{"id":"https://openalex.org/W4386365401","doi":"https://doi.org/10.1145/3603269.3604830","title":"AdaInf: Data Drift Adaptive Scheduling for Accurate and SLO-guaranteed Multiple-Model Inference Serving at Edge Servers","display_name":"AdaInf: Data Drift Adaptive Scheduling for Accurate and SLO-guaranteed Multiple-Model Inference Serving at Edge Servers","publication_year":2023,"publication_date":"2023-09-01","ids":{"openalex":"https://openalex.org/W4386365401","doi":"https://doi.org/10.1145/3603269.3604830"},"language":"en","primary_location":{"id":"doi:10.1145/3603269.3604830","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3603269.3604830","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3603269.3604830","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 ACM SIGCOMM 2023 Conference","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/10.1145/3603269.3604830","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5103080820","display_name":"Sudipta Saha Shubha","orcid":"https://orcid.org/0009-0002-9284-507X"},"institutions":[{"id":"https://openalex.org/I51556381","display_name":"University of Virginia","ror":"https://ror.org/0153tk833","country_code":"US","type":"education","lineage":["https://openalex.org/I51556381"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Sudipta Saha Shubha","raw_affiliation_strings":["Computer Science, University of Virginia, Charlottesville, Virginia, United States of America"],"raw_orcid":"https://orcid.org/0009-0002-9284-507X","affiliations":[{"raw_affiliation_string":"Computer Science, University of Virginia, Charlottesville, Virginia, United States of America","institution_ids":["https://openalex.org/I51556381"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5050569064","display_name":"Haiying Shen","orcid":"https://orcid.org/0000-0002-7548-6223"},"institutions":[{"id":"https://openalex.org/I51556381","display_name":"University of Virginia","ror":"https://ror.org/0153tk833","country_code":"US","type":"education","lineage":["https://openalex.org/I51556381"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Haiying Shen","raw_affiliation_strings":["Computer Science, University of Virginia, Charlottesville, Virginia, United States of America"],"raw_orcid":"https://orcid.org/0000-0002-7548-6223","affiliations":[{"raw_affiliation_string":"Computer Science, University of Virginia, Charlottesville, Virginia, United States of America","institution_ids":["https://openalex.org/I51556381"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I51556381"],"apc_list":null,"apc_paid":null,"fwci":2.7777,"has_fulltext":true,"cited_by_count":25,"citation_normalized_percentile":{"value":0.92392961,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":97,"max":100},"biblio":{"volume":null,"issue":null,"first_page":"473","last_page":"485"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10036","display_name":"Advanced Neural Network Applications","score":0.9991000294685364,"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":0.9991000294685364,"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/T13553","display_name":"Age of Information Optimization","score":0.998199999332428,"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/T11307","display_name":"Domain Adaptation and Few-Shot Learning","score":0.9962999820709229,"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":0.8632614016532898},{"id":"https://openalex.org/keywords/server","display_name":"Server","score":0.7105621695518494},{"id":"https://openalex.org/keywords/inference","display_name":"Inference","score":0.6637181043624878},{"id":"https://openalex.org/keywords/latency","display_name":"Latency (audio)","score":0.5376781821250916},{"id":"https://openalex.org/keywords/leverage","display_name":"Leverage (statistics)","score":0.5151692628860474},{"id":"https://openalex.org/keywords/real-time-computing","display_name":"Real-time computing","score":0.47821685671806335},{"id":"https://openalex.org/keywords/retraining","display_name":"Retraining","score":0.4760318100452423},{"id":"https://openalex.org/keywords/scheduling","display_name":"Scheduling (production processes)","score":0.46502256393432617},{"id":"https://openalex.org/keywords/edge-computing","display_name":"Edge computing","score":0.44665002822875977},{"id":"https://openalex.org/keywords/enhanced-data-rates-for-gsm-evolution","display_name":"Enhanced Data Rates for GSM Evolution","score":0.39187583327293396},{"id":"https://openalex.org/keywords/distributed-computing","display_name":"Distributed