{"id":"https://openalex.org/W4411403462","doi":"https://doi.org/10.1145/3728289","title":"Two Birds with One Stone: Efficient Deep Learning over Mislabeled Data through Subset Selection","display_name":"Two Birds with One Stone: Efficient Deep Learning over Mislabeled Data through Subset Selection","publication_year":2025,"publication_date":"2025-06-17","ids":{"openalex":"https://openalex.org/W4411403462","doi":"https://doi.org/10.1145/3728289"},"language":"en","primary_location":{"id":"doi:10.1145/3728289","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3728289","pdf_url":null,"source":{"id":"https://openalex.org/S4387289859","display_name":"Proceedings of the ACM on Management of Data","issn_l":"2836-6573","issn":["2836-6573"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319798","host_organization_name":"Association for Computing Machinery","host_organization_lineage":["https://openalex.org/P4310319798"],"host_organization_lineage_names":["Association for Computing Machinery"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the ACM on Management of Data","raw_type":"journal-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/A5044971195","display_name":"Yuhao Deng","orcid":"https://orcid.org/0009-0002-4473-4527"},"institutions":[{"id":"https://openalex.org/I125839683","display_name":"Beijing Institute of Technology","ror":"https://ror.org/01skt4w74","country_code":"CN","type":"education","lineage":["https://openalex.org/I125839683","https://openalex.org/I890469752"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Yuhao Deng","raw_affiliation_strings":["Beijing Institute of Technology, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Beijing Institute of Technology, Beijing, China","institution_ids":["https://openalex.org/I125839683"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5054869135","display_name":"Chengliang Chai","orcid":"https://orcid.org/0009-0003-5386-1330"},"institutions":[{"id":"https://openalex.org/I125839683","display_name":"Beijing Institute of Technology","ror":"https://ror.org/01skt4w74","country_code":"CN","type":"education","lineage":["https://openalex.org/I125839683","https://openalex.org/I890469752"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Chengliang Chai","raw_affiliation_strings":["Beijing Institute of Technology, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Beijing Institute of Technology, Beijing, China","institution_ids":["https://openalex.org/I125839683"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5113881881","display_name":"Kaisen Jin","orcid":"https://orcid.org/0009-0004-7020-5404"},"institutions":[{"id":"https://openalex.org/I125839683","display_name":"Beijing Institute of Technology","ror":"https://ror.org/01skt4w74","country_code":"CN","type":"education","lineage":["https://openalex.org/I125839683","https://openalex.org/I890469752"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Kaisen Jin","raw_affiliation_strings":["Beijing Institute of Technology, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Beijing Institute of Technology, Beijing, China","institution_ids":["https://openalex.org/I125839683"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5045756077","display_name":"Linan Zheng","orcid":"https://orcid.org/0009-0004-4437-1556"},"institutions":[{"id":"https://openalex.org/I138006243","display_name":"University of Arizona","ror":"https://ror.org/03m2x1q45","country_code":"US","type":"education","lineage":["https://openalex.org/I138006243"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Linan Zheng","raw_affiliation_strings":["University of Arizona, Tucson, AZ, USA"],"affiliations":[{"raw_affiliation_string":"University of Arizona, Tucson, AZ, USA","institution_ids":["https://openalex.org/I138006243"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5049926126","display_name":"Lei Cao","orcid":"https://orcid.org/0000-0001-9909-8607"},"institutions":[{"id":"https://openalex.org/I138006243","display_name":"University of Arizona","ror":"https://ror.org/03m2x1q45","country_code":"US","type":"education","lineage":["https://openalex.org/I138006243"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Lei Cao","raw_affiliation_strings":["University of Arizona, Tucson, USA and MIT, Cambridge, USA"],"affiliations":[{"raw_affiliation_string":"University of Arizona, Tucson, USA and MIT, Cambridge, USA","institution_ids":["https://openalex.org/I138006243"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5014346487","display_name":"Ye Yuan","orcid":"https://orcid.org/0000-0002-0247-9866"},"institutions":[{"id":"https://openalex.org/I125839683","display_name":"Beijing Institute of Technology","ror":"https://ror.org/01skt4w74","country_code":"CN","type":"education","lineage":["https://openalex.org/I125839683","https://openalex.org/I890469752"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Ye Yuan","raw_affiliation_strings":["Beijing Institute of Technology, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Beijing Institute of