{"id":"https://openalex.org/W2087909221","doi":"https://doi.org/10.1145/2588555.2610531","title":"Dynamically optimizing queries over large scale data platforms","display_name":"Dynamically optimizing queries over large scale data platforms","publication_year":2014,"publication_date":"2014-06-18","ids":{"openalex":"https://openalex.org/W2087909221","doi":"https://doi.org/10.1145/2588555.2610531","mag":"2087909221"},"language":"en","primary_location":{"id":"doi:10.1145/2588555.2610531","is_oa":false,"landing_page_url":"https://doi.org/10.1145/2588555.2610531","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2014 ACM SIGMOD International Conference on Management of Data","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/A5053293674","display_name":"Konstantinos Karanasos","orcid":"https://orcid.org/0009-0007-6975-2568"},"institutions":[{"id":"https://openalex.org/I4210085935","display_name":"IBM Research - Almaden","ror":"https://ror.org/005w8dd04","country_code":"US","type":"facility","lineage":["https://openalex.org/I1341412227","https://openalex.org/I4210085935","https://openalex.org/I4210114115"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Konstantinos Karanasos","raw_affiliation_strings":["IBM Research - Almaden, San Jose, CA, USA"],"affiliations":[{"raw_affiliation_string":"IBM Research - Almaden, San Jose, CA, USA","institution_ids":["https://openalex.org/I4210085935"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5003379355","display_name":"Andrey Balmin","orcid":"https://orcid.org/0000-0003-3034-6259"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Andrey Balmin","raw_affiliation_strings":["GraphSQL, Mountain View, CA, USA"],"affiliations":[{"raw_affiliation_string":"GraphSQL, Mountain View, CA, USA","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5034833360","display_name":"M. Kutsch","orcid":null},"institutions":[{"id":"https://openalex.org/I1311269955","display_name":"Apple (Israel)","ror":"https://ror.org/04ehjr030","country_code":"IL","type":"company","lineage":["https://openalex.org/I1311269955","https://openalex.org/I4210153776"]},{"id":"https://openalex.org/I4210153776","display_name":"Apple (United States)","ror":"https://ror.org/059hsda18","country_code":"US","type":"company","lineage":["https://openalex.org/I4210153776"]}],"countries":["IL","US"],"is_corresponding":false,"raw_author_name":"Marcel Kutsch","raw_affiliation_strings":["Apple Inc., Cupertino, CA, USA","[Apple, Inc, Cupertino, CA, USA]"],"affiliations":[{"raw_affiliation_string":"Apple Inc., Cupertino, CA, USA","institution_ids":["https://openalex.org/I4210153776"]},{"raw_affiliation_string":"[Apple, Inc, Cupertino, CA, USA]","institution_ids":["https://openalex.org/I1311269955"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5070638387","display_name":"Fatma \u00d6zcan","orcid":"https://orcid.org/0000-0002-4418-4724"},"institutions":[{"id":"https://openalex.org/I4210085935","display_name":"IBM Research - Almaden","ror":"https://ror.org/005w8dd04","country_code":"US","type":"facility","lineage":["https://openalex.org/I1341412227","https://openalex.org/I4210085935","https://openalex.org/I4210114115"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Fatma Ozcan","raw_affiliation_strings":["IBM Research - Almaden, San Jose, CA, USA"],"affiliations":[{"raw_affiliation_string":"IBM Research - Almaden, San Jose, CA, USA","institution_ids":["https://openalex.org/I4210085935"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5065055611","display_name":"Vuk Ercegovac","orcid":null},"institutions":[{"id":"https://openalex.org/I1291425158","display_name":"Google (United States)","ror":"https://ror.org/00njsd438","country_code":"US","type":"company","lineage":["https://openalex.org/I1291425158","https://openalex.org/I4210128969"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Vuk Ercegovac","raw_affiliation_strings":["Google, Mountain