{"id":"https://openalex.org/W4393928174","doi":"https://doi.org/10.1145/3603166.3632535","title":"Machine Learning Inference on Serverless Platforms Using Model Decomposition","display_name":"Machine Learning Inference on Serverless Platforms Using Model Decomposition","publication_year":2023,"publication_date":"2023-12-04","ids":{"openalex":"https://openalex.org/W4393928174","doi":"https://doi.org/10.1145/3603166.3632535"},"language":"en","primary_location":{"id":"doi:10.1145/3603166.3632535","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3603166.3632535","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3603166.3632535","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 IEEE/ACM 16th International Conference on Utility and Cloud Computing","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/10.1145/3603166.3632535","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5094079134","display_name":"Adrien Gallego","orcid":"https://orcid.org/0009-0007-2409-1882"},"institutions":[{"id":"https://openalex.org/I887064364","display_name":"University of Amsterdam","ror":"https://ror.org/04dkp9463","country_code":"NL","type":"education","lineage":["https://openalex.org/I887064364"]}],"countries":["NL"],"is_corresponding":true,"raw_author_name":"Adrien Gallego","raw_affiliation_strings":["Informatics Institute, University of Amsterdam, Amsterdam, The Netherlands"],"raw_orcid":"https://orcid.org/0009-0007-2409-1882","affiliations":[{"raw_affiliation_string":"Informatics Institute, University of Amsterdam, Amsterdam, The Netherlands","institution_ids":["https://openalex.org/I887064364"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5024917187","display_name":"Uraz Odyurt","orcid":"https://orcid.org/0000-0003-1094-0234"},"institutions":[{"id":"https://openalex.org/I145872427","display_name":"Radboud University Nijmegen","ror":"https://ror.org/016xsfp80","country_code":"NL","type":"education","lineage":["https://openalex.org/I145872427"]}],"countries":["NL"],"is_corresponding":false,"raw_author_name":"Uraz Odyurt","raw_affiliation_strings":["High-Energy Physics, Radboud University, Nijmegen, The Netherlands"],"raw_orcid":"https://orcid.org/0000-0003-1094-0234","affiliations":[{"raw_affiliation_string":"High-Energy Physics, Radboud University, Nijmegen, The Netherlands","institution_ids":["https://openalex.org/I145872427"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5051147810","display_name":"Yi Cheng","orcid":"https://orcid.org/0009-0000-7813-0401"},"institutions":[{"id":"https://openalex.org/I887064364","display_name":"University of Amsterdam","ror":"https://ror.org/04dkp9463","country_code":"NL","type":"education","lineage":["https://openalex.org/I887064364"]}],"countries":["NL"],"is_corresponding":false,"raw_author_name":"Yi Cheng","raw_affiliation_strings":["Informatics Institute, University of Amsterdam, Amsterdam, The Netherlands"],"raw_orcid":"https://orcid.org/0009-0000-7813-0401","affiliations":[{"raw_affiliation_string":"Informatics Institute, University of Amsterdam, Amsterdam, The Netherlands","institution_ids":["https://openalex.org/I887064364"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5040080768","display_name":"Yuandou Wang","orcid":"https://orcid.org/0000-0003-4694-9572"},"institutions":[{"id":"https://openalex.org/I887064364","display_name":"University of Amsterdam","ror":"https://ror.org/04dkp9463","country_code":"NL","type":"education","lineage":["https://openalex.org/I887064364"]}],"countries":["NL"],"is_corresponding":false,"raw_author_name":"Yuandou Wang","raw_affiliation_strings":["Informatics Institute, University of Amsterdam, Amsterdam, The Netherlands"],"raw_orcid":"https://orcid.org/0000-0003-4694-9572","affiliations":[{"raw_affiliation_string":"Informatics Institute, University of Amsterdam, Amsterdam, The Netherlands","institution_ids":["https://openalex.org/I887064364"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5068341719","display_name":"Zhiming Zhao","orcid":"https://orcid.org/0000-0002-6717-9418"},"institutions":[{"id":"https://openalex.org/I887064364","display_name":"University of Amsterdam","ror":"https://ror.org/04dkp9463","country_code":"NL","type":"education","lineage":["https://openalex.org/I887064364"]}],"countries":["NL"],"is_corresponding":false,"raw_author_name":"Zhiming Zhao","raw_affiliation_strings":["Informatics Institute, University of Amsterdam, Amsterdam, The Netherlands"],"raw_orcid":"https://orcid.org/0000-0002-6717-9418","affiliations":[{"raw_affiliation_string":"Informatics Institute, University of Amsterdam, Amsterdam, The Netherlands","institution_ids":["https://openalex.org/I887064364"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5094079134"],"corresponding_institution_ids":["https://openalex.org/I887064364"],"apc_list":null,"apc_paid":null,"fwci":0.7726,"has_fulltext":true,"cited_by_count":4,"citation_normalized_percentile":{"value":0.75081882,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":95,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"6"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10400","display_name":"Network