":[118,120],"predictions":[119],"both":[121],"classifiers.":[123,153],"Moreover,":[124],"pseudo-labels":[125,141,223,232],"cannot":[126],"be":[127],"controlled":[128],"by":[129],"data.":[134,177,202],"Wrongly":[135],"trained":[136,196],"classifiers":[137],"can":[138,155,165],"generate":[139],"inaccurate":[140,222],"cause":[143],"noticeable":[144],"errors":[145],"when":[146,173],"as":[148],"training":[149,162,201,211],"other":[152],"This":[154],"lead":[156],"overfitting":[160],"data,":[163],"which":[164],"result":[166],"poor":[168],"generalization":[169],"applied":[174],"new":[176],"address":[179],"this":[180],"issue,":[181],"deep":[185],"multi-label":[186],"framework":[188],"semi-supervised":[190],"GNNs":[191,194,203],"(MLD-GNN).":[192],"Two":[193],"simultaneously":[197],"same":[200],"original":[205],"model.":[213],"order":[215],"minimize":[217],"negative":[219],"impact":[220],"learning":[225],"augmentation,":[227],"label":[228],"augmentation":[229],"strategies":[230],"make":[231],"available":[233],"earlier":[234],"during":[235],"training.":[236]},"counts_by_year":[],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}