{"id":"https://openalex.org/W3204075005","doi":"https://doi.org/10.1145/3472456.3472501","title":"AMPS-Inf: Automatic Model Partitioning for Serverless Inference with Cost Efficiency","display_name":"AMPS-Inf: Automatic Model Partitioning for Serverless Inference with Cost Efficiency","publication_year":2021,"publication_date":"2021-08-09","ids":{"openalex":"https://openalex.org/W3204075005","doi":"https://doi.org/10.1145/3472456.3472501","mag":"3204075005"},"language":"en","primary_location":{"id":"doi:10.1145/3472456.3472501","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3472456.3472501","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"50th International Conference on Parallel Processing","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/A5083048334","display_name":"Jananie Jarachanthan","orcid":null},"institutions":[{"id":"https://openalex.org/I79516672","display_name":"University of Louisiana at Lafayette","ror":"https://ror.org/01x8rc503","country_code":"US","type":"education","lineage":["https://openalex.org/I2799628689","https://openalex.org/I79516672"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Jananie Jarachanthan","raw_affiliation_strings":["University of Louisiana at Lafayette, United States of America"],"affiliations":[{"raw_affiliation_string":"University of Louisiana at Lafayette, United States of America","institution_ids":["https://openalex.org/I79516672"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100379201","display_name":"Li Chen","orcid":"https://orcid.org/0000-0001-9725-3044"},"institutions":[{"id":"https://openalex.org/I79516672","display_name":"University of Louisiana at Lafayette","ror":"https://ror.org/01x8rc503","country_code":"US","type":"education","lineage":["https://openalex.org/I2799628689","https://openalex.org/I79516672"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Li Chen","raw_affiliation_strings":["University of Louisiana at Lafayette, United States of America"],"affiliations":[{"raw_affiliation_string":"University of Louisiana at Lafayette, United States of America","institution_ids":["https://openalex.org/I79516672"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5029626585","display_name":"Fei Xu","orcid":"https://orcid.org/0000-0003-1590-5323"},"institutions":[{"id":"https://openalex.org/I66867065","display_name":"East China Normal University","ror":"https://ror.org/02n96ep67","country_code":"CN","type":"education","lineage":["https://openalex.org/I66867065"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Fei Xu","raw_affiliation_strings":["East China Normal University, China"],"affiliations":[{"raw_affiliation_string":"East China Normal University, China","institution_ids":["https://openalex.org/I66867065"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100604098","display_name":"Bo Li","orcid":"https://orcid.org/0000-0003-3950-2019"},"institutions":[{"id":"https://openalex.org/I200769079","display_name":"Hong Kong University of Science and Technology","ror":"https://ror.org/00q4vv597","country_code":"HK","type":"education","lineage":["https://openalex.org/I200769079"]}],"countries":["HK"],"is_corresponding":false,"raw_author_name":"Bo Li","raw_affiliation_strings":["Hong Kong University of Science and Technology, Hong Kong"],"affiliations":[{"raw_affiliation_string":"Hong Kong University of Science and Technology, Hong Kong","institution_ids":["https://openalex.org/I200769079"]}]}],"institutions":[],"countries_distinct_count":3,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5083048334"],"corresponding_institution_ids":["https://openalex.org/I79516672"],"apc_list":null,"apc_paid":null,"fwci":8.2625,"has_fulltext":false,"cited_by_count":36,"citation_normalized_percentile":{"value":0.9756163,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":98,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"12"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10101","display_name":"Cloud Computing and Resource Management","score":0.9988999962806702,"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":0.9988999962806702,"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":0.9983999729156494,"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/T10036","display_name":"Advanced Neural Network