Security and Intrusion Detection","score":0.9968000054359436,"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/T10400","display_name":"Network Security and Intrusion Detection","score":0.9968000054359436,"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":0.9840999841690063,"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/T11344","display_name":"Traffic Prediction and Management Techniques","score":0.9768000245094299,"subfield":{"id":"https://openalex.org/subfields/2215","display_name":"Building and Construction"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7755491733551025},{"id":"https://openalex.org/keywords/decomposition","display_name":"Decomposition","score":0.7044183015823364},{"id":"https://openalex.org/keywords/inference","display_name":"Inference","score":0.6204700469970703},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6127736568450928},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.48793479800224304},{"id":"https://openalex.org/keywords/chemistry","display_name":"Chemistry","score":0.06548213958740234}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7755491733551025},{"id":"https://openalex.org/C124681953","wikidata":"https://www.wikidata.org/wiki/Q339062","display_name":"Decomposition","level":2,"score":0.7044183015823364},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.6204700469970703},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6127736568450928},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.48793479800224304},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.06548213958740234},{"id":"https://openalex.org/C178790620","wikidata":"https://www.wikidata.org/wiki/Q11351","display_name":"Organic chemistry","level":1,"score":0.0}],"mesh":[],"locations_count":4,"locations":[{"id":"doi:10.1145/3603166.3632535","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3603166.3632535","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3603166.3632535","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 IEEE/ACM 16th International Conference on Utility and Cloud Computing","raw_type":"proceedings-article"},{"id":"pmh:oai:dare.uva.nl:openaire_cris_publications/7da9fc6e-1751-4b44-9047-fb9ffa134806","is_oa":true,"landing_page_url":"https://handle.uba.uva.nl/personal/pure/en/publications/machine-learning-inference-on-serverless-platforms-using-model-decomposition(7da9fc6e-1751-4b44-9047-fb9ffa134806).html","pdf_url":null,"source":{"id":"https://openalex.org/S4306400088","display_name":"UvA-DARE (University of Amsterdam)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I887064364","host_organization_name":"University of Amsterdam","host_organization_lineage":["https://openalex.org/I887064364"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Gallego, A, Odyurt, U, Cheng, Y, Wang, Y & Zhao, Z 2023, Machine Learning Inference on Serverless Platforms Using Model Decomposition. in The 16th IEEE/ACM International Conference on Utility and Cloud Computing (UCC 2023) : 4-7 December 2023, Hotel Villa Diadoro, Taormina (ME), Italy., 33, Association for Computing Machinery, New York, New York, 16th IEEE/ACM International Conference on Utility and Cloud Computing, UCC 2023, Taormina, Italy, 4/12/23. https://doi.org/10.1145/3603166.3632535","raw_type":"info:eu-repo/semantics/publishedVersion"},{"id":"pmh:oai:dare.uva.nl:publications/7da9fc6e-1751-4b44-9047-fb9ffa134806","is_oa":true,"landing_page_url":"https://hdl.handle.net/11245.1/7da9fc6e-1751-4b44-9047-fb9ffa134806","pdf_url":"https://pure.uva.nl/ws/files/308244817/3603166.3632535.pdf","source":{"id":"https://openalex.org/S4306400088","display_name":"UvA-DARE (University of Amsterdam)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I887064364","host_organization_name":"University of Amsterdam","host_organization_lineage":["https://openalex.org/I887064364"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Gallego, A, Odyurt, U, Cheng, Y, Wang, Y & Zhao, Z 2023, Machine Learning Inference on Serverless Platforms Using Model Decomposition. in The 16th IEEE/ACM International Conference on Utility and Cloud Computing (UCC 2023) : 4-7 December 2023, Hotel Villa Diadoro, Taormina (ME), Italy., 33, Association for Computing Machinery, New York, New York, 16th IEEE/ACM International Conference on Utility and Cloud Computing, UCC 2023, Taormina, Italy, 4/12/23. https://doi.org/10.1145/3603166.3632535","raw_type":"info:eu-repo/semantics/publishedVersion"},{"id":"pmh:oai:repository.ubn.ru.nl:2066/308588","is_oa":true,"landing_page_url":"https://repository.ubn.ru.nl/handle/2066/308588","pdf_url":"https://repository.ubn.ru.nl/bitstream/handle/2066/308588/1/308588.pdf","source":{"id":"https://openalex.org/S4306401067","display_name":"Radboud