computing","score":0.37786033749580383},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3215758800506592},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.32077062129974365},{"id":"https://openalex.org/keywords/computer-network","display_name":"Computer network","score":0.22643333673477173}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8632614016532898},{"id":"https://openalex.org/C93996380","wikidata":"https://www.wikidata.org/wiki/Q44127","display_name":"Server","level":2,"score":0.7105621695518494},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.6637181043624878},{"id":"https://openalex.org/C82876162","wikidata":"https://www.wikidata.org/wiki/Q17096504","display_name":"Latency (audio)","level":2,"score":0.5376781821250916},{"id":"https://openalex.org/C153083717","wikidata":"https://www.wikidata.org/wiki/Q6535263","display_name":"Leverage (statistics)","level":2,"score":0.5151692628860474},{"id":"https://openalex.org/C79403827","wikidata":"https://www.wikidata.org/wiki/Q3988","display_name":"Real-time computing","level":1,"score":0.47821685671806335},{"id":"https://openalex.org/C2778712577","wikidata":"https://www.wikidata.org/wiki/Q3505966","display_name":"Retraining","level":2,"score":0.4760318100452423},{"id":"https://openalex.org/C206729178","wikidata":"https://www.wikidata.org/wiki/Q2271896","display_name":"Scheduling (production processes)","level":2,"score":0.46502256393432617},{"id":"https://openalex.org/C2778456923","wikidata":"https://www.wikidata.org/wiki/Q5337692","display_name":"Edge computing","level":3,"score":0.44665002822875977},{"id":"https://openalex.org/C162307627","wikidata":"https://www.wikidata.org/wiki/Q204833","display_name":"Enhanced Data Rates for GSM Evolution","level":2,"score":0.39187583327293396},{"id":"https://openalex.org/C120314980","wikidata":"https://www.wikidata.org/wiki/Q180634","display_name":"Distributed computing","level":1,"score":0.37786033749580383},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3215758800506592},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.32077062129974365},{"id":"https://openalex.org/C31258907","wikidata":"https://www.wikidata.org/wiki/Q1301371","display_name":"Computer network","level":1,"score":0.22643333673477173},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.0},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0},{"id":"https://openalex.org/C21547014","wikidata":"https://www.wikidata.org/wiki/Q1423657","display_name":"Operations management","level":1,"score":0.0},{"id":"https://openalex.org/C155202549","wikidata":"https://www.wikidata.org/wiki/Q178803","display_name":"International trade","level":1,"score":0.0},{"id":"https://openalex.org/C144133560","wikidata":"https://www.wikidata.org/wiki/Q4830453","display_name":"Business","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3603269.3604830","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3603269.3604830","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3603269.3604830","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 ACM SIGCOMM 2023 Conference","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.1145/3603269.3604830","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3603269.3604830","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3603269.3604830","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 ACM SIGCOMM 2023 Conference","raw_type":"proceedings-article"},"sustainable_development_goals":[{"score":0.44999998807907104,"display_name":"Decent work and economic growth","id":"https://metadata.un.org/sdg/8"}],"awards":[{"id":"https://openalex.org/G1250143932","display_name":null,"funder_award_id":"693JJ31950016","funder_id":"https://openalex.org/F4320332393","funder_display_name":"Federal Highway Administration"},{"id":"https://openalex.org/G164031158","display_name":"SPX: Integrating Persistent Memory in the Cloud","funder_award_id":"1822965","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G4140588867","display_name":"Efficient Astronomical Data Processing Among Distributed Astronomical Radio Observatories","funder_award_id":"2206522","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G6415360113","display_name":null,"funder_award_id":"NSF-1827674","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G7372718776","display_name":"PFI-RP: A Smart Building for Enhancing Human Performance, Comfort and Health","funder_award_id":"1827674","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G7415302333","display_name":null,"funder_award_id":"NSF-1822965","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"}],"funders":[{"id":"https://openalex.org/F4320306076","display_name":"National