Applications","score":0.9975000023841858,"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":0.8364830017089844},{"id":"https://openalex.org/keywords/provisioning","display_name":"Provisioning","score":0.7276836037635803},{"id":"https://openalex.org/keywords/exploit","display_name":"Exploit","score":0.5984820127487183},{"id":"https://openalex.org/keywords/distributed-computing","display_name":"Distributed computing","score":0.4682736396789551},{"id":"https://openalex.org/keywords/software-deployment","display_name":"Software deployment","score":0.4454018473625183},{"id":"https://openalex.org/keywords/integer-programming","display_name":"Integer programming","score":0.437921404838562},{"id":"https://openalex.org/keywords/cloud-computing","display_name":"Cloud computing","score":0.42864862084388733},{"id":"https://openalex.org/keywords/inference","display_name":"Inference","score":0.4147694408893585},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3892996311187744},{"id":"https://openalex.org/keywords/operating-system","display_name":"Operating system","score":0.20831778645515442},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.11851897835731506},{"id":"https://openalex.org/keywords/computer-security","display_name":"Computer security","score":0.09465661644935608}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8364830017089844},{"id":"https://openalex.org/C172191483","wikidata":"https://www.wikidata.org/wiki/Q1071806","display_name":"Provisioning","level":2,"score":0.7276836037635803},{"id":"https://openalex.org/C165696696","wikidata":"https://www.wikidata.org/wiki/Q11287","display_name":"Exploit","level":2,"score":0.5984820127487183},{"id":"https://openalex.org/C120314980","wikidata":"https://www.wikidata.org/wiki/Q180634","display_name":"Distributed computing","level":1,"score":0.4682736396789551},{"id":"https://openalex.org/C105339364","wikidata":"https://www.wikidata.org/wiki/Q2297740","display_name":"Software deployment","level":2,"score":0.4454018473625183},{"id":"https://openalex.org/C56086750","wikidata":"https://www.wikidata.org/wiki/Q6042592","display_name":"Integer programming","level":2,"score":0.437921404838562},{"id":"https://openalex.org/C79974875","wikidata":"https://www.wikidata.org/wiki/Q483639","display_name":"Cloud computing","level":2,"score":0.42864862084388733},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.4147694408893585},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3892996311187744},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.20831778645515442},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.11851897835731506},{"id":"https://openalex.org/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","level":1,"score":0.09465661644935608}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1145/3472456.3472501","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3472456.3472501","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"50th International Conference on Parallel Processing","raw_type":"proceedings-article"},{"id":"pmh:oai:repository.hkust.edu.hk:1783.1-113859","is_oa":false,"landing_page_url":"http://www.scopus.com/record/display.url?eid=2-s2.0-85117250730&origin=inward","pdf_url":null,"source":{"id":"https://openalex.org/S4306401796","display_name":"Rare & Special e-Zone (The Hong Kong University of Science and Technology)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I200769079","host_organization_name":"Hong Kong University of Science and Technology","host_organization_lineage":["https://openalex.org/I200769079"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"Conference paper"},{"id":"pmh:oai:repository.ust.hk:1783.1-113859","is_oa":false,"landing_page_url":"http://repository.ust.hk/ir/Record/1783.1-113859","pdf_url":null,"source":{"id":"https://openalex.org/S4306401796","display_name":"Rare & Special e-Zone (The Hong Kong University of Science and Technology)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I200769079","host_organization_name":"Hong Kong University of Science and Technology","host_organization_lineage":["https://openalex.org/I200769079"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"Conference paper"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/8","display_name":"Decent work and economic growth","score":0.5199999809265137}],"awards":[{"id":"https://openalex.org/G6344893743","display_name":null,"funder_award_id":"LEQSF(2019-22)-RD-A-21, LEQSF(2021-22)-RD-D-07","funder_id":"https://openalex.org/F4320309392","funder_display_name":"Louisiana