{"id":"https://openalex.org/W3196976833","doi":"https://doi.org/10.14778/3476311.3476402","title":"Managing ML pipelines","display_name":"Managing ML pipelines","publication_year":2021,"publication_date":"2021-07-01","ids":{"openalex":"https://openalex.org/W3196976833","doi":"https://doi.org/10.14778/3476311.3476402","mag":"3196976833"},"language":"en","primary_location":{"id":"doi:10.14778/3476311.3476402","is_oa":false,"landing_page_url":"https://doi.org/10.14778/3476311.3476402","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/A5054285881","display_name":"Laurel Orr","orcid":"https://orcid.org/0000-0002-2183-3541"},"institutions":[{"id":"https://openalex.org/I97018004","display_name":"Stanford University","ror":"https://ror.org/00f54p054","country_code":"US","type":"education","lineage":["https://openalex.org/I97018004"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Laurel Orr","raw_affiliation_strings":["Stanford University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Stanford University","institution_ids":["https://openalex.org/I97018004"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5016375024","display_name":"Atindriyo Sanyal","orcid":null},"institutions":[{"id":"https://openalex.org/I97018004","display_name":"Stanford University","ror":"https://ror.org/00f54p054","country_code":"US","type":"education","lineage":["https://openalex.org/I97018004"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Atindriyo Sanyal","raw_affiliation_strings":["Stanford University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Stanford University","institution_ids":["https://openalex.org/I97018004"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5011629374","display_name":"Xiao Ling","orcid":"https://orcid.org/0000-0001-5890-0691"},"institutions":[{"id":"https://openalex.org/I97018004","display_name":"Stanford University","ror":"https://ror.org/00f54p054","country_code":"US","type":"education","lineage":["https://openalex.org/I97018004"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Xiao Ling","raw_affiliation_strings":["Stanford University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Stanford University","institution_ids":["https://openalex.org/I97018004"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5063897942","display_name":"Karan Goel","orcid":null},"institutions":[{"id":"https://openalex.org/I97018004","display_name":"Stanford University","ror":"https://ror.org/00f54p054","country_code":"US","type":"education","lineage":["https://openalex.org/I97018004"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Karan Goel","raw_affiliation_strings":["Stanford University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Stanford University","institution_ids":["https://openalex.org/I97018004"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5013698287","display_name":"Megan Leszczynski","orcid":"https://orcid.org/0000-0001-8065-7763"},"institutions":[{"id":"https://openalex.org/I97018004","display_name":"Stanford University","ror":"https://ror.org/00f54p054","country_code":"US","type":"education","lineage":["https://openalex.org/I97018004"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Megan Leszczynski","raw_affiliation_strings":["Stanford University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Stanford University","institution_ids":["https://openalex.org/I97018004"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I97018004"],"apc_list":null,"apc_paid":null,"fwci":2.0026,"has_fulltext":false,"cited_by_count":20,"citation_normalized_percentile":{"value":0.8840729,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":91,"max":99},"biblio":{"volume":"14","issue":"12","first_page":"3178","last_page":"3181"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12535","display_name":"Machine Learning and Data Classification","score":0.9994000196456909,"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":0.9994000196456909,"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/T12761","display_name":"Data Stream Mining Techniques","score":0.9965000152587891,"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/T11689","display_name":"Adversarial Robustness in Machine Learning","score":0.9944000244140625,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/pipeline","display_name":"Pipeline (software)","score":0.8005841970443726},{"id":"https://openalex.org/keywords/workflow","display_name":"Workflow","score":0.7919787168502808},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.773895263671875},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7411232590675354},{"id":"https://openalex.org/keywords/downstream","display_name":"Downstream (manufacturing)","score":0.6962451934814453},{"id":"https://openalex.org/keywords/embedding","display_name":"Embedding","score":0.6921008229255676},{"id":"https://openalex.org/keywords/pipeline-transport","display_name":"Pipeline transport","score":0.6217266321182251},{"id":"https://openalex.org/keywords/feature-engineering","display_name":"Feature engineering","score":0.4728056788444519},{"id":"https://openalex.org/keywords/scale","display_name":"Scale (ratio)","score":0.4477720260620117},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.36442938446998596},{"id":"https://openalex.org/keywords/data-science","display_name":"Data science","score":0.35207992792129517},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.34737926721572876},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.3345380425453186},{"id":"https://openalex.org/keywords/systems-engineering","display_name":"Systems