{"id":"https://openalex.org/W3166319166","doi":"https://doi.org/10.1145/3448016.3457566","title":"Production Machine Learning Pipelines","display_name":"Production Machine Learning Pipelines","publication_year":2021,"publication_date":"2021-06-09","ids":{"openalex":"https://openalex.org/W3166319166","doi":"https://doi.org/10.1145/3448016.3457566","mag":"3166319166"},"language":"en","primary_location":{"id":"doi:10.1145/3448016.3457566","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3448016.3457566","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3448016.3457566","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2021 International Conference on Management of Data","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://dl.acm.org/doi/pdf/10.1145/3448016.3457566","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5028796772","display_name":"Doris Xin","orcid":null},"institutions":[{"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":true,"raw_author_name":"Doris Xin","raw_affiliation_strings":["University of California, Berkeley, Berkeley, CA, USA"],"affiliations":[{"raw_affiliation_string":"University of California, Berkeley, Berkeley, CA, USA","institution_ids":["https://openalex.org/I95457486"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101716735","display_name":"Hui Miao","orcid":"https://orcid.org/0000-0002-9839-3249"},"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":"Hui Miao","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/A5013608601","display_name":"Aditya Parameswaran","orcid":"https://orcid.org/0000-0002-4538-4752"},"institutions":[{"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":"Aditya Parameswaran","raw_affiliation_strings":["University of California, Berkeley, Berkeley, CA, USA"],"affiliations":[{"raw_affiliation_string":"University of California, Berkeley, Berkeley, CA, USA","institution_ids":["https://openalex.org/I95457486"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5010950113","display_name":"Neoklis Polyzotis","orcid":"https://orcid.org/0000-0002-2694-8591"},"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":"Neoklis Polyzotis","raw_affiliation_strings":["Google, Mountain View, CA, USA"],"affiliations":[{"raw_affiliation_string":"Google, Mountain View, CA, USA","institution_ids":["https://openalex.org/I1291425158"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5028796772"],"corresponding_institution_ids":["https://openalex.org/I95457486"],"apc_list":null,"apc_paid":null,"fwci":21.0989,"has_fulltext":true,"cited_by_count":56,"citation_normalized_percentile":{"value":0.99029992,"is_in_top_1_percent":true,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":96,"max":100},"biblio":{"volume":null,"issue":null,"first_page":"2639","last_page":"2652"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11986","display_name":"Scientific Computing and Data Management","score":0.9998999834060669,"subfield":{"id":"https://openalex.org/subfields/1802","display_name":"Information Systems and Management"},"field":{"id":"https://openalex.org/fields/18","display_name":"Decision Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},"topics":[{"id":"https://openalex.org/T11986","display_name":"Scientific Computing and Data Management","score":0.9998999834060669,"subfield":{"id":"https://openalex.org/subfields/1802","display_name":"Information Systems and Management"},"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/T11937","display_name":"Research Data Management Practices","score":0.9945999979972839,"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/T10715","display_name":"Distributed and Parallel Computing Systems","score":0.9934999942779541,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/pruning","display_name":"Pruning","score":0.790508508682251},{"id":"https://openalex.org/keywords/pipeline-transport","display_name":"Pipeline transport","score":0.7813273668289185},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7719708681106567},{"id":"https://openalex.org/keywords/software-deployment","display_name":"Software deployment","score":0.6178231835365295},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.549265444278717},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.5370368957519531},{"id":"https://openalex.org/keywords/production","display_name":"Production (economics)","score":0.4876386225223541},{"id":"https://openalex.org/keywords/computation","display_name":"Computation","score":0.47748443484306335},{"id":"https://openalex.org/keywords/network-topology","display_name":"Network topology","score":0.42804449796676636},{"id":"https://openalex.org/keywords/distributed-computing","display_name":"Distributed computing","score":0.32584813237190247},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.3249948024749756},{"id":"https://openalex.org/keywords/software-engineering","display_name":"Software engineering","score":0.18572339415550232},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.13144460320472717},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.12874501943588257}],"concepts":[{"id":"https://openalex.org/C108010975","wikidata":"https://www.wikidata.org/wiki/Q500094","display_name":"Pruning","level":2,"score":0.790508508682251},{"id":"https://openalex.org/C175309249","wikidata":"https://www.wikidata.org/wiki/Q725864","display_name":"Pipeline transport","level":2,"score":0.7813273668289185},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7719708681106567},{"id":"https://openalex.org/C105339364","wikidata":"https://www.wikidata.org/wiki/Q2297740","display_name":"Software deployment","level":2,"score":0.6178231835365295},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.549265444278717},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.5370368957519531},{"id":"https://openalex.org/C2778348673","wikidata":"https://www.wikidata.org/wiki/Q739302","display_name":"Production (economics)","level":2,"score":0.4876386225223541},{"id":"https://openalex.org/C45374587","wikidata":"https://www.wikidata.org/wiki/Q12525525","display_name":"Computation","level":2,"score":0.47748443484306335},{"id":"https://openalex.org/C199845137","wikidata":"https://www.wikidata.org/wiki/Q145490","display_name":"Network topology","level":2,"score":0.42804449796676636},{"id":"https://openalex.org/C120314980","wikidata":"https://www.wikidata.org/wiki/Q180634","display_name":"Distributed computing","level":1,"score":0.32584813237190247},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.3249948024749756},{"id":"https://openalex.org/C115903868","wikidata":"https://www.wikidata.org/wiki/Q80993","display_name":"Software engineering","level":1,"score":0.18572339415550232},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.13144460320472717},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.12874501943588257},{"id":"https://openalex.org/C6557445","wikidata":"https://www.wikidata.org/wiki/Q173113","display_name":"Agronomy","level":1,"score":0.0},{"id":"https://openalex.org/C87717796","wikidata":"https://www.wikidata.org/wiki/Q146326","display_name":"Environmental 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},{"id":"https://openalex.org/C139719470","wikidata":"https://www.wikidata.org/wiki/Q39680","display_name":"Macroeconomics","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/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3448016.3457566","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3448016.3457566","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3448016.3457566","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2021 International Conference on Management of Data","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.1145/3448016.3457566","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3448016.3457566","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3448016.3457566","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2021 International Conference on Management of Data","raw_type":"proceedings-article"},"sustainable_development_goals":[{"score":0.47999998927116394,"display_name":"Industry, innovation and infrastructure","id":"https://metadata.un.org/sdg/9"}],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W3166319166.pdf","grobid_xml":"https://content.openalex.org/works/W3166319166.grobid-xml"},"referenced_works_count":49,"referenced_works":["https://openalex.org/W1880832170","https://openalex.org/W1924304903","https://openalex.org/W1983704199","https://openalex.org/W2001108980","https://openalex.org/W2044102377","https://openalex.org/W2044849727","https://openalex.org/W2097284091","https://openalex.org/W2101234009","https://openalex.org/W2128226234","https://openalex.org/W2133986470","https://openalex.org/W2155475476","https://openalex.org/W2158915538","https://openalex.org/W2167541073