{"id":"https://openalex.org/W2548122763","doi":"https://doi.org/10.14778/2994509.2994514","title":"ActiveClean","display_name":"ActiveClean","publication_year":2016,"publication_date":"2016-08-01","ids":{"openalex":"https://openalex.org/W2548122763","doi":"https://doi.org/10.14778/2994509.2994514","mag":"2548122763"},"language":"en","primary_location":{"id":"doi:10.14778/2994509.2994514","is_oa":false,"landing_page_url":"https://doi.org/10.14778/2994509.2994514","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":["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/A5018480426","display_name":"Sanjay Krishnan","orcid":"https://orcid.org/0000-0001-6968-4090"},"institutions":[{"id":"https://openalex.org/I134446601","display_name":"Berkeley College","ror":"https://ror.org/02xewxa75","country_code":"US","type":"education","lineage":["https://openalex.org/I134446601"]},{"id":"https://openalex.org/I95457486","display_name":"University of California, Berkeley","ror":"https://ror.org/01an7q238","country_code":"US","type":"education","lineage":["https://openalex.org/I95457486"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Sanjay Krishnan","raw_affiliation_strings":["UC Berkeley"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"UC Berkeley","institution_ids":["https://openalex.org/I134446601","https://openalex.org/I95457486"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101850961","display_name":"Jiannan Wang","orcid":"https://orcid.org/0009-0002-8978-312X"},"institutions":[{"id":"https://openalex.org/I18014758","display_name":"Simon Fraser University","ror":"https://ror.org/0213rcc28","country_code":"CA","type":"education","lineage":["https://openalex.org/I18014758"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"Jiannan Wang","raw_affiliation_strings":["Simon Fraser University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Simon Fraser University","institution_ids":["https://openalex.org/I18014758"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5049016095","display_name":"Eugene Wu","orcid":"https://orcid.org/0000-0003-4254-6688"},"institutions":[{"id":"https://openalex.org/I78577930","display_name":"Columbia University","ror":"https://ror.org/00hj8s172","country_code":"US","type":"education","lineage":["https://openalex.org/I78577930"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Eugene Wu","raw_affiliation_strings":["Columbia University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Columbia University","institution_ids":["https://openalex.org/I78577930"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102019638","display_name":"Michael J. Franklin","orcid":"https://orcid.org/0000-0003-3332-8574"},"institutions":[{"id":"https://openalex.org/I134446601","display_name":"Berkeley College","ror":"https://ror.org/02xewxa75","country_code":"US","type":"education","lineage":["https://openalex.org/I134446601"]},{"id":"https://openalex.org/I95457486","display_name":"University of California, Berkeley","ror":"https://ror.org/01an7q238","country_code":"US","type":"education","lineage":["https://openalex.org/I95457486"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Michael J. Franklin","raw_affiliation_strings":["UC Berkeley"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"UC Berkeley","institution_ids":["https://openalex.org/I134446601","https://openalex.org/I95457486"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5050342525","display_name":"Ken Goldberg","orcid":"https://orcid.org/0000-0002-2661-4524"},"institutions":[{"id":"https://openalex.org/I134446601","display_name":"Berkeley College","ror":"https://ror.org/02xewxa75","country_code":"US","type":"education","lineage":["https://openalex.org/I134446601"]},{"id":"https://openalex.org/I95457486","display_name":"University of California, Berkeley","ror":"https://ror.org/01an7q238","country_code":"US","type":"education","lineage":["https://openalex.org/I95457486"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Ken Goldberg","raw_affiliation_strings":["UC Berkeley"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"UC