Technology, Beijing, China","institution_ids":["https://openalex.org/I125839683"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5054991337","display_name":"Guoren Wang","orcid":"https://orcid.org/0000-0002-0181-8379"},"institutions":[{"id":"https://openalex.org/I125839683","display_name":"Beijing Institute of Technology","ror":"https://ror.org/01skt4w74","country_code":"CN","type":"education","lineage":["https://openalex.org/I125839683","https://openalex.org/I890469752"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Guoren Wang","raw_affiliation_strings":["Beijing Institute of Technology, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Beijing Institute of Technology, Beijing, China","institution_ids":["https://openalex.org/I125839683"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":7,"corresponding_author_ids":["https://openalex.org/A5044971195"],"corresponding_institution_ids":["https://openalex.org/I125839683"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.07519515,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"3","issue":"3","first_page":"1","last_page":"28"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12535","display_name":"Machine Learning and Data Classification","score":0.9998999834060669,"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":0.9998999834060669,"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/T12072","display_name":"Machine Learning and Algorithms","score":0.9919000267982483,"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/T11652","display_name":"Imbalanced Data Classification Techniques","score":0.9818999767303467,"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/computer-science","display_name":"Computer science","score":0.750596284866333},{"id":"https://openalex.org/keywords/leverage","display_name":"Leverage (statistics)","score":0.659798264503479},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6462398171424866},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.6323872208595276},{"id":"https://openalex.org/keywords/submodular-set-function","display_name":"Submodular set function","score":0.5767592191696167},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.49793434143066406},{"id":"https://openalex.org/keywords/training-set","display_name":"Training set","score":0.4470682144165039},{"id":"https://openalex.org/keywords/deep-learning","display_name":"Deep learning","score":0.4414272606372833},{"id":"https://openalex.org/keywords/selection","display_name":"Selection (genetic algorithm)","score":0.43870511651039124},{"id":"https://openalex.org/keywords/training","display_name":"Training (meteorology)","score":0.4335441589355469},{"id":"https://openalex.org/keywords/labeled-data","display_name":"Labeled data","score":0.41644155979156494},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.3484283685684204},{"id":"https://openalex.org/keywords/mathematical-optimization","display_name":"Mathematical optimization","score":0.19079679250717163},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.11714643239974976}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.750596284866333},{"id":"https://openalex.org/C153083717","wikidata":"https://www.wikidata.org/wiki/Q6535263","display_name":"Leverage (statistics)","level":2,"score":0.659798264503479},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6462398171424866},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.6323872208595276},{"id":"https://openalex.org/C178621042","wikidata":"https://www.wikidata.org/wiki/Q7631710","display_name":"Submodular set function","level":2,"score":0.5767592191696167},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.49793434143066406},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.4470682144165039},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.4414272606372833},{"id":"https://openalex.org/C81917197","wikidata":"https://www.wikidata.org/wiki/Q628760","display_name":"Selection (genetic algorithm)","level":2,"score":0.43870511651039124},{"id":"https://openalex.org/C2777211547","wikidata":"https://www.wikidata.org/wiki/Q17141490","display_name":"Training (meteorology)","level":2,"score":0.4335441589355469},{"id":"https://openalex.org/C2776145971","wikidata":"https://www.wikidata.org/wiki/Q30673951","display_name":"Labeled data","level":2,"score":0.41644155979156494},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.3484283685684204},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.19079679250717163},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.11714643239974976},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0},{"id":"https://openalex.org/C153294291","wikidata":"https://www.wikidata.org/wiki/Q25261","display_name":"Meteorology","level":1,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3728289","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3728289","pdf_url":null,"source":{"id":"https://openalex.org/S4387289859","display_name":"Proceedings of the ACM on Management of