{"id":"https://openalex.org/W4320060379","doi":"https://doi.org/10.14778/3570690.3570692","title":"Serving and Optimizing Machine Learning Workflows on Heterogeneous Infrastructures","display_name":"Serving and Optimizing Machine Learning Workflows on Heterogeneous Infrastructures","publication_year":2022,"publication_date":"2022-11-01","ids":{"openalex":"https://openalex.org/W4320060379","doi":"https://doi.org/10.14778/3570690.3570692"},"language":"en","primary_location":{"id":"doi:10.14778/3570690.3570692","is_oa":false,"landing_page_url":"https://doi.org/10.14778/3570690.3570692","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/A5034983430","display_name":"Yongji Wu","orcid":"https://orcid.org/0009-0000-6297-1599"},"institutions":[{"id":"https://openalex.org/I170897317","display_name":"Duke University","ror":"https://ror.org/00py81415","country_code":"US","type":"education","lineage":["https://openalex.org/I170897317"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Yongji Wu","raw_affiliation_strings":["Duke University"],"affiliations":[{"raw_affiliation_string":"Duke University","institution_ids":["https://openalex.org/I170897317"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5000778364","display_name":"Matthew Lentz","orcid":"https://orcid.org/0000-0003-1034-2736"},"institutions":[{"id":"https://openalex.org/I170897317","display_name":"Duke University","ror":"https://ror.org/00py81415","country_code":"US","type":"education","lineage":["https://openalex.org/I170897317"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Matthew Lentz","raw_affiliation_strings":["Duke University"],"affiliations":[{"raw_affiliation_string":"Duke University","institution_ids":["https://openalex.org/I170897317"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5007943946","display_name":"Danyang Zhuo","orcid":"https://orcid.org/0000-0002-0611-3941"},"institutions":[{"id":"https://openalex.org/I170897317","display_name":"Duke University","ror":"https://ror.org/00py81415","country_code":"US","type":"education","lineage":["https://openalex.org/I170897317"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Danyang Zhuo","raw_affiliation_strings":["Duke University"],"affiliations":[{"raw_affiliation_string":"Duke University","institution_ids":["https://openalex.org/I170897317"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5114860385","display_name":"Yao Lu","orcid":"https://orcid.org/0000-0001-5563-0796"},"institutions":[{"id":"https://openalex.org/I4210164937","display_name":"Microsoft Research (United Kingdom)","ror":"https://ror.org/05k87vq12","country_code":"GB","type":"company","lineage":["https://openalex.org/I1290206253","https://openalex.org/I4210164937"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Yao Lu","raw_affiliation_strings":["Microsoft Research"],"affiliations":[{"raw_affiliation_string":"Microsoft Research","institution_ids":["https://openalex.org/I4210164937"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5034983430"],"corresponding_institution_ids":["https://openalex.org/I170897317"],"apc_list":null,"apc_paid":null,"fwci":1.4211,"has_fulltext":false,"cited_by_count":11,"citation_normalized_percentile":{"value":0.82921533,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":94,"max":99},"biblio":{"volume":"16","issue":"3","first_page":"406","last_page":"419"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10273","display_name":"IoT and Edge/Fog Computing","score":0.9969000220298767,"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/T10273","display_name":"IoT and Edge/Fog Computing","score":0.9969000220298767,"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/T10764","display_name":"Privacy-Preserving Technologies in Data","score":0.9919999837875366,"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":0.9919999837875366,"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/computer-science","display_name":"Computer science","score":0.8160949945449829},{"id":"https://openalex.org/keywords/cloud-computing","display_name":"Cloud computing","score":0.720321774482727},{"id":"https://openalex.org/keywords/inference","display_name":"Inference","score":0.6480277180671692},{"id":"https://openalex.org/keywords/workflow","display_name":"Workflow","score":0.6169143915176392},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.6111780405044556},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5796049237251282},{"id":"https://openalex.org/keywords/software-deployment","display_name":"Software deployment","score":0.523278534412384},{"id":"https://openalex.org/keywords/edge-device","display_name":"Edge device","score":0.4904043674468994},{"id":"https://openalex.org/keywords/distributed-computing","display_name":"Distributed computing","score":0.4860130250453949},{"id":"https://openalex.org/keywords/enhanced-data-rates-for-gsm-evolution","display_name":"Enhanced Data Rates for GSM Evolution","score":0.4664689004421234},{"id":"https://openalex.org/keywords/edge-computing","display_name":"Edge computing","score":0.4571714997291565},{"id":"https://openalex.org/keywords/software-engineering","display_name":"Software engineering","score":0.19305482506752014},{"id":"https://openalex.org/keywords/database","display_name":"Database","score":0.14932894706726074},{"id":"https://openalex.org/keywords/operating-system","display_name":"Operating system","score":0.11325159668922424}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8160949945449829},{"id":"https://openalex.org/C79974875","wikidata":"https://www.wikidata.org/wiki/Q483639","display_name":"Cloud