Berkeley","institution_ids":["https://openalex.org/I134446601","https://openalex.org/I95457486"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":4,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":33.9824,"has_fulltext":false,"cited_by_count":249,"citation_normalized_percentile":{"value":0.99643397,"is_in_top_1_percent":true,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":90,"max":100},"biblio":{"volume":"9","issue":"12","first_page":"948","last_page":"959"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12535","display_name":"Machine Learning and Data Classification","score":0.9835000038146973,"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":0.9835000038146973,"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/T10136","display_name":"Statistical Methods and Inference","score":0.982200026512146,"subfield":{"id":"https://openalex.org/subfields/2613","display_name":"Statistics and Probability"},"field":{"id":"https://openalex.org/fields/26","display_name":"Mathematics"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T11719","display_name":"Data Quality and Management","score":0.9815999865531921,"subfield":{"id":"https://openalex.org/subfields/1803","display_name":"Management Science and Operations Research"},"field":{"id":"https://openalex.org/fields/18","display_name":"Decision Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/mnist-database","display_name":"MNIST database","score":0.8228068947792053},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7464317083358765},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.5770806670188904},{"id":"https://openalex.org/keywords/support-vector-machine","display_name":"Support vector machine","score":0.5233554244041443},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.48443368077278137},{"id":"https://openalex.org/keywords/convergence","display_name":"Convergence (economics)","score":0.48222410678863525},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.47470465302467346},{"id":"https://openalex.org/keywords/class","display_name":"Class (philosophy)","score":0.4600927233695984},{"id":"https://openalex.org/keywords/iterative-and-incremental-development","display_name":"Iterative and incremental development","score":0.421889990568161},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.40124645829200745},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.33930516242980957},{"id":"https://openalex.org/keywords/deep-learning","display_name":"Deep learning","score":0.1881864070892334}],"concepts":[{"id":"https://openalex.org/C190502265","wikidata":"https://www.wikidata.org/wiki/Q17069496","display_name":"MNIST database","level":3,"score":0.8228068947792053},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7464317083358765},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.5770806670188904},{"id":"https://openalex.org/C12267149","wikidata":"https://www.wikidata.org/wiki/Q282453","display_name":"Support vector machine","level":2,"score":0.5233554244041443},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.48443368077278137},{"id":"https://openalex.org/C2777303404","wikidata":"https://www.wikidata.org/wiki/Q759757","display_name":"Convergence (economics)","level":2,"score":0.48222410678863525},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.47470465302467346},{"id":"https://openalex.org/C2777212361","wikidata":"https://www.wikidata.org/wiki/Q5127848","display_name":"Class (philosophy)","level":2,"score":0.4600927233695984},{"id":"https://openalex.org/C143587482","wikidata":"https://www.wikidata.org/wiki/Q1543216","display_name":"Iterative and incremental development","level":2,"score":0.421889990568161},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.40124645829200745},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.33930516242980957},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.1881864070892334},{"id":"https://openalex.org/C50522688","wikidata":"https://www.wikidata.org/wiki/Q189833","display_name":"Economic growth","level":1,"score":0.0},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"id":"https://openalex.org/C151730666","wikidata":"https://www.wikidata.org/wiki/Q7205","display_name":"Paleontology","level":1,"score":0.0},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0},{"id":"https://openalex.org/C115903868","wikidata":"https://www.wikidata.org/wiki/Q80993","display_name":"Software engineering","level":1,"score":0.0},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.14778/2994509.2994514","is_oa":false,"landing_page_url":"https://doi.org/10.14778/2994509.2994514","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"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Industry, innovation