{"id":"https://openalex.org/W2750756391","doi":"https://doi.org/10.14778/3137628.3137641","title":"Query optimization for dynamic imputation","display_name":"Query optimization for dynamic imputation","publication_year":2017,"publication_date":"2017-08-01","ids":{"openalex":"https://openalex.org/W2750756391","doi":"https://doi.org/10.14778/3137628.3137641","mag":"2750756391"},"language":"en","primary_location":{"id":"doi:10.14778/3137628.3137641","is_oa":false,"landing_page_url":"https://doi.org/10.14778/3137628.3137641","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":true,"oa_status":"green","oa_url":"https://hdl.handle.net/1721.1/137765","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5046282128","display_name":"Jos\u00e9 Cambronero","orcid":"https://orcid.org/0000-0002-0713-6141"},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Jos\u00e9 Cambronero","raw_affiliation_strings":["MIT CSAIL"],"affiliations":[{"raw_affiliation_string":"MIT CSAIL","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5007050759","display_name":"John Feser","orcid":"https://orcid.org/0000-0001-8577-1784"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"John K. Feser","raw_affiliation_strings":["MIT CSAIL"],"affiliations":[{"raw_affiliation_string":"MIT CSAIL","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5103970214","display_name":"Micah J. Smith","orcid":null},"institutions":[{"id":"https://openalex.org/I4210109586","display_name":"Moscow Institute of Thermal Technology","ror":"https://ror.org/021es5e59","country_code":"RU","type":"facility","lineage":["https://openalex.org/I4210109586"]}],"countries":["RU"],"is_corresponding":false,"raw_author_name":"Micah J. Smith","raw_affiliation_strings":["MIT LIDS"],"affiliations":[{"raw_affiliation_string":"MIT LIDS","institution_ids":["https://openalex.org/I4210109586"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5037742794","display_name":"Samuel Madden","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Samuel Madden","raw_affiliation_strings":["MIT CSAIL"],"affiliations":[{"raw_affiliation_string":"MIT CSAIL","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5046282128"],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":2.9827,"has_fulltext":false,"cited_by_count":42,"citation_normalized_percentile":{"value":0.92325502,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":90,"max":99},"biblio":{"volume":"10","issue":"11","first_page":"1310","last_page":"1321"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11106","display_name":"Data Management and Algorithms","score":0.995199978351593,"subfield":{"id":"https://openalex.org/subfields/1711","display_name":"Signal Processing"},"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/T11106","display_name":"Data Management and Algorithms","score":0.995199978351593,"subfield":{"id":"https://openalex.org/subfields/1711","display_name":"Signal Processing"},"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/T11719","display_name":"Data Quality and Management","score":0.9927999973297119,"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"}},{"id":"https://openalex.org/T12205","display_name":"Time Series Analysis and Forecasting","score":0.9886000156402588,"subfield":{"id":"https://openalex.org/subfields/1711","display_name":"Signal Processing"},"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/imputation","display_name":"Imputation (statistics)","score":0.9140069484710693},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7965353727340698},{"id":"https://openalex.org/keywords/tuple","display_name":"Tuple","score":0.6686205863952637},{"id":"https://openalex.org/keywords/missing-data","display_name":"Missing data","score":0.6673113703727722},{"id":"https://openalex.org/keywords/usability","display_name":"Usability","score":0.574619710445404},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.5432682037353516},{"id":"https://openalex.org/keywords/on-the-fly","display_name":"On the fly","score":0.541392982006073},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.38425105810165405},{"id":"https://openalex.org/keywords/database","display_name":"Database","score":0.32724636793136597},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.11455070972442627},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.10116484761238098}],"concepts":[{"id":"https://openalex.org/C58041806","wikidata":"https://www.wikidata.org/wiki/Q1660484","display_name":"Imputation (statistics)","level":3,"score":0.9140069484710693},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7965353727340698},{"id":"https://openalex.org/C118930307","wikidata":"https://www.wikidata.org/wiki/Q600590","display_name":"Tuple","level":2,"score":0.6686205863952637},{"id":"https://openalex.org/C9357733","wikidata":"https://www.wikidata.org/wiki/Q6878417","display_name":"Missing data","level":2,"score":0.6673113703727722},{"id":"https://openalex.org/C170130773","wikidata":"https://www.wikidata.org/wiki/Q216378","display_name":"Usability","level":2,"score":0.574619710445404},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.5432682037353516},{"id":"https://openalex.org/C2781020372","wikidata":"https://www.wikidata.org/wiki/Q533093","display_name":"On the