computing","level":2,"score":0.720321774482727},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.6480277180671692},{"id":"https://openalex.org/C177212765","wikidata":"https://www.wikidata.org/wiki/Q627335","display_name":"Workflow","level":2,"score":0.6169143915176392},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.6111780405044556},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5796049237251282},{"id":"https://openalex.org/C105339364","wikidata":"https://www.wikidata.org/wiki/Q2297740","display_name":"Software deployment","level":2,"score":0.523278534412384},{"id":"https://openalex.org/C138236772","wikidata":"https://www.wikidata.org/wiki/Q25098575","display_name":"Edge device","level":3,"score":0.4904043674468994},{"id":"https://openalex.org/C120314980","wikidata":"https://www.wikidata.org/wiki/Q180634","display_name":"Distributed computing","level":1,"score":0.4860130250453949},{"id":"https://openalex.org/C162307627","wikidata":"https://www.wikidata.org/wiki/Q204833","display_name":"Enhanced Data Rates for GSM Evolution","level":2,"score":0.4664689004421234},{"id":"https://openalex.org/C2778456923","wikidata":"https://www.wikidata.org/wiki/Q5337692","display_name":"Edge computing","level":3,"score":0.4571714997291565},{"id":"https://openalex.org/C115903868","wikidata":"https://www.wikidata.org/wiki/Q80993","display_name":"Software engineering","level":1,"score":0.19305482506752014},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.14932894706726074},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.11325159668922424}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.14778/3570690.3570692","is_oa":false,"landing_page_url":"https://doi.org/10.14778/3570690.3570692","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":[{"score":0.6299999952316284,"display_name":"Industry, innovation and infrastructure","id":"https://metadata.un.org/sdg/9"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":29,"referenced_works":["https://openalex.org/W410850256","https://openalex.org/W1502629466","https://openalex.org/W2109507516","https://openalex.org/W2780624097","https://openalex.org/W2804032941","https://openalex.org/W2912338293","https://openalex.org/W2913894086","https://openalex.org/W2979826702","https://openalex.org/W3000407226","https://openalex.org/W3023935494","https://openalex.org/W3034368386","https://openalex.org/W3138154797","https://openalex.org/W3162118826","https://openalex.org/W3177525997","https://openalex.org/W4205185581","https://openalex.org/W4234552385","https://openalex.org/W4236099117","https://openalex.org/W4242509916","https://openalex.org/W4243371102","https://openalex.org/W4245551996","https://openalex.org/W4246762826","https://openalex.org/W4247297565","https://openalex.org/W4251247712","https://openalex.org/W4251248674","https://openalex.org/W4285337599","https://openalex.org/W4287777801","https://openalex.org/W6614148910","https://openalex.org/W6713134421","https://openalex.org/W6777017071"],"related_works":["https://openalex.org/W4322761281","https://openalex.org/W4238233472","https://openalex.org/W3013760193","https://openalex.org/W3162668736","https://openalex.org/W4312996489","https://openalex.org/W3111395152","https://openalex.org/W4313526662","https://openalex.org/W3106131444","https://openalex.org/W3216099748","https://openalex.org/W4366999913"],"abstract_inverted_index":{"With":[0],"the":[1,10,24,27,45,64,134,140,159,175,203],"advent":[2],"of":[3,6,12,26,98,152,163],"ubiquitous":[4],"deployment":[5],"smart":[7],"devices":[8],"and":[9,39,48,60,78,106,110,117,143,171,189],"Internet":[11],"Things,":[13],"data":[14],"sources":[15],"for":[16,74,80,83,115],"machine":[17,30,85,119],"learning":[18,31,86,120],"inference":[19,32,121],"have":[20,70],"increasingly":[21],"moved":[22],"to":[23,146,169,182,206],"edge":[25,54,58],"network.":[28],"Existing":[29],"platforms":[33],"typically":[34],"assume":[35],"a":[36,84,96,113],"homogeneous":[37],"infrastructure":[38,51],"do":[40],"not":[41],"take":[42],"into":[43],"account":[44],"more":[46],"complex":[47],"tiered":[49],"computing":[50],"that":[52,138,156],"includes":[53],"devices,":[55],"local":[56],"hubs,":[57],"datacenters,":[59],"cloud":[61],"datacenters.":[62],"On":[63],"other":[65],"hand,":[66],"recent":[67],"AutoML":[68],"efforts":[69],"provided":[71],"viable":[72],"solutions":[73],"model":[75,99,187],"compression,":[76],"pruning":[77],"quantization":[79],"heterogeneous":[81,124],"environments;":[82],"model,":[87],"now":[88],"we":[89],"may":[90],"easily":[91],"find":[92],"or":[93],"even":[94],"generate":[95],"series":[97],"variants":[100],"with":[101,185],"different":[102,150],"tradeoffs":[103],"between":[104],"accuracy":[105,141],"efficiency.":[107],"We":[108],"design":[109],"implement":[111],"JellyBean,":[112],"system":[114],"serving":[116,161,198,209],"optimizing":[118],"workflows":[122],"on":[123,202],"infrastructures.":[125,153],"Given":[126],"service-level":[127],"objectives":[128],"(e.g.,":[129,200],"throughput,":[130],"accuracy),":[131],"JellyBean":[132,157,193],"picks":[133],"most":[135],"cost-efficient":[136],"models":[137],"meet":[139],"target":[142],"decides":[144],"how":[145],"deploy":[147],"them":[148],"across":[149],"tiers":[151],"Evaluations":[154],"show":[155],"reduces":[158],"total":[160],"cost":[162],"visual":[164],"question":[165],"answering":[166],"by":[167,180],"up":[168,181,205],"58%":[170],"vehicle":[172],"tracking":[173],"from":[174],"NVIDIA":[176],"AI":[177],"City":[178],"Challenge":[179],"36%,":[183],"compared":[184],"state-of-the-art":[186],"selection":[188],"worker":[190],"assignment":[191],"solutions.":[192],"also":[194],"outperforms":[195],"prior":[196],"ML":[197],"systems":[199],"Spark":[201],"cloud)":[204],"5x":[207],"in":[208],"costs.":[210]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":3},{"year":2024,"cited_by_count":5},{"year":2023,"cited_by_count":2}],"updated_date":"2026-03-21T08:13:44.787528","created_date":"2025-10-10T00:00:00"}