{"id":"https://openalex.org/W4385568120","doi":"https://doi.org/10.1145/3580305.3599522","title":"To Aggregate or Not? Learning with Separate Noisy Labels","display_name":"To Aggregate or Not? Learning with Separate Noisy Labels","publication_year":2023,"publication_date":"2023-08-04","ids":{"openalex":"https://openalex.org/W4385568120","doi":"https://doi.org/10.1145/3580305.3599522"},"language":"en","primary_location":{"id":"doi:10.1145/3580305.3599522","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3580305.3599522","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3580305.3599522","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 29th ACM SIGKDD Conference on Knowledge Discovery and Data Mining","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://dl.acm.org/doi/pdf/10.1145/3580305.3599522","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5049263948","display_name":"Jiaheng Wei","orcid":"https://orcid.org/0000-0003-3573-1711"},"institutions":[{"id":"https://openalex.org/I185103710","display_name":"University of California, Santa Cruz","ror":"https://ror.org/03s65by71","country_code":"US","type":"education","lineage":["https://openalex.org/I185103710"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Jiaheng Wei","raw_affiliation_strings":["University of California, Santa Cruz, Santa Cruz, CA, USA"],"raw_orcid":"https://orcid.org/0000-0003-3573-1711","affiliations":[{"raw_affiliation_string":"University of California, Santa Cruz, Santa Cruz, CA, USA","institution_ids":["https://openalex.org/I185103710"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5025441627","display_name":"Zhaowei Zhu","orcid":"https://orcid.org/0000-0003-3894-5862"},"institutions":[{"id":"https://openalex.org/I185103710","display_name":"University of California, Santa Cruz","ror":"https://ror.org/03s65by71","country_code":"US","type":"education","lineage":["https://openalex.org/I185103710"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Zhaowei Zhu","raw_affiliation_strings":["University of California, Santa Cruz, Santa Cruz, CA, USA"],"raw_orcid":"https://orcid.org/0000-0003-3894-5862","affiliations":[{"raw_affiliation_string":"University of California, Santa Cruz, Santa Cruz, CA, USA","institution_ids":["https://openalex.org/I185103710"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5066431124","display_name":"Tianyi Luo","orcid":"https://orcid.org/0000-0002-9497-7044"},"institutions":[{"id":"https://openalex.org/I1311688040","display_name":"Amazon (United States)","ror":"https://ror.org/04mv4n011","country_code":"US","type":"company","lineage":["https://openalex.org/I1311688040"]},{"id":"https://openalex.org/I4210133358","display_name":"Search","ror":"https://ror.org/03f78hn46","country_code":"US","type":"nonprofit","lineage":["https://openalex.org/I4210133358"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Tianyi Luo","raw_affiliation_strings":["Amazon Search Science and AI, Palo Alto, CA, USA"],"raw_orcid":"https://orcid.org/0000-0002-9497-7044","affiliations":[{"raw_affiliation_string":"Amazon Search Science and AI, Palo Alto, CA, USA","institution_ids":["https://openalex.org/I1311688040","https://openalex.org/I4210133358"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5056776503","display_name":"Ehsan Amid","orcid":"https://orcid.org/0000-0001-6097-0226"},"institutions":[{"id":"https://openalex.org/I1291425158","display_name":"Google (United States)","ror":"https://ror.org/00njsd438","country_code":"US","type":"company","lineage":["https://openalex.org/I1291425158","https://openalex.org/I4210128969"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Ehsan Amid","raw_affiliation_strings":["Google Research, Brain Team, Mountain View, CA, USA"],"raw_orcid":"https://orcid.org/0000-0001-6097-0226","affiliations":[{"raw_affiliation_string":"Google Research, Brain Team, Mountain View, CA, USA","institution_ids":["https://openalex.org/I1291425158"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102004400","display_name":"Abhishek Kumar","orcid":"https://orcid.org/0000-0003-1040-3527"},"institutions":[{"id":"https://openalex.org/I185103710","display_name":"University of California, Santa Cruz","ror":"https://ror.org/03s65by71","country_code":"US","type":"education","lineage":["https://openalex.org/I185103710"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Abhishek Kumar","raw_affiliation_strings":["University of California, Santa Cruz, Mountain View, CA, USA"],"raw_orcid":"https://orcid.org/0000-0003-1040-3527","affiliations":[{"raw_affiliation_string":"University of California, Santa Cruz, Mountain View, CA, USA","institution_ids":["https://openalex.org/I185103710"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100355722","display_name":"Yang Liu","orcid":"https://orcid.org/0000-0001-8420-6011"},"institutions":[{"id":"https://openalex.org/I185103710","display_name":"University