","https://openalex.org/W2189162242","https://openalex.org/W2294556882","https://openalex.org/W2340086043","https://openalex.org/W2357449897","https://openalex.org/W2438792749","https://openalex.org/W2584580687","https://openalex.org/W2604713509","https://openalex.org/W2609517807","https://openalex.org/W2613597870","https://openalex.org/W2743948853","https://openalex.org/W2752857821","https://openalex.org/W2791094827","https://openalex.org/W2896357488","https://openalex.org/W2905588001","https://openalex.org/W2912468772","https://openalex.org/W2922234936","https://openalex.org/W2926314329","https://openalex.org/W2927176210","https://openalex.org/W2929793114","https://openalex.org/W2943962500","https://openalex.org/W2946595616","https://openalex.org/W2965196503","https://openalex.org/W2997591727","https://openalex.org/W3020531607","https://openalex.org/W3021318396","https://openalex.org/W3029504795","https://openalex.org/W3036176069","https://openalex.org/W3045936340","https://openalex.org/W3084542178","https://openalex.org/W3086791196","https://openalex.org/W3091508867","https://openalex.org/W3104582284","https://openalex.org/W3110197861","https://openalex.org/W3166319166","https://openalex.org/W4248547660","https://openalex.org/W4365786623"],"related_works":["https://openalex.org/W96612179","https://openalex.org/W2770234245","https://openalex.org/W2987774938","https://openalex.org/W2566006169","https://openalex.org/W4256492088","https://openalex.org/W632915154","https://openalex.org/W4229499248","https://openalex.org/W4378874356","https://openalex.org/W2055733372","https://openalex.org/W2369811061"],"abstract_inverted_index":{"Machine":[0],"learning":[1],"(ML)":[2],"is":[3,46],"now":[4],"commonplace,":[5],"powering":[6],"data-driven":[7],"applications":[8],"in":[9,18,107,152],"various":[10,133],"organizations.":[11],"Unlike":[12],"the":[13,53,85,112,122,136,204],"traditional":[14,169],"perception":[15],"of":[16,42,49,59,88,103,127,179],"ML":[17,20,91,130,154],"research,":[19],"production":[21,90,117],"pipelines":[22,61,92,131],"are":[23,34],"complex,":[24],"with":[25],"many":[26],"interlocking":[27],"analytical":[28],"components":[29,151],"beyond":[30],"training,":[31],"whose":[32],"sub-parts":[33],"often":[35],"run":[36,150],"multiple":[37],"times":[38],"on":[39],"overlapping":[40],"subsets":[41],"data.":[43],"However,":[44],"there":[45],"a":[47,101,140],"lack":[48],"quantitative":[50],"evidence":[51],"regarding":[52],"lifespan,":[54],"architecture,":[55],"frequency,":[56],"and":[57,78,114,125,146,184],"complexity":[58,113],"these":[60,153,180],"to":[62,71,110,192],"understand":[63,111],"how":[64,175],"data":[65,142,170],"management":[66,171],"research":[67],"can":[68,195],"be":[69],"used":[70],"make":[72],"them":[73],"more":[74],"efficient,":[75],"effective,":[76],"robust,":[77],"reproducible.":[79],"To":[80],"that":[81,188],"end,":[82],"we":[83,138,157],"analyze":[84],"provenance":[86],"graphs":[87],"3000":[89],"at":[93,132],"Google,":[94],"comprising":[95],"over":[96,104],"450,000":[97],"models":[98],"trained,":[99],"spanning":[100],"period":[102],"four":[105],"months,":[106],"an":[108],"effort":[109],"challenges":[115],"underlying":[116],"ML.":[118],"Our":[119],"analysis":[120],"reveals":[121],"characteristics,":[123],"components,":[124],"topologies":[126],"typical":[128],"industry-strength":[129],"granularities.":[134],"Along":[135],"way,":[137],"introduce":[139],"specialized":[141],"model":[143,159,193,205],"for":[144,166],"representing":[145],"reasoning":[147],"about":[148],"repeatedly":[149],"pipelines,":[155],"which":[156],"call":[158],"graphlets.":[160],"We":[161,173],"identify":[162],"several":[163],"rich":[164],"opportunities":[165],"optimization,":[167],"leveraging":[168],"ideas.":[172],"show":[174],"targeting":[176],"even":[177],"one":[178],"opportunities,":[181],"i.e.,":[182],"identifying":[183],"pruning":[185],"wasted":[186,197],"computation":[187,198],"does":[189],"not":[190],"translate":[191],"deployment,":[194],"reduce":[196],"cost":[199],"by":[200],"50%":[201],"without":[202],"compromising":[203],"deployment":[206],"cadence.":[207]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":13},{"year":2024,"cited_by_count":12},{"year":2023,"cited_by_count":19},{"year":2022,"cited_by_count":7},{"year":2021,"cited_by_count":4}],"updated_date":"2026-03-28T08:17:26.163206","created_date":"2025-10-10T00:00:00"}