{"id":"https://openalex.org/W4281626245","doi":"https://doi.org/10.1145/3514221.3526141","title":"End-to-end Optimization of Machine Learning Prediction Queries","display_name":"End-to-end Optimization of Machine Learning Prediction Queries","publication_year":2022,"publication_date":"2022-06-10","ids":{"openalex":"https://openalex.org/W4281626245","doi":"https://doi.org/10.1145/3514221.3526141"},"language":"en","primary_location":{"id":"doi:10.1145/3514221.3526141","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3514221.3526141","pdf_url":null,"source":{"id":"https://openalex.org/S4363608845","display_name":"Proceedings of the 2022 International Conference on Management of Data","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 2022 International Conference on Management of Data","raw_type":"proceedings-article"},"type":"article","indexed_in":["arxiv","crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2206.00136","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5010089204","display_name":"Kwanghyun Park","orcid":"https://orcid.org/0000-0003-0757-2725"},"institutions":[{"id":"https://openalex.org/I1290206253","display_name":"Microsoft (United States)","ror":"https://ror.org/00d0nc645","country_code":"US","type":"company","lineage":["https://openalex.org/I1290206253"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Kwanghyun Park","raw_affiliation_strings":["Microsoft, Redmond, WA, USA"],"affiliations":[{"raw_affiliation_string":"Microsoft, Redmond, WA, USA","institution_ids":["https://openalex.org/I1290206253"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5011234989","display_name":"Karla Saur","orcid":"https://orcid.org/0009-0005-0741-5190"},"institutions":[{"id":"https://openalex.org/I1290206253","display_name":"Microsoft (United States)","ror":"https://ror.org/00d0nc645","country_code":"US","type":"company","lineage":["https://openalex.org/I1290206253"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Karla Saur","raw_affiliation_strings":["Microsoft, Redmond, WA, USA"],"affiliations":[{"raw_affiliation_string":"Microsoft, Redmond, WA, USA","institution_ids":["https://openalex.org/I1290206253"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5022818623","display_name":"Dalitso Banda","orcid":null},"institutions":[{"id":"https://openalex.org/I1290206253","display_name":"Microsoft (United States)","ror":"https://ror.org/00d0nc645","country_code":"US","type":"company","lineage":["https://openalex.org/I1290206253"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Dalitso Banda","raw_affiliation_strings":["Microsoft, Redmond, WA, USA"],"affiliations":[{"raw_affiliation_string":"Microsoft, Redmond, WA, USA","institution_ids":["https://openalex.org/I1290206253"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5061137265","display_name":"Rathijit Sen","orcid":"https://orcid.org/0000-0003-4736-2837"},"institutions":[{"id":"https://openalex.org/I1290206253","display_name":"Microsoft (United States)","ror":"https://ror.org/00d0nc645","country_code":"US","type":"company","lineage":["https://openalex.org/I1290206253"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Rathijit Sen","raw_affiliation_strings":["Microsoft, Madison, WI, USA"],"affiliations":[{"raw_affiliation_string":"Microsoft, Madison, WI, USA","institution_ids":["https://openalex.org/I1290206253"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5071206013","display_name":"Matteo Interlandi","orcid":"https://orcid.org/0000-0002-5756-8321"},"institutions":[{"id":"https://openalex.org/I1290206253","display_name":"Microsoft (United States)","ror":"https://ror.org/00d0nc645","country_code":"US","type":"company","lineage":["https://openalex.org/I1290206253"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Matteo Interlandi","raw_affiliation_strings":["Microsoft, Redmond, WA, USA"],"affiliations":[{"raw_affiliation_string":"Microsoft, Redmond, WA, USA","institution_ids":["https://openalex.org/I1290206253"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5053293674","display_name":"Konstantinos Karanasos","orcid":"https://orcid.org/0009-0007-6975-2568"},"institutions":[{"id":"https://openalex.org/I1290206253","display_name":"Microsoft (United States)","ror":"https://ror.org/00d0nc645","country_code":"US","type":"company","lineage":["https://openalex.org/I1290206253"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Konstantinos Karanasos","raw_affiliation_strings":["Microsoft, Redmond, WA, USA"],"affiliations":[{"raw_affiliation_string":"Microsoft, Redmond, WA, USA","institution_ids":["https://openalex.org/I1290206253"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":6,"corresponding_author_ids":["https://openalex.org/A5010089204"],"corresponding_institution_ids":["https://openalex.org/I1290206253"],"apc_list":null,"apc_paid":null,"fwci":5.263,"has_fulltext":true,"cited_by_count":38,"citation_normalized_percentile":{"value":0.96525097,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":94,"max":100},"biblio":{"volume":null,"issue":null,"first_page":"587","last_page":"601"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10101","display_name":"Cloud