{"id":"https://openalex.org/W4399254960","doi":"https://doi.org/10.1145/3652963.3655046","title":"Automated Backend Allocation for Multi-Model, On-Device AI Inference","display_name":"Automated Backend Allocation for Multi-Model, On-Device AI Inference","publication_year":2024,"publication_date":"2024-06-01","ids":{"openalex":"https://openalex.org/W4399254960","doi":"https://doi.org/10.1145/3652963.3655046"},"language":"en","primary_location":{"id":"doi:10.1145/3652963.3655046","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3652963.3655046","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Abstracts of the 2024 ACM SIGMETRICS/IFIP PERFORMANCE Joint International Conference on Measurement and Modeling of Computer Systems","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/A5042109946","display_name":"Venkatraman Iyer","orcid":null},"institutions":[{"id":"https://openalex.org/I2250650973","display_name":"Samsung (South Korea)","ror":"https://ror.org/04w3jy968","country_code":"KR","type":"company","lineage":["https://openalex.org/I2250650973"]}],"countries":["KR"],"is_corresponding":true,"raw_author_name":"Venkatraman Iyer","raw_affiliation_strings":["Samsung Electronics, Seoul, Republic of Korea"],"raw_orcid":"https://orcid.org/0009-0004-8707-3196","affiliations":[{"raw_affiliation_string":"Samsung Electronics, Seoul, Republic of Korea","institution_ids":["https://openalex.org/I2250650973"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5010724789","display_name":"Sungho Lee","orcid":"https://orcid.org/0009-0005-3808-1592"},"institutions":[{"id":"https://openalex.org/I2250650973","display_name":"Samsung (South Korea)","ror":"https://ror.org/04w3jy968","country_code":"KR","type":"company","lineage":["https://openalex.org/I2250650973"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Sungho Lee","raw_affiliation_strings":["Samsung Electronics, Seoul, Republic of Korea"],"raw_orcid":"https://orcid.org/0009-0005-3808-1592","affiliations":[{"raw_affiliation_string":"Samsung Electronics, Seoul, Republic of Korea","institution_ids":["https://openalex.org/I2250650973"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5064421035","display_name":"Semun Lee","orcid":"https://orcid.org/0009-0001-3550-7958"},"institutions":[{"id":"https://openalex.org/I2250650973","display_name":"Samsung (South Korea)","ror":"https://ror.org/04w3jy968","country_code":"KR","type":"company","lineage":["https://openalex.org/I2250650973"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Semun Lee","raw_affiliation_strings":["Samsung Electronics, Seoul, Republic of Korea"],"raw_orcid":"https://orcid.org/0009-0001-3550-7958","affiliations":[{"raw_affiliation_string":"Samsung Electronics, Seoul, Republic of Korea","institution_ids":["https://openalex.org/I2250650973"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5003174140","display_name":"Juitem Joonwoo Kim","orcid":"https://orcid.org/0009-0008-5709-0875"},"institutions":[{"id":"https://openalex.org/I2250650973","display_name":"Samsung (South Korea)","ror":"https://ror.org/04w3jy968","country_code":"KR","type":"company","lineage":["https://openalex.org/I2250650973"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Juitem Joonwoo Kim","raw_affiliation_strings":["Samsung Electronics, Seoul, Republic of Korea"],"raw_orcid":"https://orcid.org/0009-0008-5709-0875","affiliations":[{"raw_affiliation_string":"Samsung Electronics, Seoul, Republic of Korea","institution_ids":["https://openalex.org/I2250650973"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102859295","display_name":"Hyunjun Kim","orcid":"https://orcid.org/0009-0001-3539-2679"},"institutions":[{"id":"https://openalex.org/I2250650973","display_name":"Samsung (South Korea)","ror":"https://ror.org/04w3jy968","country_code":"KR","type":"company","lineage":["https://openalex.org/I2250650973"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Hyunjun Kim","raw_affiliation_strings":["Samsung Electronics, Seoul, Republic of Korea"],"raw_orcid":"https://orcid.org/0009-0001-3539-2679","affiliations":[{"raw_affiliation_string":"Samsung Electronics, Seoul, Republic of Korea","institution_ids":["https://openalex.org/I2250650973"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5014882842","display_name":"Young-Jae Shin","orcid":"https://orcid.org/0009-0005-5749-2995"},"institutions":[{"id":"https://openalex.org/I2250650973","display_name":"Samsung (South Korea)","ror":"https://ror.org/04w3jy968","country_code":"KR","type":"company","lineage":["https://openalex.org/I2250650973"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Youngjae Shin","raw_affiliation_strings":["Samsung Electronics, Seoul, Republic of Korea"],"raw_orcid":"https://orcid.org/0009-0005-5749-2995","affiliations":[{"raw_affiliation_string":"Samsung