View, CA, USA"],"affiliations":[{"raw_affiliation_string":"Google, Mountain View, CA, USA","institution_ids":["https://openalex.org/I1291425158"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5045111126","display_name":"Chunyang Xia","orcid":"https://orcid.org/0000-0002-3943-1321"},"institutions":[{"id":"https://openalex.org/I1341412227","display_name":"IBM (United States)","ror":"https://ror.org/05hh8d621","country_code":"US","type":"company","lineage":["https://openalex.org/I1341412227"]},{"id":"https://openalex.org/I4210148712","display_name":"Silicon Valley University","ror":"https://ror.org/04jk6hn97","country_code":"US","type":"education","lineage":["https://openalex.org/I4210148712"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Chunyang Xia","raw_affiliation_strings":["IBM Silicon Valley Lab, San Jose, CA, USA","IBM Silicon Valley Lab., San Jose, CA, USA"],"affiliations":[{"raw_affiliation_string":"IBM Silicon Valley Lab, San Jose, CA, USA","institution_ids":["https://openalex.org/I4210148712"]},{"raw_affiliation_string":"IBM Silicon Valley Lab., San Jose, CA, USA","institution_ids":["https://openalex.org/I1341412227"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5041639478","display_name":"Jesse Jackson","orcid":"https://orcid.org/0000-0003-1870-5757"},"institutions":[{"id":"https://openalex.org/I1341412227","display_name":"IBM (United States)","ror":"https://ror.org/05hh8d621","country_code":"US","type":"company","lineage":["https://openalex.org/I1341412227"]},{"id":"https://openalex.org/I4210148712","display_name":"Silicon Valley University","ror":"https://ror.org/04jk6hn97","country_code":"US","type":"education","lineage":["https://openalex.org/I4210148712"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Jesse Jackson","raw_affiliation_strings":["IBM Silicon Valley Lab, San Jose, CA, USA","IBM Silicon Valley Lab., San Jose, CA, USA"],"affiliations":[{"raw_affiliation_string":"IBM Silicon Valley Lab, San Jose, CA, USA","institution_ids":["https://openalex.org/I4210148712"]},{"raw_affiliation_string":"IBM Silicon Valley Lab., San Jose, CA, USA","institution_ids":["https://openalex.org/I1341412227"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":7,"corresponding_author_ids":["https://openalex.org/A5053293674"],"corresponding_institution_ids":["https://openalex.org/I4210085935"],"apc_list":null,"apc_paid":null,"fwci":3.4481,"has_fulltext":false,"cited_by_count":31,"citation_normalized_percentile":{"value":0.93345158,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"943","last_page":"954"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10317","display_name":"Advanced Database Systems and Queries","score":0.9994000196456909,"subfield":{"id":"https://openalex.org/subfields/1705","display_name":"Computer Networks and Communications"},"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/T10317","display_name":"Advanced Database Systems and Queries","score":0.9994000196456909,"subfield":{"id":"https://openalex.org/subfields/1705","display_name":"Computer Networks and Communications"},"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/T11106","display_name":"Data Management and Algorithms","score":0.9994000196456909,"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/T10101","display_name":"Cloud Computing and Resource Management","score":0.9991999864578247,"subfield":{"id":"https://openalex.org/subfields/1710","display_name":"Information Systems"},"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":0.8816496133804321},{"id":"https://openalex.org/keywords/query-optimization","display_name":"Query optimization","score":0.7570275664329529},{"id":"https://openalex.org/keywords/query-plan","display_name":"Query plan","score":0.6904406547546387},{"id":"https://openalex.org/keywords/big-data","display_name":"Big