engineering","score":0.32374393939971924},{"id":"https://openalex.org/keywords/database","display_name":"Database","score":0.21091961860656738},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.1756114959716797},{"id":"https://openalex.org/keywords/deep-learning","display_name":"Deep learning","score":0.11582997441291809}],"concepts":[{"id":"https://openalex.org/C43521106","wikidata":"https://www.wikidata.org/wiki/Q2165493","display_name":"Pipeline (software)","level":2,"score":0.8005841970443726},{"id":"https://openalex.org/C177212765","wikidata":"https://www.wikidata.org/wiki/Q627335","display_name":"Workflow","level":2,"score":0.7919787168502808},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.773895263671875},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7411232590675354},{"id":"https://openalex.org/C2776207758","wikidata":"https://www.wikidata.org/wiki/Q5303302","display_name":"Downstream (manufacturing)","level":2,"score":0.6962451934814453},{"id":"https://openalex.org/C41608201","wikidata":"https://www.wikidata.org/wiki/Q980509","display_name":"Embedding","level":2,"score":0.6921008229255676},{"id":"https://openalex.org/C175309249","wikidata":"https://www.wikidata.org/wiki/Q725864","display_name":"Pipeline transport","level":2,"score":0.6217266321182251},{"id":"https://openalex.org/C2778827112","wikidata":"https://www.wikidata.org/wiki/Q22245680","display_name":"Feature engineering","level":3,"score":0.4728056788444519},{"id":"https://openalex.org/C2778755073","wikidata":"https://www.wikidata.org/wiki/Q10858537","display_name":"Scale (ratio)","level":2,"score":0.4477720260620117},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.36442938446998596},{"id":"https://openalex.org/C2522767166","wikidata":"https://www.wikidata.org/wiki/Q2374463","display_name":"Data science","level":1,"score":0.35207992792129517},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.34737926721572876},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3345380425453186},{"id":"https://openalex.org/C201995342","wikidata":"https://www.wikidata.org/wiki/Q682496","display_name":"Systems engineering","level":1,"score":0.32374393939971924},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.21091961860656738},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.1756114959716797},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.11582997441291809},{"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/C21547014","wikidata":"https://www.wikidata.org/wiki/Q1423657","display_name":"Operations management","level":1,"score":0.0},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","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},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.14778/3476311.3476402","is_oa":false,"landing_page_url":"https://doi.org/10.14778/3476311.3476402","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","id":"https://metadata.un.org/sdg/9","score":0.47999998927116394}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":17,"referenced_works":["https://openalex.org/W2123958332","https://openalex.org/W2432911982","https://openalex.org/W2574488981","https://openalex.org/W2769041395","https://openalex.org/W2798649495","https://openalex.org/W2804619229","https://openalex.org/W2887428522","https://openalex.org/W2926314329","https://openalex.org/W2947737663","https://openalex.org/W2954337038","https://openalex.org/W2959716049","https://openalex.org/W2973042192","https://openalex.org/W2998554035","https://openalex.org/W3021397474","https://openalex.org/W3034439313","https://openalex.org/W3037852608","https://openalex.org/W3094024085"],"related_works":["https://openalex.org/W1583765404","https://openalex.org/W1981780420","https://openalex.org/W2182707996","https://openalex.org/W4214653257","https://openalex.org/W45233828","https://openalex.org/W2964988449","https://openalex.org/W188202134","https://openalex.org/W2397952901","https://openalex.org/W2029380707","https://openalex.org/W2081900870"],"abstract_inverted_index":{"The":[0],"industrial":[1],"machine":[2],"learning":[3],"pipeline":[4],"requires":[5],"iterating":[6],"on":[7,36],"model":[8,45,55],"features,":[9],"training":[10,75],"and":[11,14,26,60,80,108,112],"deploying":[12],"models,":[13],"monitoring":[15,81],"deployed":[16],"models":[17,83],"at":[18],"scale.":[19],"Feature":[20],"stores":[21],"were":[22],"developed":[23],"to":[24,72,102,115],"manage":[25],"standardize":[27],"the":[28,61,104,110],"engineer's":[29],"workflow":[30],"in":[31,92,98],"this":[32,99],"end-to-end":[33],"pipeline,":[34],"focusing":[35],"traditional":[37],"tabular":[38],"feature":[39,94,105],"data.":[40],"In":[41],"recent":[42],"years,":[43],"however,":[44],"development":[46],"has":[47],"shifted":[48],"towards":[49],"using":[50],"self-supervised":[51],"pretrained":[52],"embeddings":[53,59],"as":[54],"features.":[56],"Managing":[57],"these":[58,117],"downstream":[62,82],"systems":[63],"that":[64,84],"use":[65,85],"them":[66],"introduces":[67],"new":[68,118],"challenges":[69,88,111],"with":[70],"respect":[71],"managing":[73,116],"embedding":[74,78],"data,":[76],"measuring":[77],"quality,":[79],"embeddings.":[86],"These":[87],"are":[89],"largely":[90],"unaddressed":[91],"standard":[93],"stores.":[95],"Our":[96],"goal":[97],"tutorial":[100],"is":[101],"introduce":[103],"store":[106],"system":[107],"discuss":[109],"current":[113],"solutions":[114],"embedding-centric":[119],"pipelines.":[120]},"counts_by_year":[{"year":2026,"cited_by_count":4},{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":5},{"year":2023,"cited_by_count":5},{"year":2022,"cited_by_count":5}],"updated_date":"2026-08-11T07:18:39.950985","created_date":"2025-10-10T00:00:00"}