Computing and Resource Management","score":0.9954000115394592,"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"}},"topics":[{"id":"https://openalex.org/T10101","display_name":"Cloud Computing and Resource Management","score":0.9954000115394592,"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"}},{"id":"https://openalex.org/T10317","display_name":"Advanced Database Systems and Queries","score":0.9948999881744385,"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/T12292","display_name":"Graph Theory and Algorithms","score":0.9944000244140625,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"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":0.884088933467865},{"id":"https://openalex.org/keywords/speedup","display_name":"Speedup","score":0.7449550628662109},{"id":"https://openalex.org/keywords/sql","display_name":"SQL","score":0.5286664962768555},{"id":"https://openalex.org/keywords/spark","display_name":"SPARK (programming language)","score":0.47477957606315613},{"id":"https://openalex.org/keywords/analytics","display_name":"Analytics","score":0.4624192416667938},{"id":"https://openalex.org/keywords/graph","display_name":"Graph","score":0.45105424523353577},{"id":"https://openalex.org/keywords/online-analytical-processing","display_name":"Online analytical processing","score":0.43449339270591736},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4021201729774475},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.38215452432632446},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.3641367554664612},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.3327530026435852},{"id":"https://openalex.org/keywords/theoretical-computer-science","display_name":"Theoretical computer science","score":0.3030954897403717},{"id":"https://openalex.org/keywords/database","display_name":"Database","score":0.25470098853111267},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.25402724742889404}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.884088933467865},{"id":"https://openalex.org/C68339613","wikidata":"https://www.wikidata.org/wiki/Q1549489","display_name":"Speedup","level":2,"score":0.7449550628662109},{"id":"https://openalex.org/C510870499","wikidata":"https://www.wikidata.org/wiki/Q47607","display_name":"SQL","level":2,"score":0.5286664962768555},{"id":"https://openalex.org/C2781215313","wikidata":"https://www.wikidata.org/wiki/Q3493345","display_name":"SPARK (programming language)","level":2,"score":0.47477957606315613},{"id":"https://openalex.org/C79158427","wikidata":"https://www.wikidata.org/wiki/Q485396","display_name":"Analytics","level":2,"score":0.4624192416667938},{"id":"https://openalex.org/C132525143","wikidata":"https://www.wikidata.org/wiki/Q141488","display_name":"Graph","level":2,"score":0.45105424523353577},{"id":"https://openalex.org/C201932085","wikidata":"https://www.wikidata.org/wiki/Q642514","display_name":"Online analytical processing","level":3,"score":0.43449339270591736},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4021201729774475},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.38215452432632446},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3641367554664612},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.3327530026435852},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.3030954897403717},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.25470098853111267},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.25402724742889404},{"id":"https://openalex.org/C135572916","wikidata":"https://www.wikidata.org/wiki/Q193351","display_name":"Data warehouse","level":2,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1145/3514221.3526141","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3514221.3526141","pdf_url":null,"source":{"id":"https://openalex.org/S4363608845","display_name":"Proceedings of the 2022 International Conference on Management of Data","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 2022 International Conference on Management of Data","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2206.00136","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2206.00136","pdf_url":"https://arxiv.org/pdf/2206.00136","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:2206.00136","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2206.00136","pdf_url":"https://arxiv.org/pdf/2206.00136","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":[{"display_name":"Industry, innovation and