and infrastructure","score":0.5600000023841858,"id":"https://metadata.un.org/sdg/9"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":42,"referenced_works":["https://openalex.org/W1551385575","https://openalex.org/W1579798859","https://openalex.org/W1610496399","https://openalex.org/W1842094663","https://openalex.org/W1955857676","https://openalex.org/W1975184797","https://openalex.org/W1996848289","https://openalex.org/W2044102377","https://openalex.org/W2053503869","https://openalex.org/W2063103859","https://openalex.org/W2089206172","https://openalex.org/W2097995023","https://openalex.org/W2099637074","https://openalex.org/W2107966677","https://openalex.org/W2117400432","https://openalex.org/W2129566246","https://openalex.org/W2130062883","https://openalex.org/W2134130436","https://openalex.org/W2143891888","https://openalex.org/W2151773168","https://openalex.org/W2159294971","https://openalex.org/W2163598528","https://openalex.org/W2165053334","https://openalex.org/W2165698076","https://openalex.org/W2165798027","https://openalex.org/W2167421362","https://openalex.org/W2168440643","https://openalex.org/W2243458913","https://openalex.org/W2292361954","https://openalex.org/W2296272300","https://openalex.org/W2421097601","https://openalex.org/W2437990191","https://openalex.org/W2471080787","https://openalex.org/W2616345629","https://openalex.org/W2903158431","https://openalex.org/W2905472553","https://openalex.org/W6636177537","https://openalex.org/W6675063435","https://openalex.org/W6683272254","https://openalex.org/W6684327724","https://openalex.org/W6684402436","https://openalex.org/W6756615331"],"related_works":["https://openalex.org/W2950475743","https://openalex.org/W4386603768","https://openalex.org/W2886711096","https://openalex.org/W4380078352","https://openalex.org/W3046591097","https://openalex.org/W2590796488","https://openalex.org/W2734358244","https://openalex.org/W2750384547","https://openalex.org/W2809732489","https://openalex.org/W3088091256"],"abstract_inverted_index":{"Analysts":[0],"often":[1],"clean":[2],"dirty":[3,140],"data":[4,15,40,128],"iteratively--cleaning":[5],"some":[6],"data,":[7],"executing":[8],"the":[9,18,22,27,84,124],"analysis,":[10],"and":[11,49,74,76,99,106,136,150],"then":[12],"cleaning":[13,24,51,78,134],"more":[14,144],"based":[16],"on":[17,89,137],"results.":[19,85],"We":[20,42,86],"explore":[21],"iterative":[23,50],"process":[25],"in":[26,52],"context":[28],"of":[29,39,65,127],"statistical":[30,53],"model":[31,118],"training,":[32],"which":[33,45],"is":[34],"an":[35,62],"increasingly":[36],"popular":[37],"form":[38],"analytics.":[41],"propose":[43],"ActiveClean,":[44],"allows":[46],"for":[47,123,131],"progressive":[48],"modeling":[54],"problems":[55],"while":[56],"preserving":[57],"convergence":[58],"guarantees.":[59],"ActiveClean":[60,88,142],"supports":[61],"important":[63],"class":[64],"models":[66,70,146],"called":[67],"convex":[68],"loss":[69],"(e.g.,":[71],"linear":[72],"regression":[73],"SVMs),":[75],"prioritizes":[77],"those":[79],"records":[80],"likely":[81],"to":[82],"affect":[83],"evaluate":[87],"five":[90],"real-world":[91],"datasets":[92],"UCI":[93,95],"Adult,":[94],"EEG,":[96],"MNIST,":[97],"IMDB,":[98],"Dollars":[100],"For":[101],"Docs":[102],"with":[103],"both":[104],"real":[105,139],"synthetic":[107],"errors.":[108],"The":[109],"results":[110],"show":[111],"that":[112],"our":[113],"proposed":[114],"optimizations":[115],"can":[116],"improve":[117],"accuracy":[119],"by":[120],"up-to":[121],"2.5x":[122],"same":[125],"amount":[126],"cleaned.":[129],"Furthermore":[130],"a":[132],"fixed":[133],"budget":[135],"all":[138],"datasets,":[141],"returns":[143],"accurate":[145],"than":[147],"uniform":[148],"sampling":[149],"Active":[151],"Learning.":[152]},"counts_by_year":[{"year":2026,"cited_by_count":11},{"year":2025,"cited_by_count":30},{"year":2024,"cited_by_count":28},{"year":2023,"cited_by_count":28},{"year":2022,"cited_by_count":24},{"year":2021,"cited_by_count":41},{"year":2020,"cited_by_count":25},{"year":2019,"cited_by_count":37},{"year":2018,"cited_by_count":15},{"year":2017,"cited_by_count":9},{"year":2016,"cited_by_count":1}],"updated_date":"2026-07-26T07:53:14.480251","created_date":"2016-11-11T00:00:00"}