fly","level":2,"score":0.541392982006073},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.38425105810165405},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.32724636793136597},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.11455070972442627},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.10116484761238098},{"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/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.0},{"id":"https://openalex.org/C118615104","wikidata":"https://www.wikidata.org/wiki/Q121416","display_name":"Discrete mathematics","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.14778/3137628.3137641","is_oa":false,"landing_page_url":"https://doi.org/10.14778/3137628.3137641","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:dspace.mit.edu:1721.1/137765","is_oa":true,"landing_page_url":"https://hdl.handle.net/1721.1/137765","pdf_url":null,"source":{"id":"https://openalex.org/S4306400425","display_name":"DSpace@MIT (Massachusetts Institute of Technology)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I63966007","host_organization_name":"Massachusetts Institute of Technology","host_organization_lineage":["https://openalex.org/I63966007"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"The Proceedings of the VLDB Endowment","raw_type":"http://purl.org/eprint/type/ConferencePaper"}],"best_oa_location":{"id":"pmh:oai:dspace.mit.edu:1721.1/137765","is_oa":true,"landing_page_url":"https://hdl.handle.net/1721.1/137765","pdf_url":null,"source":{"id":"https://openalex.org/S4306400425","display_name":"DSpace@MIT (Massachusetts Institute of Technology)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I63966007","host_organization_name":"Massachusetts Institute of Technology","host_organization_lineage":["https://openalex.org/I63966007"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"The Proceedings of the VLDB Endowment","raw_type":"http://purl.org/eprint/type/ConferencePaper"},"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320326435","display_name":"Uniwersytet Medyczny im. Karola Marcinkowskiego w Poznaniu","ror":"https://ror.org/02zbb2597"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":30,"referenced_works":["https://openalex.org/W163027401","https://openalex.org/W1502624642","https://openalex.org/W1504694836","https://openalex.org/W1570448133","https://openalex.org/W1603000516","https://openalex.org/W1680392829","https://openalex.org/W1789812421","https://openalex.org/W1972585091","https://openalex.org/W1981457167","https://openalex.org/W2010272308","https://openalex.org/W2048665112","https://openalex.org/W2060370171","https://openalex.org/W2084807986","https://openalex.org/W2100358124","https://openalex.org/W2115098571","https://openalex.org/W2119803607","https://openalex.org/W2125055259","https://openalex.org/W2131617151","https://openalex.org/W2160770893","https://openalex.org/W2169076391","https://openalex.org/W2210027199","https://openalex.org/W2266577992","https://openalex.org/W2337180559","https://openalex.org/W2962969461","https://openalex.org/W3102147710","https://openalex.org/W3140662957","https://openalex.org/W3146507833","https://openalex.org/W4253407506","https://openalex.org/W4253562113","https://openalex.org/W6679712532"],"related_works":["https://openalex.org/W2541565311","https://openalex.org/W3049453136","https://openalex.org/W2784019465","https://openalex.org/W2751555317","https://openalex.org/W569810835","https://openalex.org/W2900766238","https://openalex.org/W1973721774","https://openalex.org/W1513289763","https://openalex.org/W2112497756","https://openalex.org/W2750756391"],"abstract_inverted_index":{"Missing":[0],"values":[1,22,130],"are":[2,13],"common":[3],"in":[4],"data":[5,30],"analysis":[6],"and":[7,92],"present":[8],"a":[9,25,33,44],"usability":[10],"challenge.":[11],"Users":[12],"forced":[14],"to":[15,58],"pick":[16],"between":[17,90],"removing":[18],"tuples":[19,127],"with":[20,128],"missing":[21,129],"or":[23],"creating":[24],"cleaned":[26],"version":[27],"of":[28,70,137],"their":[29,61],"by":[31,119],"applying":[32],"relatively":[34],"expensive":[35],"imputation":[36,42,71,111,117,141],"strategy.":[37],"Our":[38,82],"system,":[39],"ImputeDB,":[40],"incorporates":[41],"into":[43],"cost-based":[45],"query":[46,87,107,133],"optimizer,":[47],"performing":[48],"necessary":[49],"imputations":[50],"on-the-fly":[51,110,140],"for":[52],"each":[53],"query.":[54],"This":[55],"allows":[56],"users":[57],"immediately":[59],"explore":[60],"data,":[62,139],"while":[63,125],"the":[64,67,99,106,114,138],"system":[65],"picks":[66],"optimal":[68],"placement":[69],"operations.":[72],"We":[73],"evaluate":[74],"this":[75],"approach":[76,118],"on":[77],"three":[78],"real-world":[79],"survey-based":[80],"datasets.":[81],"experiments":[83],"show":[84,104,123],"that":[85,105,124,131],"our":[86],"plans":[88],"execute":[89],"10":[91],"140":[93],"times":[94],"faster":[95],"than":[96],"first":[97],"imputing":[98],"base":[100],"tables.":[101],"Furthermore,":[102],"we":[103,122],"results":[108],"from":[109,113],"differ":[112],"traditional":[115],"base-table":[116],"0--8%.":[120],"Finally,":[121],"dropping":[126],"fail":[132],"constraints":[134],"discards":[135],"6--78%":[136],"loses":[142],"only":[143],"0--21%.":[144]},"counts_by_year":[{"year":2025,"cited_by_count":8},{"year":2024,"cited_by_count":4},{"year":2023,"cited_by_count":10},{"year":2022,"cited_by_count":1},{"year":2021,"cited_by_count":3},{"year":2020,"cited_by_count":6},{"year":2019,"cited_by_count":8},{"year":2018,"cited_by_count":2}],"updated_date":"2026-04-04T16:13:02.066488","created_date":"2025-10-10T00:00:00"}