{"id":"https://openalex.org/W4385532471","doi":"https://doi.org/10.1109/sera57763.2023.10197667","title":"Towards Imbalanced Large Scale Multi-label Classification with Partially Annotated Labels","display_name":"Towards Imbalanced Large Scale Multi-label Classification with Partially Annotated Labels","publication_year":2023,"publication_date":"2023-05-23","ids":{"openalex":"https://openalex.org/W4385532471","doi":"https://doi.org/10.1109/sera57763.2023.10197667"},"language":"en","primary_location":{"id":"doi:10.1109/sera57763.2023.10197667","is_oa":false,"landing_page_url":"https://doi.org/10.1109/sera57763.2023.10197667","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2023 IEEE/ACIS 21st International Conference on Software Engineering Research, Management and Applications (SERA)","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/A5100327327","display_name":"Xin Zhang","orcid":"https://orcid.org/0000-0001-5647-2777"},"institutions":[{"id":"https://openalex.org/I155781252","display_name":"University of South Carolina","ror":"https://ror.org/02b6qw903","country_code":"US","type":"education","lineage":["https://openalex.org/I155781252"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Xin Zhang","raw_affiliation_strings":["University of South Carolina,Columbia,United States","University of South Carolina, Columbia, United States"],"affiliations":[{"raw_affiliation_string":"University of South Carolina,Columbia,United States","institution_ids":["https://openalex.org/I155781252"]},{"raw_affiliation_string":"University of South Carolina, Columbia, United States","institution_ids":["https://openalex.org/I155781252"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5039446470","display_name":"Yuqi Song","orcid":"https://orcid.org/0009-0000-8148-9212"},"institutions":[{"id":"https://openalex.org/I155781252","display_name":"University of South Carolina","ror":"https://ror.org/02b6qw903","country_code":"US","type":"education","lineage":["https://openalex.org/I155781252"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Yuqi Song","raw_affiliation_strings":["University of South Carolina,Columbia,United States","University of South Carolina, Columbia, United States"],"affiliations":[{"raw_affiliation_string":"University of South Carolina,Columbia,United States","institution_ids":["https://openalex.org/I155781252"]},{"raw_affiliation_string":"University of South Carolina, Columbia, United States","institution_ids":["https://openalex.org/I155781252"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5049921697","display_name":"Fei Zuo","orcid":"https://orcid.org/0000-0001-8902-1753"},"institutions":[{"id":"https://openalex.org/I139325414","display_name":"University of Central Oklahoma","ror":"https://ror.org/02n455404","country_code":"US","type":"education","lineage":["https://openalex.org/I139325414"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Fei Zuo","raw_affiliation_strings":["University of Central Oklahoma,Oklahoma,United States","University of Central Oklahoma, Oklahoma, United States"],"affiliations":[{"raw_affiliation_string":"University of Central Oklahoma,Oklahoma,United States","institution_ids":["https://openalex.org/I139325414"]},{"raw_affiliation_string":"University of Central Oklahoma, Oklahoma, United States","institution_ids":["https://openalex.org/I139325414"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5111019271","display_name":"Zheqing Zhou","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zheqing Zhou","raw_affiliation_strings":["Ningbo Jifeng Technology, Co.,China","Ningbo Jifeng Technology, Co., China"],"affiliations":[{"raw_affiliation_string":"Ningbo Jifeng Technology, Co.,China","institution_ids":[]},{"raw_affiliation_string":"Ningbo Jifeng Technology, Co., China","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100333260","display_name":"Xiaofeng Wang","orcid":"https://orcid.org/0000-0003-0144-5944"},"institutions":[{"id":"https://openalex.org/I155781252","display_name":"University of South Carolina","ror":"https://ror.org/02b6qw903","country_code":"US","type":"education","lineage":["https://openalex.org/I155781252"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Xiaofeng