Data","issn_l":"2836-6573","issn":["2836-6573"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319798","host_organization_name":"Association for Computing Machinery","host_organization_lineage":["https://openalex.org/P4310319798"],"host_organization_lineage_names":["Association for Computing Machinery"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the ACM on Management of Data","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G7148827108","display_name":null,"funder_award_id":"62472031,624B2023,61932004, 62225203, U21A20516,62427808, U2001211","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/F4320322183","display_name":"Huawei Technologies","ror":"https://ror.org/00cmhce21"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":35,"referenced_works":["https://openalex.org/W18156408","https://openalex.org/W1572720249","https://openalex.org/W1585680390","https://openalex.org/W1666942233","https://openalex.org/W1921293667","https://openalex.org/W1997865285","https://openalex.org/W2045964207","https://openalex.org/W2150757437","https://openalex.org/W2358876993","https://openalex.org/W2396309311","https://openalex.org/W2548122763","https://openalex.org/W2560674852","https://openalex.org/W2747329762","https://openalex.org/W2807006342","https://openalex.org/W2964155802","https://openalex.org/W2964292098","https://openalex.org/W2998239226","https://openalex.org/W3009953871","https://openalex.org/W3034197595","https://openalex.org/W3035716296","https://openalex.org/W3113682753","https://openalex.org/W3139458990","https://openalex.org/W3156669901","https://openalex.org/W3176502563","https://openalex.org/W3197431719","https://openalex.org/W4206648492","https://openalex.org/W4206908526","https://openalex.org/W4292070111","https://openalex.org/W4312929313","https://openalex.org/W4381329328","https://openalex.org/W4385567975","https://openalex.org/W4386065630","https://openalex.org/W4390873603","https://openalex.org/W4396601766","https://openalex.org/W6966844147"],"related_works":["https://openalex.org/W2129767422","https://openalex.org/W3210196349","https://openalex.org/W2950181282","https://openalex.org/W2798287483","https://openalex.org/W2913410650","https://openalex.org/W3000197790","https://openalex.org/W4398789279","https://openalex.org/W2130553454","https://openalex.org/W3022007134","https://openalex.org/W4317548404"],"abstract_inverted_index":{"Using":[0],"a":[1,7,13,47,88,94,143,147,177],"large":[2],"training":[3,30,44,51,63,98,117,157,197,218,233],"dataset":[4],"to":[5,74,107,121,181,210,236],"train":[6],"big":[8],"and":[9,28,32,119,126,175,225],"powerful":[10],"model":[11,134,241],"--":[12],"typical":[14],"practice":[15],"in":[16,70],"modern":[17],"deep":[18,113],"learning,":[19],"often":[20],"suffers":[21],"from":[22],"two":[23,79],"major":[24],"problems:":[25],"the":[26,33,43,57,109,123,128,135,152,155,196,201,216,232,240],"expensive":[27],"slow":[29],"process":[31,234],"error-prone":[34],"labels.":[35,163],"The":[36,103],"existing":[37],"approaches,":[38],"targeting":[39],"either":[40],"speeding":[41],"up":[42,235],"by":[45],"selecting":[46],"subset":[48,95,138,148,193,214],"of":[49,60,77,96,137,145,154],"representative":[50,97,129],"instances":[52,99],"(subset":[53],"selection)":[54],"or":[55],"eliminating":[56],"negative":[58],"effect":[59],"mislabels":[61],"during":[62,112,215],"(mislabel":[64],"detection),":[65],"do":[66],"not":[67],"perform":[68],"well":[69],"this":[71,83,183,191,213],"scenario":[72],"due":[73],"overlooking":[75],"one":[76],"these":[78],"problems.":[80],"To":[81],"fill":[82],"gap,":[84],"we":[85,133,205],"propose":[86,176,206],"Deem,":[87],"novel":[89],"data-efficient":[90],"framework":[91],"that":[92,149,166,229],"selects":[93],"under":[100,140],"label":[101,124],"uncertainty.":[102],"key":[104],"idea":[105],"is":[106,168],"leverage":[108],"metadata":[110],"produced":[111],"learning":[114],"training,":[115],"e.g.,":[116],"losses":[118],"gradients,":[120],"estimate":[122],"uncertainty":[125,141],"select":[127],"instances.":[130],"In":[131],"particular,":[132],"problem":[136,144,171,184],"selection":[139],"as":[142],"finding":[146],"closely":[150],"approximates":[151],"gradient":[153],"whole":[156],"data":[158],"set":[159],"derived":[160],"on":[161,190,222],"soft":[162],"We":[164],"show":[165],"it":[167],"an":[169,186,207],"NP-hard":[170],"with":[172,185],"submodular":[173],"property":[174],"low":[178],"complexity":[179],"algorithm":[180],"solve":[182],"approximate":[187],"ratio.":[188],"Training":[189],"small":[192],"thus":[194],"improves":[195],"efficiency":[198],"while":[199],"guaranteeing":[200],"model's":[202],"accuracy.":[203,242],"Moreover,":[204],"efficient":[208],"strategy":[209],"dynamically":[211],"refine":[212],"iterative":[217],"process.":[219],"Extensive":[220],"experiments":[221],"6":[223],"datasets":[224],"10":[226],"baselines":[227],"demonstrate":[228],"Deem":[230],"accelerates":[231],"10X":[237],"without":[238],"sacrificing":[239]},"counts_by_year":[],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}