{"id":"https://openalex.org/W4404384872","doi":"https://doi.org/10.1145/3698038.3698548","title":"FaPES: Enabling Efficient Elastic Scaling for Serverless Machine Learning Platforms","display_name":"FaPES: Enabling Efficient Elastic Scaling for Serverless Machine Learning Platforms","publication_year":2024,"publication_date":"2024-11-14","ids":{"openalex":"https://openalex.org/W4404384872","doi":"https://doi.org/10.1145/3698038.3698548"},"language":"en","primary_location":{"id":"doi:10.1145/3698038.3698548","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3698038.3698548","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the ACM Symposium on Cloud Computing","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/A5035542111","display_name":"Xiaoyang Zhao","orcid":"https://orcid.org/0000-0002-8260-2181"},"institutions":[{"id":"https://openalex.org/I889458895","display_name":"University of Hong Kong","ror":"https://ror.org/02zhqgq86","country_code":"HK","type":"education","lineage":["https://openalex.org/I889458895"]}],"countries":["HK"],"is_corresponding":true,"raw_author_name":"Xiaoyang Zhao","raw_affiliation_strings":["The University of Hong Kong"],"affiliations":[{"raw_affiliation_string":"The University of Hong Kong","institution_ids":["https://openalex.org/I889458895"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5016852628","display_name":"Siran Yang","orcid":"https://orcid.org/0009-0001-0272-3718"},"institutions":[{"id":"https://openalex.org/I4210095624","display_name":"Alibaba Group (United States)","ror":"https://ror.org/00rn0m335","country_code":"US","type":"company","lineage":["https://openalex.org/I4210095624","https://openalex.org/I45928872"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Siran Yang","raw_affiliation_strings":["Alibaba Group"],"affiliations":[{"raw_affiliation_string":"Alibaba Group","institution_ids":["https://openalex.org/I4210095624"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5025403631","display_name":"Jiamang Wang","orcid":null},"institutions":[{"id":"https://openalex.org/I4210095624","display_name":"Alibaba Group (United States)","ror":"https://ror.org/00rn0m335","country_code":"US","type":"company","lineage":["https://openalex.org/I4210095624","https://openalex.org/I45928872"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Jiamang Wang","raw_affiliation_strings":["Alibaba Group"],"affiliations":[{"raw_affiliation_string":"Alibaba Group","institution_ids":["https://openalex.org/I4210095624"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5020574416","display_name":"Lansong Diao","orcid":"https://orcid.org/0009-0000-6193-6126"},"institutions":[{"id":"https://openalex.org/I4210095624","display_name":"Alibaba Group (United States)","ror":"https://ror.org/00rn0m335","country_code":"US","type":"company","lineage":["https://openalex.org/I4210095624","https://openalex.org/I45928872"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Lansong Diao","raw_affiliation_strings":["Alibaba Group"],"affiliations":[{"raw_affiliation_string":"Alibaba Group","institution_ids":["https://openalex.org/I4210095624"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5114651253","display_name":"Lin Qu","orcid":null},"institutions":[{"id":"https://openalex.org/I4210095624","display_name":"Alibaba Group (United States)","ror":"https://ror.org/00rn0m335","country_code":"US","type":"company","lineage":["https://openalex.org/I4210095624","https://openalex.org/I45928872"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Lin Qu","raw_affiliation_strings":["Alibaba Group"],"affiliations":[{"raw_affiliation_string":"Alibaba Group","institution_ids":["https://openalex.org/I4210095624"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5012597518","display_name":"Chuan Wu","orcid":"https://orcid.org/0000-0002-3144-4398"},"institutions":[{"id":"https://openalex.org/I889458895","display_name":"University of Hong Kong","ror":"https://ror.org/02zhqgq86","country_code":"HK","type":"education","lineage":["https://openalex.org/I889458895"]}],"countries":["HK"],"is_corresponding":false,"raw_author_name":"Chuan Wu","raw_affiliation_strings":["The University of Hong Kong"],"affiliations":[{"raw_affiliation_string":"The University of Hong Kong","institution_ids":["https://openalex.org/I889458895"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":6,"corresponding_author_ids":["https://openalex.org/A5035542111"],"corresponding_institution_ids":["https://openalex.org/I889458895"],"apc_list":null,"apc_paid":null,"fwci":2.3792,"has_fulltext":false,"cited_by_count":3,"citation_normalized_percentile":{"value":0.91492909,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":96,"max":97},"biblio":{"volume":null,"issue":null,"first_page":"443","last_page":"459"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10101","display_name":"Cloud