{"id":"https://openalex.org/W4213336168","doi":"https://doi.org/10.1145/3488560.3498482","title":"Efficient Two-stage Label Noise Reduction for Retrieval-based Tasks","display_name":"Efficient Two-stage Label Noise Reduction for Retrieval-based Tasks","publication_year":2022,"publication_date":"2022-02-11","ids":{"openalex":"https://openalex.org/W4213336168","doi":"https://doi.org/10.1145/3488560.3498482"},"language":"en","primary_location":{"id":"doi:10.1145/3488560.3498482","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3488560.3498482","pdf_url":null,"source":{"id":"https://openalex.org/S4363608885","display_name":"Proceedings of the Fifteenth ACM International Conference on Web Search and Data Mining","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Fifteenth ACM International Conference on Web Search and Data Mining","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/A5003035265","display_name":"Mengmeng Kuang","orcid":"https://orcid.org/0000-0001-9656-5652"},"institutions":[{"id":"https://openalex.org/I2250653659","display_name":"Tencent (China)","ror":"https://ror.org/00hhjss72","country_code":"CN","type":"company","lineage":["https://openalex.org/I2250653659"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Mengmeng Kuang","raw_affiliation_strings":["Tencent Holdings Ltd., Guangzhou, China"],"affiliations":[{"raw_affiliation_string":"Tencent Holdings Ltd., Guangzhou, China","institution_ids":["https://openalex.org/I2250653659"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5013332473","display_name":"Weiyan Wang","orcid":"https://orcid.org/0000-0002-4105-0691"},"institutions":[{"id":"https://openalex.org/I200769079","display_name":"Hong Kong University of Science and Technology","ror":"https://ror.org/00q4vv597","country_code":"HK","type":"education","lineage":["https://openalex.org/I200769079"]}],"countries":["HK"],"is_corresponding":false,"raw_author_name":"Weiyan Wang","raw_affiliation_strings":["Hong Kong University of Science and Technology, Hong Kong, China"],"affiliations":[{"raw_affiliation_string":"Hong Kong University of Science and Technology, Hong Kong, China","institution_ids":["https://openalex.org/I200769079"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5059772660","display_name":"Zhenhong Chen","orcid":"https://orcid.org/0009-0005-2440-6261"},"institutions":[{"id":"https://openalex.org/I2250653659","display_name":"Tencent (China)","ror":"https://ror.org/00hhjss72","country_code":"CN","type":"company","lineage":["https://openalex.org/I2250653659"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhenhong Chen","raw_affiliation_strings":["Tencent Holdings Ltd., Guangzhou, China"],"affiliations":[{"raw_affiliation_string":"Tencent Holdings Ltd., Guangzhou, China","institution_ids":["https://openalex.org/I2250653659"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5042803147","display_name":"Lie Kang","orcid":null},"institutions":[{"id":"https://openalex.org/I2250653659","display_name":"Tencent (China)","ror":"https://ror.org/00hhjss72","country_code":"CN","type":"company","lineage":["https://openalex.org/I2250653659"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Lie Kang","raw_affiliation_strings":["Tencent Holdings Ltd., Guangzhou, China"],"affiliations":[{"raw_affiliation_string":"Tencent Holdings Ltd., Guangzhou, China","institution_ids":["https://openalex.org/I2250653659"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5101766249","display_name":"Qiang Yan","orcid":"https://orcid.org/0000-0002-7328-2278"},"institutions":[{"id":"https://openalex.org/I2250653659","display_name":"Tencent (China)","ror":"https://ror.org/00hhjss72","country_code":"CN","type":"company","lineage":["https://openalex.org/I2250653659"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Qiang Yan","raw_affiliation_strings":["Tencent Holdings Ltd., Guangzhou, China"],"affiliations":[{"raw_affiliation_string":"Tencent Holdings