{"id":"https://openalex.org/W3186434753","doi":"https://doi.org/10.14778/3476249.3476290","title":"CHEF","display_name":"CHEF","publication_year":2021,"publication_date":"2021-07-01","ids":{"openalex":"https://openalex.org/W3186434753","doi":"https://doi.org/10.14778/3476249.3476290","mag":"3186434753"},"language":"en","primary_location":{"id":"doi:10.14778/3476249.3476290","is_oa":false,"landing_page_url":"https://doi.org/10.14778/3476249.3476290","pdf_url":null,"source":{"id":"https://openalex.org/S4210226185","display_name":"Proceedings of the VLDB Endowment","issn_l":"2150-8097","issn":["2150-8097"],"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 VLDB Endowment","raw_type":"journal-article"},"type":"article","indexed_in":["arxiv","crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2107.08588","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":null,"display_name":"Yinjun Wu","orcid":null},"institutions":[{"id":"https://openalex.org/I36788626","display_name":"California University of Pennsylvania","ror":"https://ror.org/01spssf70","country_code":"US","type":"education","lineage":["https://openalex.org/I36788626"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Yinjun Wu","raw_affiliation_strings":["University of Pennsylvania"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Pennsylvania","institution_ids":["https://openalex.org/I36788626"]}]},{"author_position":"middle","author":{"id":null,"display_name":"James Weimer","orcid":null},"institutions":[{"id":"https://openalex.org/I36788626","display_name":"California University of Pennsylvania","ror":"https://ror.org/01spssf70","country_code":"US","type":"education","lineage":["https://openalex.org/I36788626"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"James Weimer","raw_affiliation_strings":["University of Pennsylvania"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Pennsylvania","institution_ids":["https://openalex.org/I36788626"]}]},{"author_position":"last","author":{"id":null,"display_name":"Susan B. Davidson","orcid":null},"institutions":[{"id":"https://openalex.org/I36788626","display_name":"California University of Pennsylvania","ror":"https://ror.org/01spssf70","country_code":"US","type":"education","lineage":["https://openalex.org/I36788626"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Susan B. Davidson","raw_affiliation_strings":["University of Pennsylvania"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Pennsylvania","institution_ids":["https://openalex.org/I36788626"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I36788626"],"apc_list":null,"apc_paid":null,"fwci":0.9328,"has_fulltext":false,"cited_by_count":4,"citation_normalized_percentile":{"value":0.7818854,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":91,"max":97},"biblio":{"volume":"14","issue":"11","first_page":"2410","last_page":"2418"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12399","display_name":"Wine Industry and Tourism","score":0.8600000143051147,"subfield":{"id":"https://openalex.org/subfields/1409","display_name":"Tourism, Leisure and Hospitality Management"},"field":{"id":"https://openalex.org/fields/14","display_name":"Business, Management and Accounting"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},"topics":[{"id":"https://openalex.org/T12399","display_name":"Wine Industry and Tourism","score":0.8600000143051147,"subfield":{"id":"https://openalex.org/subfields/1409","display_name":"Tourism, Leisure and Hospitality Management"},"field":{"id":"https://openalex.org/fields/14","display_name":"Business, Management and Accounting"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},{"id":"https://openalex.org/T11925","display_name":"Culinary Culture and Tourism","score":0.843500018119812,"subfield":{"id":"https://openalex.org/subfields/1106","display_name":"Food Science"},"field":{"id":"https://openalex.org/fields/11","display_name":"Agricultural and Biological Sciences"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}},{"id":"https://openalex.org/T10750","display_name":"Fermentation and Sensory Analysis","score":0.7943999767303467,"subfield":{"id":"https://openalex.org/subfields/1106","display_name":"Food Science"},"field":{"id":"https://openalex.org/fields/11","display_name":"Agricultural and Biological Sciences"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/pipeline","display_name":"Pipeline (software)","score":0.6985999941825867},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.6018000245094299},{"id":"https://openalex.org/keywords/probabilistic-logic","display_name":"Probabilistic logic","score":0.5827999711036682},{"id":"https://openalex.org/keywords/sample","display_name":"Sample (material)","score":0.5264999866485596},{"id":"https://openalex.org/keywords/overhead","display_name":"Overhead (engineering)","score":0.5264000296592712},{"id":"https://openalex.org/keywords/statistical-model","display_name":"Statistical model","score":0.32739999890327454}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.724399983882904},{"id":"https://openalex.org/C43521106","wikidata":"https://www.wikidata.org/wiki/Q2165493","display_name":"Pipeline (software)","level":2,"score":0.6985999941825867},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.6018000245094299},{"id":"https://openalex.org/C49937458","wikidata":"https://www.wikidata.org/wiki/Q2599292","display_name":"Probabilistic