Electronics, Seoul, Republic of Korea","institution_ids":["https://openalex.org/I2250650973"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":6,"corresponding_author_ids":["https://openalex.org/A5042109946"],"corresponding_institution_ids":["https://openalex.org/I2250650973"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.06484375,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"27","last_page":"28"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10036","display_name":"Advanced Neural Network Applications","score":0.9793000221252441,"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"}},"topics":[{"id":"https://openalex.org/T10036","display_name":"Advanced Neural Network Applications","score":0.9793000221252441,"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"}},{"id":"https://openalex.org/T12535","display_name":"Machine Learning and Data Classification","score":0.9750999808311462,"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/T10715","display_name":"Distributed and Parallel Computing Systems","score":0.9650999903678894,"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":0.7600257396697998},{"id":"https://openalex.org/keywords/inference","display_name":"Inference","score":0.6787203550338745},{"id":"https://openalex.org/keywords/data-modeling","display_name":"Data modeling","score":0.43969589471817017},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3261297345161438},{"id":"https://openalex.org/keywords/database","display_name":"Database","score":0.2771872282028198}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7600257396697998},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.6787203550338745},{"id":"https://openalex.org/C67186912","wikidata":"https://www.wikidata.org/wiki/Q367664","display_name":"Data modeling","level":2,"score":0.43969589471817017},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3261297345161438},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.2771872282028198}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3652963.3655046","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3652963.3655046","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Abstracts of the 2024 ACM SIGMETRICS/IFIP PERFORMANCE Joint International Conference on Measurement and Modeling of Computer Systems","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":2,"referenced_works":["https://openalex.org/W3186289964","https://openalex.org/W4389628299"],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2748952813","https://openalex.org/W2390279801","https://openalex.org/W2358668433","https://openalex.org/W4396701345","https://openalex.org/W2376932109","https://openalex.org/W2001405890","https://openalex.org/W4396696052","https://openalex.org/W2382290278","https://openalex.org/W4395014643"],"abstract_inverted_index":{"On-Device":[0],"Artificial":[1],"Intelligence":[2],"(AI)":[3],"services":[4,25],"such":[5],"as":[6,130,132],"face":[7],"recognition,":[8],"object":[9],"tracking":[10],"and":[11,35,57,87,96,109,121],"voice":[12],"recognition":[13],"are":[14],"rapidly":[15],"scaling":[16],"up":[17],"deployments":[18],"on":[19,33],"embedded,":[20],"memory-constrained":[21],"hardware":[22],"devices.":[23],"These":[24],"typically":[26],"delegate":[27],"AI":[28,78],"inference":[29,107],"models":[30],"for":[31],"execution":[32],"CPU":[34,86],"GPU":[36,40,88],"computing":[37],"backends.":[38],"While":[39],"delegation":[41],"is":[42,94],"a":[43,70,83,99],"common":[44],"practice":[45],"to":[46,72],"achieve":[47],"high":[48],"speed":[49],"computation,":[50],"the":[51],"approach":[52],"suffers":[53],"from":[54],"degraded":[55],"throughput":[56,126],"completion":[58],"times":[59],"under":[60],"multi-model":[61,137],"scenarios,":[62],"i.e.,":[63],"concurrently":[64],"executing":[65],"services.":[66],"This":[67],"paper":[68],"introduces":[69],"solution":[71],"sustain":[73],"performance":[74],"in":[75,125],"multi-model,":[76],"on-device":[77],"contexts":[79],"by":[80,98],"dynamically":[81],"allocating":[82],"combination":[84],"of":[85,101],"backends":[89],"per":[90,119],"model.":[91],"The":[92],"allocation":[93,114],"feedback-driven,":[95],"guided":[97],"knowledge":[100],"model-specific,":[102],"multi-objective":[103],"pareto":[104],"fronts":[105],"comprising":[106],"latency":[108],"memory":[110],"consumption.":[111],"Our":[112],"backend":[113],"algorithm":[115],"that":[116],"runs":[117],"online":[118],"model,":[120],"achieves":[122],"25-100%":[123],"improvement":[124],"over":[127],"static":[128],"allocations":[129],"well":[131],"load-balancing":[133],"scheduler":[134],"solutions":[135],"targeting":[136],"scenarios.":[138]},"counts_by_year":[],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}