Ltd., Guangzhou, China","institution_ids":["https://openalex.org/I2250653659"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5003035265"],"corresponding_institution_ids":["https://openalex.org/I2250653659"],"apc_list":null,"apc_paid":null,"fwci":0.4155,"has_fulltext":false,"cited_by_count":4,"citation_normalized_percentile":{"value":0.54794225,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":96},"biblio":{"volume":null,"issue":null,"first_page":"526","last_page":"534"},"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":0.9970999956130981,"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":0.9914000034332275,"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":0.8631049394607544},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7360537052154541},{"id":"https://openalex.org/keywords/noise-reduction","display_name":"Noise reduction","score":0.628240168094635},{"id":"https://openalex.org/keywords/noise","display_name":"Noise (video)","score":0.5676534175872803},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5563192963600159},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.5171391367912292},{"id":"https://openalex.org/keywords/probability-distribution","display_name":"Probability distribution","score":0.45106273889541626},{"id":"https://openalex.org/keywords/reduction","display_name":"Reduction (mathematics)","score":0.448725163936615},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.34956851601600647},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.21831423044204712},{"id":"https://openalex.org/keywords/statistics","display_name":"Statistics","score":0.15795528888702393},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.14346718788146973},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.12263223528862}],"concepts":[{"id":"https://openalex.org/C22019652","wikidata":"https://www.wikidata.org/wiki/Q331309","display_name":"Overfitting","level":3,"score":0.8631049394607544},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7360537052154541},{"id":"https://openalex.org/C163294075","wikidata":"https://www.wikidata.org/wiki/Q581861","display_name":"Noise reduction","level":2,"score":0.628240168094635},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.5676534175872803},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5563192963600159},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.5171391367912292},{"id":"https://openalex.org/C149441793","wikidata":"https://www.wikidata.org/wiki/Q200726","display_name":"Probability distribution","level":2,"score":0.45106273889541626},{"id":"https://openalex.org/C111335779","wikidata":"https://www.wikidata.org/wiki/Q3454686","display_name":"Reduction (mathematics)","level":2,"score":0.448725163936615},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.34956851601600647},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.21831423044204712},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.15795528888702393},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.14346718788146973},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.12263223528862},{"id":"https://openalex.org/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","level":1,"score":0.0}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1145/3488560.3498482","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3488560.3498482","pdf_url":null,"source":{"id":"https://openalex.org/S4363608885","display_name":"Proceedings of the Fifteenth ACM International Conference on Web Search and Data Mining","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Fifteenth ACM International Conference on Web Search and Data Mining","raw_type":"proceedings-article"},{"id":"pmh:oai:repository.hkust.edu.hk:1783.1-116137","is_oa":false,"landing_page_url":"http://lbdiscover.ust.hk/uresolver?url_ver=Z39.88-2004&rft_val_fmt=info:ofi/fmt:kev:mtx:journal&rfr_id=info:sid/HKUST:SPI&rft.genre=article&rft.issn=&rft.volume=&rft.issue=&rft.date=2022&rft.spage=526&rft.aulast=Kuang&rft.aufirst=&rft.atitle=Efficient+two-stage+label+noise+reduction+for+retrieval-based+tasks&rft.title=WSDM+2022+-+Proceedings+of+the+15th+ACM+International+Conference+on+Web+Search+and+Data+Mining","pdf_url":null,"source":{"id":"https://openalex.org/S4306401796","display_name":"Rare & Special e-Zone (The Hong Kong University of Science and Technology)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I200769079","host_organization_name":"Hong Kong University of Science and Technology","host_organization_lineage":["https://openalex.org/I200769079"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Conference