Wang","raw_affiliation_strings":["University of South Carolina,Columbia,United States","University of South Carolina, Columbia, United States"],"affiliations":[{"raw_affiliation_string":"University of South Carolina,Columbia,United States","institution_ids":["https://openalex.org/I155781252"]},{"raw_affiliation_string":"University of South Carolina, Columbia, United States","institution_ids":["https://openalex.org/I155781252"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5100327327"],"corresponding_institution_ids":["https://openalex.org/I155781252"],"apc_list":null,"apc_paid":null,"fwci":0.6993,"has_fulltext":false,"cited_by_count":4,"citation_normalized_percentile":{"value":0.75246175,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":94,"max":96},"biblio":{"volume":null,"issue":null,"first_page":"195","last_page":"200"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11550","display_name":"Text and Document Classification Technologies","score":0.9977999925613403,"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/T11550","display_name":"Text and Document Classification Technologies","score":0.9977999925613403,"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/T11775","display_name":"COVID-19 diagnosis using AI","score":0.9950000047683716,"subfield":{"id":"https://openalex.org/subfields/2741","display_name":"Radiology, Nuclear Medicine and Imaging"},"field":{"id":"https://openalex.org/fields/27","display_name":"Medicine"},"domain":{"id":"https://openalex.org/domains/4","display_name":"Health Sciences"}},{"id":"https://openalex.org/T11512","display_name":"Anomaly Detection Techniques and Applications","score":0.9879999756813049,"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/multi-label-classification","display_name":"Multi-label classification","score":0.8531210422515869},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8288785219192505},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6615217328071594},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.6591529846191406},{"id":"https://openalex.org/keywords/dimension","display_name":"Dimension (graph theory)","score":0.4857178330421448},{"id":"https://openalex.org/keywords/limit","display_name":"Limit (mathematics)","score":0.4401649236679077},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.39457884430885315},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.3730700612068176},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.07731384038925171}],"concepts":[{"id":"https://openalex.org/C2776482837","wikidata":"https://www.wikidata.org/wiki/Q3553958","display_name":"Multi-label classification","level":2,"score":0.8531210422515869},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8288785219192505},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6615217328071594},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.6591529846191406},{"id":"https://openalex.org/C33676613","wikidata":"https://www.wikidata.org/wiki/Q13415176","display_name":"Dimension (graph theory)","level":2,"score":0.4857178330421448},{"id":"https://openalex.org/C151201525","wikidata":"https://www.wikidata.org/wiki/Q177239","display_name":"Limit (mathematics)","level":2,"score":0.4401649236679077},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.39457884430885315},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3730700612068176},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.07731384038925171},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.0},{"id":"https://openalex.org/C202444582","wikidata":"https://www.wikidata.org/wiki/Q837863","display_name":"Pure mathematics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/sera57763.2023.10197667","is_oa":false,"landing_page_url":"https://doi.org/10.1109/sera57763.2023.10197667","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2023 IEEE/ACIS 21st International Conference on Software Engineering Research, Management and Applications (SERA)","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":36,"referenced_works":["https://openalex.org/W1797268635","https://openalex.org/W1861492603","https://openalex.org/W1940008012","https://openalex.org/W1984983329","https://openalex.org/W2007972815","https://openalex.org/W2102765684","https://openalex.org/W2108598243","https://openalex.org/W2114393161","https://openalex.org/W2115119296","https://openalex.org/W2145908112","https://openalex.org/W2146241755","https://openalex.org/W2183341477","https://openalex.org/W2549139847","https://openalex.org/W2950121050","https://openalex.org/W2963351448","https://openalex.org/W2969792713","https://openalex.org/W2990520530","https://openalex.org/W3011722050","https://openalex.org/W3095707208","https://openalex.org/W3098331497","https://openalex.org/W3160262531","https://openalex.org/W3165691894","https://openalex.org/W4214673031","https://openalex.org/W4226095984","https://openalex.org/W4244207479","https://openalex.org/W4288083516","https://openalex.org/W4361019813","https://openalex.org/W6638319203","https://openalex.org/W6639102338","https://openalex.org/W6640485552","https://openalex.org/W6646556945","https://openalex.org/W6677150689","https://openalex.org/W6681897715","https://openalex.org/W6764172607","https://openalex.org/W6785105160","https://openalex.org/W6811007050"],"related_works":["https://openalex.org/W2353396818","https://openalex.org/W2370473919","https://openalex.org/W2039871688","https://openalex.org/W1987895267","https://openalex.org/W2350519135","https://openalex.org/W2390496461","https://openalex.org/W2017214274","https://openalex.org/W2883491016","https://openalex.org/W2389654532","https://openalex.org/W4281776617"],"abstract_inverted_index":{"Multi-label":[0],"classification":[1],"is":[2,22,37,66],"a":[3,23,29,129,151],"widely":[4],"encountered":[5],"problem":[6],"in":[7,97,115,207],"daily":[8],"life,":[9],"where":[10],"an":[11],"instance":[12],"can":[13,51],"be":[14,41,113],"associated":[15],"with":[16,219],"multiple":[17],"classes.":[18],"In":[19,47,78,147],"theory,":[20],"this":[21,79],"supervised":[24],"learning":[25],"method":[26],"that":[27,133,198],"requires":[28],"large":[30,98],"amount":[31],"of":[32,55,85,159,191],"labeling.":[33],"However,":[34],"annotating":[35],"data":[36],"time-consuming":[38],"and":[39,88,163,184,205],"may":[40],"infeasible":[42],"for":[43,122],"huge":[44],"labeling":[45,99,161,210],"spaces.":[46,100],"addition,":[48,148],"label":[49,86,144],"imbalance":[50,87,145],"limit":[52],"the":[53,83,104,120,143,157,160,166,189,192,216],"performance":[54],"multi-label":[56,177],"classifiers,":[57],"especially":[58],"when":[59],"some":[60,174,208],"labels":[61,96],"are":[62],"missing.":[63],"Therefore,":[64],"it":[65],"meaningful":[67],"to":[68,71,91,112,140,155,187],"study":[69],"how":[70,90],"train":[72,92],"neural":[73],"networks":[74,111],"using":[75,94],"partial":[76,95,209],"labels.":[77,221],"work,":[80],"we":[81,102,127,149,169],"address":[82],"issue":[84],"investigate":[89],"classifiers":[93],"First,":[101],"introduce":[103],"pseudo-labeling":[105],"technique,":[106],"which":[107],"allows":[108],"commonly":[109],"adopted":[110],"applied":[114],"partially":[116],"labeled":[117],"settings":[118],"without":[119],"need":[121],"additional":[123],"complex":[124],"structures.":[125],"Then,":[126],"propose":[128],"novel":[130],"loss":[131],"function":[132],"leverages":[134],"statistical":[135],"information":[136],"from":[137],"existing":[138],"datasets":[139,178],"effectively":[141],"alleviate":[142],"problem.":[146],"design":[150],"dynamic":[152],"training":[153],"scheme":[154],"reduce":[156],"dimension":[158],"space":[162],"further":[164],"mitigate":[165],"imbalance.":[167],"Finally,":[168],"conduct":[170],"extensive":[171],"experiments":[172],"on":[173],"publicly":[175],"available":[176],"such":[179],"as":[180],"COCO,":[181],"NUS-WIDE,":[182],"CUB,":[183],"Open":[185],"Images":[186],"demonstrate":[188],"effectiveness":[190],"proposed":[193],"approach.":[194],"The":[195],"results":[196],"show":[197],"our":[199,212],"approach":[200,213],"outperforms":[201],"several":[202],"state-of-the-art":[203],"methods,":[204],"surprisingly,":[206],"settings,":[211],"even":[214],"exceeds":[215],"methods":[217],"trained":[218],"full":[220]},"counts_by_year":[{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":2}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}