data","score":0.5258631706237793},{"id":"https://openalex.org/keywords/sargable","display_name":"Sargable","score":0.5243513584136963},{"id":"https://openalex.org/keywords/relational-database","display_name":"Relational database","score":0.49216049909591675},{"id":"https://openalex.org/keywords/scale","display_name":"Scale (ratio)","score":0.4524955153465271},{"id":"https://openalex.org/keywords/volume","display_name":"Volume (thermodynamics)","score":0.42482465505599976},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.37979522347450256},{"id":"https://openalex.org/keywords/database","display_name":"Database","score":0.3522772789001465},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.31784921884536743},{"id":"https://openalex.org/keywords/web-search-query","display_name":"Web search query","score":0.24624702334403992},{"id":"https://openalex.org/keywords/search-engine","display_name":"Search engine","score":0.16429385542869568}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8816496133804321},{"id":"https://openalex.org/C157692150","wikidata":"https://www.wikidata.org/wiki/Q2919848","display_name":"Query optimization","level":2,"score":0.7570275664329529},{"id":"https://openalex.org/C2779729312","wikidata":"https://www.wikidata.org/wiki/Q784232","display_name":"Query plan","level":5,"score":0.6904406547546387},{"id":"https://openalex.org/C75684735","wikidata":"https://www.wikidata.org/wiki/Q858810","display_name":"Big data","level":2,"score":0.5258631706237793},{"id":"https://openalex.org/C192939062","wikidata":"https://www.wikidata.org/wiki/Q104840822","display_name":"Sargable","level":4,"score":0.5243513584136963},{"id":"https://openalex.org/C5655090","wikidata":"https://www.wikidata.org/wiki/Q192588","display_name":"Relational database","level":2,"score":0.49216049909591675},{"id":"https://openalex.org/C2778755073","wikidata":"https://www.wikidata.org/wiki/Q10858537","display_name":"Scale (ratio)","level":2,"score":0.4524955153465271},{"id":"https://openalex.org/C20556612","wikidata":"https://www.wikidata.org/wiki/Q4469374","display_name":"Volume (thermodynamics)","level":2,"score":0.42482465505599976},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.37979522347450256},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.3522772789001465},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.31784921884536743},{"id":"https://openalex.org/C164120249","wikidata":"https://www.wikidata.org/wiki/Q995982","display_name":"Web search query","level":3,"score":0.24624702334403992},{"id":"https://openalex.org/C97854310","wikidata":"https://www.wikidata.org/wiki/Q19541","display_name":"Search engine","level":2,"score":0.16429385542869568},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","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:10.1145/2588555.2610531","is_oa":false,"landing_page_url":"https://doi.org/10.1145/2588555.2610531","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2014 ACM SIGMOD International Conference on Management of Data","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/9","display_name":"Industry, innovation and infrastructure","score":0.5400000214576721}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":44,"referenced_works":["https://openalex.org/W135863099","https://openalex.org/W1493893823","https://openalex.org/W1535431348","https://openalex.org/W1575324001","https://openalex.org/W1975731516","https://openalex.org/W1985229168","https://openalex.org/W1988504473","https://openalex.org/W1992363839","https://openalex.org/W1997020216","https://openalex.org/W2007069074","https://openalex.org/W2023195086","https://openalex.org/W2027720485","https://openalex.org/W2036971997","https://openalex.org/W2037168816","https://openalex.org/W2041563709","https://openalex.org/W2043099794","https://openalex.org/W2052312648","https://openalex.org/W2058991275","https://openalex.org/W2060280513","https://openalex.org/W2060883486","https://openalex.org/W2066140355","https://openalex.org/W2074013691","