Board of Regents"}],"funders":[{"id":"https://openalex.org/F4320309392","display_name":"Louisiana Board of Regents","ror":"https://ror.org/00jv89z46"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":28,"referenced_works":["https://openalex.org/W1506859583","https://openalex.org/W1542938076","https://openalex.org/W2091480518","https://openalex.org/W2167066679","https://openalex.org/W2183341477","https://openalex.org/W2194775991","https://openalex.org/W2290452516","https://openalex.org/W2531409750","https://openalex.org/W2591324491","https://openalex.org/W2612445135","https://openalex.org/W2776671691","https://openalex.org/W2899160556","https://openalex.org/W2918828872","https://openalex.org/W2918996793","https://openalex.org/W2934208298","https://openalex.org/W2949979136","https://openalex.org/W2955766048","https://openalex.org/W2956461999","https://openalex.org/W2962866832","https://openalex.org/W2963341956","https://openalex.org/W2964108773","https://openalex.org/W2964299589","https://openalex.org/W2970445008","https://openalex.org/W2987607480","https://openalex.org/W3105227206","https://openalex.org/W3130689885","https://openalex.org/W3189255189","https://openalex.org/W4297825594"],"related_works":["https://openalex.org/W17155033","https://openalex.org/W3207760230","https://openalex.org/W1496222301","https://openalex.org/W4312814274","https://openalex.org/W1590307681","https://openalex.org/W2536018345","https://openalex.org/W4285370786","https://openalex.org/W2296488620","https://openalex.org/W2358353312","https://openalex.org/W2941957272"],"abstract_inverted_index":{"The":[0,135],"salient":[1],"pay-per-use":[2],"nature":[3],"of":[4,49,75,137,145,160],"serverless":[5,33,43,63,77,112],"computing":[6,15,78],"has":[7],"driven":[8],"its":[9],"continuous":[10],"penetration":[11],"as":[12],"an":[13,104],"alternative":[14],"paradigm":[16,79],"for":[17,80,108,132,151],"various":[18],"workloads.":[19,134],"Yet,":[20],"challenges":[21],"arise":[22],"and":[23,88,101,118,128,143,154,187,189,194],"remain":[24],"open":[25],"when":[26],"shifting":[27],"machine":[28,81],"learning":[29,82],"workloads":[30,83],"to":[31,56,70,204],"the":[32,36,39,47,73,76,93,116,125,141,158,172,178],"environment.":[34],"Specifically,":[35],"restriction":[37],"on":[38,140,171],"deployment":[40],"size":[41],"over":[42],"platforms":[44],"combining":[45],"with":[46,157,177,191],"complexity":[48],"neural":[50],"network":[51],"models":[52,59,181],"makes":[53],"it":[54],"difficult":[55],"deploy":[57,169],"large":[58],"in":[60,111,182],"a":[61,146],"single":[62],"function.":[64],"In":[65],"this":[66],"paper,":[67],"we":[68],"aim":[69],"fully":[71],"exploit":[72],"advantages":[74],"targeting":[84],"at":[85],"mitigating":[86],"management":[87],"overall":[89],"cost":[90,162,206],"while":[91],"meeting":[92],"response-time":[94],"Service":[95],"Level":[96],"Objective":[97],"(SLO).":[98],"We":[99,168],"design":[100],"implement":[102],"AMPS-Inf,":[103],"autonomous":[105],"framework":[106],"customized":[107],"model":[109,152],"inferencing":[110],"computing.":[113],"Driven":[114],"by":[115],"cost-efficiency":[117],"timely-response,":[119],"our":[120],"proposed":[121],"AMPS-Inf":[122,138,170,201],"automatically":[123],"generates":[124],"optimal":[126],"execution":[127],"resource":[129,155],"provisioning":[130,156],"plans":[131],"inference":[133],"core":[136],"relies":[139],"formulation":[142],"solution":[144],"Mixed-Integer":[147],"Quadratic":[148],"Programming":[149],"problem":[150],"partitioning":[153],"objective":[159],"minimizing":[161],"without":[163,208],"violating":[164],"response":[165,210],"time":[166,211],"SLO.":[167],"AWS":[173],"Lambda":[174],"platform,":[175],"evaluate":[176],"state-of-the-art":[179],"pre-trained":[180],"Keras":[183],"including":[184],"ResNet50,":[185],"Inception-V3":[186],"Xception,":[188],"compare":[190],"Amazon":[192],"SageMaker":[193],"three":[195],"baselines.":[196],"Experimental":[197],"results":[198],"demonstrate":[199],"that":[200],"achieves":[202],"up":[203],"98%":[205],"saving":[207],"degrading":[209],"performance.":[212]},"counts_by_year":[{"year":2025,"cited_by_count":6},{"year":2024,"cited_by_count":12},{"year":2023,"cited_by_count":10},{"year":2022,"cited_by_count":8}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}