Computing and Resource Management","score":0.9994000196456909,"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":0.9994000196456909,"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/T10273","display_name":"IoT and Edge/Fog Computing","score":0.9958999752998352,"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/T12127","display_name":"Software System Performance and Reliability","score":0.9932000041007996,"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/computer-science","display_name":"Computer science","score":0.737892746925354},{"id":"https://openalex.org/keywords/scaling","display_name":"Scaling","score":0.6108375787734985}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.737892746925354},{"id":"https://openalex.org/C99844830","wikidata":"https://www.wikidata.org/wiki/Q102441924","display_name":"Scaling","level":2,"score":0.6108375787734985},{"id":"https://openalex.org/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","level":1,"score":0.0},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3698038.3698548","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3698038.3698548","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the ACM Symposium on Cloud Computing","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":17,"referenced_works":["https://openalex.org/W95608104","https://openalex.org/W2798515322","https://openalex.org/W2919897868","https://openalex.org/W2946090645","https://openalex.org/W2969388332","https://openalex.org/W4205500752","https://openalex.org/W4206566909","https://openalex.org/W4238732474","https://openalex.org/W4288093768","https://openalex.org/W4318541537","https://openalex.org/W4362566357","https://openalex.org/W4372262787","https://openalex.org/W4386436407","https://openalex.org/W4386565950","https://openalex.org/W4387321109","https://openalex.org/W4388662057","https://openalex.org/W6769475105"],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2899084033","https://openalex.org/W2748952813","https://openalex.org/W2390279801","https://openalex.org/W4391913857","https://openalex.org/W2358668433","https://openalex.org/W4396701345","https://openalex.org/W2376932109","https://openalex.org/W2001405890","https://openalex.org/W4396696052"],"abstract_inverted_index":{"Serverless":[0],"computing":[1],"platforms":[2,81],"have":[3],"become":[4],"increasingly":[5],"popular":[6],"for":[7,34,82,93,118],"running":[8,94,100],"machine":[9],"learning":[10],"(ML)":[11],"tasks":[12],"due":[13],"to":[14,24,54,74,112,157,169],"their":[15,63],"user-friendliness":[16],"and":[17,48,57,96,124,136,147,163],"decoupling":[18],"from":[19,144],"underlying":[20],"infrastructure.":[21],"However,":[22],"auto-scaling":[23],"efficiently":[25],"serve":[26],"incoming":[27],"requests":[28],"still":[29],"remains":[30],"a":[31,42,68,137,152],"challenge,":[32],"especially":[33],"distributed":[35],"ML":[36,83],"training":[37,47,95,119],"or":[38],"inference":[39,49,97,101],"jobs":[40,50],"in":[41,79],"serverless":[43,80],"GPU":[44,122],"cluster.":[45],"Distributed":[46],"are":[51,104,127],"highly":[52],"sensitive":[53],"resource":[55,77,88,138,148],"configurations,":[56],"demand":[58,107],"high":[59],"model":[60,125,135,145],"efficiency":[61],"throughout":[62],"lifecycle.":[64],"We":[65],"propose":[66],"FaPES,":[67],"FaaS-oriented":[69],"Performance-aware":[70],"Elastic":[71],"Scaling":[72],"system":[73],"enable":[75],"efficient":[76],"allocation":[78,123],"jobs.":[84,98],"FaPES":[85],"enables":[86],"flexible":[87],"loaning":[89],"between":[90],"virtual":[91],"clusters":[92],"For":[99],"jobs,":[102,120],"servers":[103],"reclaimed":[105],"on":[106,131,151],"with":[108],"minimal":[109],"preemption":[110],"overhead":[111],"guarantee":[113],"service":[114],"level":[115],"objective":[116],"(SLO);":[117],"optimal":[121],"hyperparameters":[126],"jointly":[128],"adapted":[129],"based":[130],"an":[132],"ML-based":[133],"performance":[134],"usage":[139],"prediction":[140],"board,":[141],"alleviating":[142],"users":[143],"tuning":[146],"specification.":[149],"Evaluation":[150],"128-GPU":[153],"testbed":[154],"demonstrates":[155],"up":[156],"24.8%":[158],"job":[159],"completion":[160],"time":[161],"reduction":[162],"\u00d71.8":[164],"Goodput":[165],"improvement,":[166],"as":[167],"compared":[168],"representative":[170],"elastic":[171],"scaling":[172],"schemes.":[173]},"counts_by_year":[{"year":2025,"cited_by_count":3}],"updated_date":"2026-03-20T23:20:44.827607","created_date":"2025-10-10T00:00:00"}