paper"},{"id":"pmh:oai:repository.ust.hk:1783.1-116137","is_oa":false,"landing_page_url":"http://repository.ust.hk/ir/Record/1783.1-116137","pdf_url":null,"source":{"id":"https://openalex.org/S4306401796","display_name":"Rare & Special e-Zone (The Hong Kong University of Science and Technology)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I200769079","host_organization_name":"Hong Kong University of Science and Technology","host_organization_lineage":["https://openalex.org/I200769079"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"Conference paper"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":16,"referenced_works":["https://openalex.org/W1516184288","https://openalex.org/W2022995284","https://openalex.org/W2107189314","https://openalex.org/W2149427297","https://openalex.org/W2154776925","https://openalex.org/W2167460663","https://openalex.org/W2204904589","https://openalex.org/W2251939518","https://openalex.org/W2964292098","https://openalex.org/W2981873476","https://openalex.org/W2990476713","https://openalex.org/W3021636956","https://openalex.org/W3036320503","https://openalex.org/W3098468692","https://openalex.org/W3102725307","https://openalex.org/W3156669901"],"related_works":["https://openalex.org/W2989932438","https://openalex.org/W3011996705","https://openalex.org/W3099765033","https://openalex.org/W3175189414","https://openalex.org/W4210794429","https://openalex.org/W2985459377","https://openalex.org/W3206592002","https://openalex.org/W1996541855","https://openalex.org/W4225691219","https://openalex.org/W2944843851"],"abstract_inverted_index":{"The":[0,136],"existence":[1],"of":[2,41,72,193,224],"noisy":[3,20,65,75,110,133,144,162],"labels":[4,21,66,134],"in":[5,13,184,199],"datasets":[6,92,103,202,244],"has":[7,93,104],"always":[8],"been":[9],"an":[10],"essential":[11],"dilemma":[12],"deep":[14],"learning":[15],"studies.":[16],"Previous":[17],"works":[18],"detected":[19],"by":[22,29,124,150,164],"analyzing":[23,165],"the":[24,30,34,39,50,55,62,69,147,151,155,185,209,222,225],"predicted":[25,51],"probability":[26,52,70,129],"distribution":[27,53,71,130],"generated":[28],"model":[31,152],"trained":[32,153],"on":[33,64,90,101,154,190],"same":[35],"data":[36],"and":[37,61,74,159,175,195,214,237],"calculating":[38],"probabilities":[40,149],"each":[42],"label":[43,87,98,111,197,210,226,234],"to":[44,77,131,232],"be":[45,78,119],"regarded":[46],"as":[47],"noise.":[48],"However,":[49],"from":[54],"whole":[56],"dataset":[57],"may":[58,67],"introduce":[59,171],"overfitting,":[60],"overfitting":[63],"induce":[68],"clean":[73,243],"items":[76,163],"not":[79,241],"conditional":[80,127],"independent,":[81],"making":[82],"identification":[83],"more":[84],"challenging.":[85],"Additionally,":[86],"noise":[88,99,198,211,227,235],"reduction":[89,100,112,212,228],"image":[91],"received":[94],"much":[95],"attention,":[96],"while":[97],"text":[102,115,201],"not.":[105],"This":[106],"paper":[107],"proposes":[108],"a":[109,126,140,166,172,176],"method":[113,137,206,229,239],"for":[114,181],"datasets,":[116,236],"which":[117],"could":[118],"applied":[120],"at":[121],"retrieval-based":[122],"tasks":[123],"getting":[125],"independent":[128],"identify":[132],"accurately.":[135],"first":[138,186],"generates":[139],"candidate":[141],"set":[142],"containing":[143],"labels,":[145],"predicts":[146],"category":[148],"rest":[156],"cleaner":[157],"data,":[158],"then":[160],"identifies":[161],"confidence":[167],"matrix.":[168],"Moreover,":[169],"we":[170,219],"warm-up":[173],"module":[174],"sharpened":[177],"cross-entropy":[178],"loss":[179],"function":[180],"efficiently":[182],"training":[183],"stage.":[187],"Empirical":[188],"results":[189],"different":[191],"rates":[192],"uniform":[194],"random":[196],"five":[200],"demonstrate":[203],"that":[204,221],"our":[205,238],"can":[207],"improve":[208],"accuracy":[213],"end-to-end":[215],"classification":[216],"accuracy.":[217],"Further,":[218],"find":[220],"iteration":[223],"is":[230],"efficient":[231],"high-rate":[233],"will":[240],"hurt":[242],"too":[245],"much.":[246]},"counts_by_year":[{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":1},{"year":2022,"cited_by_count":2}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}