of California, Santa Cruz","ror":"https://ror.org/03s65by71","country_code":"US","type":"education","lineage":["https://openalex.org/I185103710"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Yang Liu","raw_affiliation_strings":["University of California, Santa Cruz, Santa Cruz, CA, USA"],"raw_orcid":"https://orcid.org/0000-0001-8420-6011","affiliations":[{"raw_affiliation_string":"University of California, Santa Cruz, Santa Cruz, CA, USA","institution_ids":["https://openalex.org/I185103710"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"cited_by_count":22,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"2523","last_page":"2535"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12535","display_name":"Machine Learning and Data Classification","score":0.9990000128746033,"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/T12535","display_name":"Machine Learning and Data Classification","score":0.9990000128746033,"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/T11704","display_name":"Mobile Crowdsensing and Crowdsourcing","score":0.9962999820709229,"subfield":{"id":"https://openalex.org/subfields/1706","display_name":"Computer Science Applications"},"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/T12072","display_name":"Machine Learning and Algorithms","score":0.9947999715805054,"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/crowdsourcing","display_name":"Crowdsourcing","score":0.8416847586631775},{"id":"https://openalex.org/keywords/aggregate","display_name":"Aggregate (composite)","score":0.8383725881576538},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8304632902145386},{"id":"https://openalex.org/keywords/imperfect","display_name":"Imperfect","score":0.7406542301177979},{"id":"https://openalex.org/keywords/empirical-risk-minimization","display_name":"Empirical risk minimization","score":0.6717559695243835},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.6028450131416321},{"id":"https://openalex.org/keywords/noise","display_name":"Noise (video)","score":0.5716313719749451},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5588767528533936},{"id":"https://openalex.org/keywords/training-set","display_name":"Training set","score":0.5249583721160889},{"id":"https://openalex.org/keywords/empirical-research","display_name":"Empirical research","score":0.46818530559539795},{"id":"https://openalex.org/keywords/minification","display_name":"Minification","score":0.4607890546321869},{"id":"https://openalex.org/keywords/labeled-data","display_name":"Labeled data","score":0.4171467423439026},{"id":"https://openalex.org/keywords/statistics","display_name":"Statistics","score":0.11675789952278137},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.10294413566589355}],"concepts":[{"id":"https://openalex.org/C62230096","wikidata":"https://www.wikidata.org/wiki/Q275969","display_name":"Crowdsourcing","level":2,"score":0.8416847586631775},{"id":"https://openalex.org/C4679612","wikidata":"https://www.wikidata.org/wiki/Q866298","display_name":"Aggregate (composite)","level":2,"score":0.8383725881576538},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8304632902145386},{"id":"https://openalex.org/C2780310539","wikidata":"https://www.wikidata.org/wiki/Q12547192","display_name":"Imperfect","level":2,"score":0.7406542301177979},{"id":"https://openalex.org/C107321475","wikidata":"https://www.wikidata.org/wiki/Q5374254","display_name":"Empirical risk minimization","level":2,"score":0.6717559695243835},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.6028450131416321},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.5716313719749451},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5588767528533936},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.5249583721160889},{"id":"https://openalex.org/C120936955","wikidata":"https://www.wikidata.org/wiki/Q2155640","display_name":"Empirical research","level":2,"score":0.46818530559539795},{"id":"https://openalex.org/C147764199","wikidata":"https://www.wikidata.org/wiki/Q6865248","display_name":"Minification","level":2,"score":0.4607890546321869},{"id":"https://openalex.org/C2776145971","wikidata":"https://www.wikidata.org/wiki/Q30673951","display_name":"Labeled data","level":2,"score":0.4171467423439026},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.11675789952278137},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.10294413566589355},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.0},{"id":"https://openalex.org/C159985019","wikidata":"https://www.wikidata.org/wiki/Q181790","display_name":"Composite material","level":1,"score":0.0},{"id":"https://openalex.org/C192562407","wikidata":"https://www.wikidata.org/wiki/Q228736","display_name":"Materials