logic","level":2,"score":0.5827999711036682},{"id":"https://openalex.org/C198531522","wikidata":"https://www.wikidata.org/wiki/Q485146","display_name":"Sample (material)","level":2,"score":0.5264999866485596},{"id":"https://openalex.org/C2779960059","wikidata":"https://www.wikidata.org/wiki/Q7113681","display_name":"Overhead (engineering)","level":2,"score":0.5264000296592712},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.517300009727478},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.45719999074935913},{"id":"https://openalex.org/C114289077","wikidata":"https://www.wikidata.org/wiki/Q3284399","display_name":"Statistical model","level":2,"score":0.32739999890327454},{"id":"https://openalex.org/C172658912","wikidata":"https://www.wikidata.org/wiki/Q661613","display_name":"Batch processing","level":2,"score":0.2872999906539917},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.28380000591278076},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.28299999237060547},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.27079999446868896},{"id":"https://openalex.org/C93983250","wikidata":"https://www.wikidata.org/wiki/Q795053","display_name":"Cost estimate","level":2,"score":0.26820001006126404},{"id":"https://openalex.org/C75684735","wikidata":"https://www.wikidata.org/wiki/Q858810","display_name":"Big data","level":2,"score":0.25600001215934753}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.14778/3476249.3476290","is_oa":false,"landing_page_url":"https://doi.org/10.14778/3476249.3476290","pdf_url":null,"source":{"id":"https://openalex.org/S4210226185","display_name":"Proceedings of the VLDB Endowment","issn_l":"2150-8097","issn":["2150-8097"],"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 VLDB Endowment","raw_type":"journal-article"},{"id":"pmh:oai:arXiv.org:2107.08588","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2107.08588","pdf_url":"https://arxiv.org/pdf/2107.08588","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"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":"text"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2107.08588","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2107.08588","pdf_url":"https://arxiv.org/pdf/2107.08588","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"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":"text"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":19,"referenced_works":["https://openalex.org/W2006471615","https://openalex.org/W2122860281","https://openalex.org/W2194775991","https://openalex.org/W2307480936","https://openalex.org/W2319454238","https://openalex.org/W2548122763","https://openalex.org/W2557738935","https://openalex.org/W2769041395","https://openalex.org/W2903440991","https://openalex.org/W2911424454","https://openalex.org/W2915915402","https://openalex.org/W2963466845","https://openalex.org/W2963735582","https://openalex.org/W2966732283","https://openalex.org/W2988966271","https://openalex.org/W3004898594","https://openalex.org/W3008570669","https://openalex.org/W3030888939","https://openalex.org/W6768662356"],"related_works":[],"abstract_inverted_index":{"High-quality":[0],"labels":[1,20,38,104],"are":[2,26,39],"expensive":[3],"to":[4,28,47,82,105,114,128,135],"obtain":[5],"for":[6,99],"many":[7],"machine":[8],"learning":[9],"tasks,":[10],"such":[11],"as":[12],"medical":[13],"image":[14],"classification":[15],"tasks.":[16],"Therefore,":[17],"probabilistic":[18],"(weak)":[19],"produced":[21],"by":[22,43],"weak":[23,37],"supervision":[24],"tools":[25],"used":[27],"seed":[29],"a":[30,65],"process":[31],"in":[32],"which":[33,74,92],"influential":[34,96,131],"samples":[35,98,157],"with":[36],"identified":[40],"and":[41,57,70,101,120,133,171],"cleaned":[42,103],"several":[44],"human":[45,87,111,150],"annotators":[46,151],"improve":[48],"the":[49,54,77,84,94,107,116,121,138,143,177],"model":[50,122,169,179,192],"performance.":[51],"To":[52],"lower":[53],"overall":[55,168],"cost":[56,85,108],"computational":[58],"overhead":[59],"of":[60,76,86,109,156,163],"this":[61],"process,":[62],"we":[63,89,125,141],"propose":[64],"solution":[66],"called":[67],"CHEF":[68],"(CHEap":[69],"Fast":[71],"label":[72,145],"cleaning),":[73],"consists":[75],"following":[78],"three":[79],"components.":[80],"First,":[81],"reduce":[83],"annotators,":[88],"use":[90,126],"INFL,":[91],"prioritizes":[93],"most":[95],"training":[97],"cleaning":[100,146],"provides":[102],"save":[106],"one":[110,160],"annotator.":[112],"Second,":[113],"accelerate":[115],"sample":[117],"selector":[118],"phase":[119],"constructor":[123],"phase,":[124],"Increm-INFL":[127],"incrementally":[129,136],"produce":[130],"samples,":[132],"DeltaGrad-L":[134],"update":[137],"model.":[139],"Third,":[140],"redesign":[142],"typical":[144],"pipeline":[147],"so":[148],"that":[149,187],"iteratively":[152],"clean":[153],"smaller":[154],"batch":[155,162],"rather":[158],"than":[159],"big":[161],"samples.":[164],"This":[165],"yields":[166],"better":[167],"performance":[170,180,194],"enables":[172],"possible":[173],"early":[174],"termination":[175],"when":[176],"expected":[178],"has":[181],"been":[182],"achieved.":[183],"Extensive":[184],"experiments":[185],"show":[186],"our":[188],"approach":[189],"gives":[190],"good":[191],"prediction":[193],"while":[195],"achieving":[196],"significant":[197],"speed-ups.":[198]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":3}],"updated_date":"2026-05-21T06:26:12.895304","created_date":"2021-08-02T00:00:00"}