https://openalex.org/W2079806729","https://openalex.org/W2090066046","https://openalex.org/W2090452820","https://openalex.org/W2102489964","https://openalex.org/W2110086534","https://openalex.org/W2113124441","https://openalex.org/W2114303224","https://openalex.org/W2131975293","https://openalex.org/W2139072600","https://openalex.org/W2142031898","https://openalex.org/W2143452574","https://openalex.org/W2151065878","https://openalex.org/W2153329411","https://openalex.org/W2158237121","https://openalex.org/W2164507334","https://openalex.org/W2173213060","https://openalex.org/W2262278669","https://openalex.org/W2397097813","https://openalex.org/W2766000922","https://openalex.org/W4206606839","https://openalex.org/W6605485969","https://openalex.org/W6632229964"],"related_works":["https://openalex.org/W4361194359","https://openalex.org/W2006459955","https://openalex.org/W2955368753","https://openalex.org/W1977331029","https://openalex.org/W2941854747","https://openalex.org/W3125756434","https://openalex.org/W203907944","https://openalex.org/W1608254253","https://openalex.org/W4386051213","https://openalex.org/W2992414350"],"abstract_inverted_index":{"Enterprises":[0],"are":[1,61,186],"adapting":[2],"large-scale":[3],"data":[4,55,139],"processing":[5],"platforms,":[6],"such":[7],"as":[8,169,189],"Hadoop,":[9],"to":[10,29,48,53,64,140,152,194],"gain":[11],"actionable":[12],"insights":[13],"from":[14],"their":[15],"\"big":[16],"data\".":[17],"Query":[18],"optimization":[19,77,163],"is":[20],"still":[21],"an":[22,154],"open":[23],"challenge":[24],"in":[25,83,165],"this":[26,84,101],"environment":[27],"due":[28],"the":[30,54,65,88,132,138,172,202],"volume":[31],"and":[32,39,112,143,192],"heterogeneity":[33],"of":[34,131,137,171],"data,":[35],"comprising":[36],"both":[37],"structured":[38],"un/semi-structured":[40],"datasets.":[41,99],"Moreover,":[42],"it":[43],"has":[44],"become":[45],"common":[46],"practice":[47],"push":[49],"business":[50],"logic":[51],"close":[52],"via":[56],"user-defined":[57],"functions":[58],"(UDFs),":[59],"which":[60,128,166],"usually":[62],"opaque":[63],"optimizer,":[66],"further":[67],"complicating":[68],"cost-based":[69,146],"optimization.":[70],"As":[71],"a":[72,135,145,161],"result,":[73],"classical":[74],"relational":[75],"query":[76,92,133,156,206],"techniques":[78,106,182],"do":[79],"not":[80],"fit":[81],"well":[82],"setting,":[85],"while":[86],"at":[87,187],"same":[89],"time,":[90],"suboptimal":[91],"plans":[93,167,184],"can":[94],"be":[95],"disastrous":[96],"with":[97],"large":[98,121],"In":[100],"paper,":[102],"we":[103,159],"propose":[104],"new":[105],"that":[107,148,180,185],"take":[108],"into":[109],"account":[110],"UDFs":[111],"correlations":[113],"between":[114],"relations":[115],"for":[116,198],"optimizing":[117],"queries":[118,173],"running":[119],"on":[120],"scale":[122],"clusters.":[123],"We":[124],"introduce":[125],"\"pilot":[126],"runs\",":[127],"execute":[129],"part":[130],"over":[134],"sample":[136],"estimate":[141],"selectivities,":[142],"employ":[144],"optimizer":[147],"uses":[149],"these":[150],"selectivities":[151],"choose":[153],"initial":[155],"plan.":[157],"Then,":[158],"follow":[160],"dynamic":[162],"approach,":[164],"evolve":[168],"parts":[170],"get":[174],"executed.":[175],"Our":[176],"experimental":[177],"results":[178],"show":[179],"our":[181],"produce":[183],"least":[188],"good":[190],"as,":[191],"up":[193],"2x":[195],"(4x)":[196],"better":[197],"Jaql":[199],"(Hive)":[200],"than,":[201],"best":[203],"hand-written":[204],"left-deep":[205],"plans.":[207]},"counts_by_year":[{"year":2023,"cited_by_count":1},{"year":2022,"cited_by_count":1},{"year":2021,"cited_by_count":5},{"year":2020,"cited_by_count":5},{"year":2019,"cited_by_count":2},{"year":2018,"cited_by_count":7},{"year":2016,"cited_by_count":6},{"year":2015,"cited_by_count":3},{"year":2014,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}