science","level":0,"score":0.0},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3580305.3599522","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3580305.3599522","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3580305.3599522","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 29th ACM SIGKDD Conference on Knowledge Discovery and Data Mining","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.1145/3580305.3599522","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3580305.3599522","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3580305.3599522","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 29th ACM SIGKDD Conference on Knowledge Discovery and Data Mining","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G1645553586","display_name":"Collaborative Research: RI: Small: Wisdom of Crowds with Machines in the Loop","funder_award_id":"2007951","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G1821378518","display_name":null,"funder_award_id":"IIS-2007951, IIS-2143895","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"}],"funders":[{"id":"https://openalex.org/F4320306076","display_name":"National Science Foundation","ror":"https://ror.org/021nxhr62"}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4385568120.pdf","grobid_xml":"https://content.openalex.org/works/W4385568120.grobid-xml"},"referenced_works_count":36,"referenced_works":["https://openalex.org/W9014458","https://openalex.org/W398859631","https://openalex.org/W569478347","https://openalex.org/W605727707","https://openalex.org/W1501025848","https://openalex.org/W1514928307","https://openalex.org/W2095838485","https://openalex.org/W2147687736","https://openalex.org/W2171913066","https://openalex.org/W2194775991","https://openalex.org/W2339885376","https://openalex.org/W2567736915","https://openalex.org/W2582409643","https://openalex.org/W2612690371","https://openalex.org/W2895604144","https://openalex.org/W2911701540","https://openalex.org/W2913081045","https://openalex.org/W2963772355","https://openalex.org/W2964292098","https://openalex.org/W2981873476","https://openalex.org/W3005295611","https://openalex.org/W3029818501","https://openalex.org/W3034185248","https://openalex.org/W3034786938","https://openalex.org/W3035261884","https://openalex.org/W3042609801","https://openalex.org/W3104255659","https://openalex.org/W3170414933","https://openalex.org/W4212774754","https://openalex.org/W4221149743","https://openalex.org/W4225139517","https://openalex.org/W4293409613","https://openalex.org/W6600862597","https://openalex.org/W6602430550","https://openalex.org/W6608748766","https://openalex.org/W6609098157"],"related_works":["https://openalex.org/W2130553454","https://openalex.org/W3022007134","https://openalex.org/W2110091014","https://openalex.org/W4317548404","https://openalex.org/W2087783760","https://openalex.org/W1509924131","https://openalex.org/W2964083560","https://openalex.org/W3163689946","https://openalex.org/W4287890939","https://openalex.org/W2033364610"],"abstract_inverted_index":{"The":[0,39],"rawly":[1],"collected":[2,11],"training":[3,37],"data":[4],"often":[5],"comes":[6],"with":[7,111],"separate":[8,25,68],"noisy":[9,69,112],"labels":[10,26,70],"from":[12],"multiple":[13],"imperfect":[14],"annotators":[15],"(e.g.,":[16],"via":[17],"crowdsourcing).":[18],"A":[19],"typical":[20],"way":[21],"of":[22,63,85,97,109,134],"using":[23],"these":[24],"is":[27,120,136],"to":[28,56,60],"first":[29],"aggregate":[30,67],"them":[31,76],"into":[32,71],"one":[33,65],"and":[34,54],"apply":[35],"standard":[36],"methods.":[38],"literature":[40],"has":[41],"also":[42],"studied":[43],"extensively":[44],"on":[45],"effective":[46],"aggregation":[47,124],"approaches.":[48],"This":[49],"paper":[50],"revisits":[51],"this":[52],"choice":[53],"aims":[55],"provide":[57],"an":[58],"answer":[59],"the":[61,83,89,102,107,126,132],"question":[62],"whether":[64],"should":[66],"single":[72],"ones":[73,103],"or":[74,131],"use":[75],"separately":[77],"as":[78],"given.":[79],"We":[80],"theoretically":[81],"analyze":[82],"performance":[84],"both":[86],"approaches":[87],"under":[88],"empirical":[90,139],"risk":[91],"minimization":[92],"framework":[93],"for":[94,106],"a":[95],"number":[96,133],"popular":[98],"loss":[99],"functions,":[100],"including":[101],"designed":[104],"specifically":[105],"problem":[108],"learning":[110],"labels.":[113],"Our":[114],"theorems":[115],"conclude":[116],"that":[117],"label":[118,123],"separation":[119],"preferred":[121],"over":[122],"when":[125],"noise":[127],"rates":[128],"are":[129],"high,":[130],"labelers/annotations":[135],"insufficient.":[137],"Extensive":[138],"results":[140],"validate":[141],"our":[142],"conclusions.":[143]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":7},{"year":2024,"cited_by_count":11},{"year":2023,"cited_by_count":2},{"year":2022,"cited_by_count":1}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}