Repository (Radboud University)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I145872427","host_organization_name":"Radboud University Nijmegen","host_organization_lineage":["https://openalex.org/I145872427"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Rana, O. (ed.), UCC '23: IEEE/ACM 16th International Conference on Utility and Cloud Computing Taormina (Messina) Italy December 4 - 7, 2023, pp. 1-6","raw_type":"Article in monograph or in proceedings"}],"best_oa_location":{"id":"doi:10.1145/3603166.3632535","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3603166.3632535","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3603166.3632535","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 IEEE/ACM 16th International Conference on Utility and Cloud Computing","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G2300613588","display_name":null,"funder_award_id":"860627","funder_id":"https://openalex.org/F4320320300","funder_display_name":"European Commission"},{"id":"https://openalex.org/G4292344142","display_name":null,"funder_award_id":"860627","funder_id":"https://openalex.org/F4320332999","funder_display_name":"Horizon 2020 Framework Programme"},{"id":"https://openalex.org/G8072458336","display_name":null,"funder_award_id":"101094227","funder_id":"https://openalex.org/F4320320300","funder_display_name":"European Commission"}],"funders":[{"id":"https://openalex.org/F4320320300","display_name":"European Commission","ror":"https://ror.org/00k4n6c32"},{"id":"https://openalex.org/F4320321800","display_name":"Nederlandse Organisatie voor Wetenschappelijk Onderzoek","ror":"https://ror.org/04jsz6e67"},{"id":"https://openalex.org/F4320332999","display_name":"Horizon 2020 Framework Programme","ror":"https://ror.org/00k4n6c32"}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4393928174.pdf","grobid_xml":"https://content.openalex.org/works/W4393928174.grobid-xml"},"referenced_works_count":10,"referenced_works":["https://openalex.org/W2612193523","https://openalex.org/W2793714280","https://openalex.org/W2889893539","https://openalex.org/W2896180420","https://openalex.org/W2963988417","https://openalex.org/W2996705685","https://openalex.org/W3005276590","https://openalex.org/W3019166713","https://openalex.org/W3121702752","https://openalex.org/W4293234116"],"related_works":["https://openalex.org/W2961085424","https://openalex.org/W4306674287","https://openalex.org/W3046775127","https://openalex.org/W3107602296","https://openalex.org/W3170094116","https://openalex.org/W4386462264","https://openalex.org/W4364306694","https://openalex.org/W4312192474","https://openalex.org/W4283697347","https://openalex.org/W4210805261"],"abstract_inverted_index":{"Serverless":[0,23,51,62,95,108],"offers":[1],"a":[2,64,94],"scalable":[3],"and":[4,54,61],"cost-effective":[5],"service":[6],"model":[7,121,146],"for":[8,112,119],"users":[9],"to":[10,28,47,81],"run":[11],"applications":[12],"without":[13],"focusing":[14],"on":[15,106,141,160],"underlying":[16],"infrastructure":[17],"or":[18],"physical":[19],"servers.":[20],"While":[21],"the":[22,30,48,57,107,135,145,150,158],"architecture":[24,155],"is":[25,43,63],"not":[26],"designed":[27],"address":[29],"unique":[31],"challenges":[32],"posed":[33],"by":[34,110],"resource-intensive":[35],"workloads,":[36],"e.g.,":[37],"Machine":[38],"Learning":[39],"(ML)":[40],"tasks,":[41],"it":[42],"highly":[44],"scalable.":[45],"Due":[46],"limitations":[49],"of":[50,59,73,99,137,144,153],"function":[52],"deployment":[53],"resource":[55],"provisioning,":[56],"combination":[58],"ML":[60,75,87,120,138],"complex":[65],"undertaking.":[66],"We":[67,84],"tackle":[68],"this":[69,154],"problem":[70],"through":[71],"decomposition":[72,132],"large":[74],"models":[76],"into":[77],"smaller":[78],"sub-models,":[79],"referred":[80],"as":[82,93,164],"slices.":[83],"set":[85],"up":[86],"inference":[88,139],"tasks":[89,140],"using":[90],"these":[91],"slices":[92],"workflow,":[96],"i.e.,":[97],"sequence":[98],"functions.":[100],"Our":[101],"experimental":[102],"evaluations":[103],"are":[104],"performed":[105],"offering":[109],"AWS":[111],"demonstration":[113],"purposes,":[114],"considering":[115],"an":[116],"open-source":[117],"format":[118],"representation,":[122],"Open":[123],"Neural":[124],"Network":[125],"Exchange.":[126],"Achieved":[127],"results":[128],"portray":[129],"that":[130],"our":[131],"method":[133],"enables":[134],"execution":[136],"Serverless,":[142],"regardless":[143],"size,":[147],"benefiting":[148],"from":[149],"high":[151],"scalability":[152],"while":[156],"lowering":[157],"strain":[159],"computing":[161],"resources,":[162],"such":[163],"required":[165],"run-time":[166],"memory.":[167]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":3}],"updated_date":"2026-05-17T08:19:37.847499","created_date":"2024-04-05T00:00:00"}