infrastructure","id":"https://metadata.un.org/sdg/9","score":0.5}],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4281626245.pdf","grobid_xml":"https://content.openalex.org/works/W4281626245.grobid-xml"},"referenced_works_count":37,"referenced_works":["https://openalex.org/W410850256","https://openalex.org/W2032775418","https://openalex.org/W2038412523","https://openalex.org/W2044849727","https://openalex.org/W2070553391","https://openalex.org/W2078945459","https://openalex.org/W2090850279","https://openalex.org/W2295598076","https://openalex.org/W2430301697","https://openalex.org/W2547386789","https://openalex.org/W2604255113","https://openalex.org/W2612139288","https://openalex.org/W2612261081","https://openalex.org/W2743948853","https://openalex.org/W2768348081","https://openalex.org/W2786278116","https://openalex.org/W2807799957","https://openalex.org/W2962746093","https://openalex.org/W2963741525","https://openalex.org/W2971290973","https://openalex.org/W2992496917","https://openalex.org/W2997591727","https://openalex.org/W3029900615","https://openalex.org/W3044177535","https://openalex.org/W3082570516","https://openalex.org/W3084542178","https://openalex.org/W3085477028","https://openalex.org/W3086179797","https://openalex.org/W3106772683","https://openalex.org/W3123554940","https://openalex.org/W3165312848","https://openalex.org/W3175089547","https://openalex.org/W3176459841","https://openalex.org/W3196732841","https://openalex.org/W3197125869","https://openalex.org/W4251637954","https://openalex.org/W6614148910"],"related_works":["https://openalex.org/W2058965144","https://openalex.org/W2164382479","https://openalex.org/W2146343568","https://openalex.org/W98480971","https://openalex.org/W2150291671","https://openalex.org/W2558523485","https://openalex.org/W4379407450","https://openalex.org/W2905107896","https://openalex.org/W3191926225","https://openalex.org/W2895375519"],"abstract_inverted_index":{"Prediction":[0],"queries":[1,187],"are":[2],"widely":[3],"used":[4,164],"across":[5],"industries":[6],"to":[7,42,101,130,142,162,171,182,196,213,217],"perform":[8,43],"advanced":[9],"analytics":[10],"and":[11,30,79,93,126,150,152,191,198],"draw":[12],"insights":[13],"from":[14],"data.":[15],"They":[16],"include":[17],"a":[18,31,63,85,97],"data":[19,78,92,117],"processing":[20],"part":[21,35,118,129,167],"(e.g.,":[22],"for":[23,57,66,165,202],"joining,":[24],"filtering,":[25],"cleaning,":[26],"featurizing":[27],"the":[28,72,116,120,123,127,160,169],"datasets)":[29],"machine":[32],"learning":[33],"(ML)":[34],"invoking":[36],"one":[37],"or":[38],"more":[39],"trained":[40],"models":[41,204],"predictions.":[44],"These":[45],"parts":[46],"have":[47],"so":[48],"far":[49],"been":[50],"optimized":[51],"in":[52,96],"isolation,":[53],"leaving":[54],"significant":[55],"opportunities":[56],"optimization":[58],"unexplored.":[59],"We":[60],"present":[61],"Raven,":[62],"production-ready":[64],"system":[65],"optimizing":[67],"prediction":[68,186],"queries.":[69],"Raven":[70,179,210],"follows":[71],"enterprise":[73],"architectural":[74],"trend":[75],"of":[76,105,122,168,185],"collocating":[77],"ML":[80,94,128],"runtimes.":[81],"It":[82],"relies":[83],"on":[84,145,188],"unified":[86],"intermediate":[87],"representation":[88],"that":[89,112,139,178],"captures":[90],"both":[91],"operators":[95,141],"single":[98],"graph":[99],"structure":[100],"unlock":[102],"two":[103],"families":[104],"optimizations.":[106],"First,":[107],"it":[108,135],"employs":[109],"logical":[110],"optimizations":[111,158],"pass":[113],"information":[114],"between":[115],"(and":[119],"properties":[121],"underlying":[124],"data)":[125],"optimize":[131],"each":[132,166],"other.":[133],"Second,":[134],"introduces":[136],"logical-to-physical":[137],"transformations":[138],"allow":[140],"be":[143,163],"executed":[144],"different":[146],"run-times":[147],"(relational,":[148],"ML,":[149],"DNN)":[151],"hardware":[153],"(CPU,":[154],"GPU).":[155],"Novel":[156],"data-driven":[157],"determine":[159],"runtime":[161],"query":[170],"achieve":[172],"optimal":[173],"performance.":[174],"Our":[175],"evaluation":[176],"shows":[177],"is":[180,208],"able":[181],"improve":[183],"performance":[184],"Apache":[189],"Spark":[190],"SQL":[192],"Server":[193],"by":[194],"up":[195,212],"13.1x":[197],"330x,":[199],"respectively.":[200],"Finally,":[201],"complex":[203],"where":[205],"GPU":[206],"acceleration":[207],"beneficial,":[209],"provides":[211],"8\u00d7":[214],"speedup":[215],"compared":[216],"state-of-the-art":[218],"systems.":[219]},"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2025,"cited_by_count":15},{"year":2024,"cited_by_count":11},{"year":2023,"cited_by_count":8},{"year":2022,"cited_by_count":2}],"updated_date":"2026-03-20T23:20:44.827607","created_date":"2025-10-10T00:00:00"}