Science Foundation","ror":"https://ror.org/021nxhr62"},{"id":"https://openalex.org/F4320332393","display_name":"Federal Highway Administration","ror":"https://ror.org/0473rr271"}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4386365401.pdf","grobid_xml":"https://content.openalex.org/works/W4386365401.grobid-xml"},"referenced_works_count":28,"referenced_works":["https://openalex.org/W2105767494","https://openalex.org/W2139501017","https://openalex.org/W2565600385","https://openalex.org/W2599379624","https://openalex.org/W2763148304","https://openalex.org/W2899071864","https://openalex.org/W2912237282","https://openalex.org/W2913640523","https://openalex.org/W2950601690","https://openalex.org/W2956461999","https://openalex.org/W2963342110","https://openalex.org/W2964189064","https://openalex.org/W3030364939","https://openalex.org/W3033527233","https://openalex.org/W3096484587","https://openalex.org/W3114989277","https://openalex.org/W3138327474","https://openalex.org/W3156643189","https://openalex.org/W3162157550","https://openalex.org/W3212832037","https://openalex.org/W4213332096","https://openalex.org/W4221149750","https://openalex.org/W4236362309","https://openalex.org/W4285212262","https://openalex.org/W4289533987","https://openalex.org/W4293025059","https://openalex.org/W6798686915","https://openalex.org/W6891745771"],"related_works":["https://openalex.org/W2081982437","https://openalex.org/W4394857231","https://openalex.org/W2027050655","https://openalex.org/W3028244590","https://openalex.org/W4254349500","https://openalex.org/W2014369232","https://openalex.org/W3122042562","https://openalex.org/W2050078012","https://openalex.org/W2060761133","https://openalex.org/W3154796165"],"abstract_inverted_index":{"Various":[0],"audio":[1],"and":[2,104,112,137,149,168,174,225],"video":[3],"applications":[4,154],"rely":[5],"on":[6,14,156,183,208,247],"multiple":[7],"deep":[8],"neural":[9],"network":[10],"(DNN)":[11],"models":[12,84],"deployed":[13],"edge":[15,142,249],"servers":[16,143],"to":[17,46,64,119,170,200,223,231,234],"conduct":[18],"inference":[19,169],"with":[20],"ms-level":[21],"latency":[22],"service-level-objectives":[23],"(SLOs).":[24],"To":[25],"avoid":[26],"accuracy":[27,54,220,239],"decreases":[28],"caused":[29],"by":[30,96,221,229],"data":[31,91,131],"drift,":[32,92],"continual":[33],"retraining":[34,94,148,167,180],"is":[35],"necessary.":[36],"However,":[37],"this":[38,56,66,69,77,198],"poses":[39],"a":[40,130],"challenge":[41],"for":[42,135,251],"GPU":[43,151,164,177,245],"resource":[44],"allocation":[45],"satisfy":[47,171],"the":[48,113,194,202,248,252],"tight":[49],"SLOs":[50],"while":[51],"maintaining":[52],"high":[53],"in":[55,76,197],"scenario.":[57],"There":[58],"has":[59],"been":[60],"no":[61],"research":[62],"devoted":[63],"tackling":[65],"issue.":[67],"In":[68,187],"paper,":[70],"we":[71,128],"conducted":[72],"trace-based":[73],"experimental":[74,213],"analysis":[75],"particular":[78],"scenario,":[79],"which":[80],"shows":[81,215],"that":[82,98,192,216],"different":[83],"have":[85],"varying":[86],"degrees":[87],"of":[88,204],"impact":[89,185,203],"from":[90],"incremental":[93,147],"(proposed":[95],"us":[97],"retrains":[99],"certain":[100],"samples":[101],"before":[102],"inference)":[103],"early-exit":[105],"model":[106],"structures":[107],"can":[108,218],"help":[109],"increase":[110,219],"accuracy,":[111],"interdependencies":[114],"among":[115,153,179],"tasks":[116,181],"may":[117],"lead":[118],"significant":[120],"CPU-GPU":[121,205],"memory":[122,206],"communications.":[123],"Leveraging":[124],"these":[125],"unique":[126],"observations,":[127],"propose":[129],"drift":[132],"Adaptive":[133],"scheduler":[134],"accurate":[136],"SLO-guaranteed":[138],"Inference":[139],"serving":[140],"at":[141],"(AdaInf).":[144],"AdaInf":[145,189,217,241],"uses":[146],"allocates":[150,176],"amount":[152],"based":[155,182],"their":[157,184],"SLOs.":[158],"For":[159],"each":[160],"application,":[161],"it":[162],"splits":[163],"time":[165,178],"between":[166],"its":[172],"SLO,":[173],"then":[175],"degrees.":[186],"addition,":[188],"proposes":[190],"strategies":[191],"leverage":[193],"job":[195],"features":[196],"scenario":[199],"reduce":[201,226],"communications":[207],"latency.":[209],"Our":[210],"real":[211],"trace-driven":[212],"evaluation":[214],"up":[222,230],"21%":[224],"SLO":[227],"violations":[228],"54%":[232],"compared":[233],"existing":[235,253],"methods.":[236],"Achieving":[237],"similar":[238],"as":[240],"requires":[242],"4\u00d7":[243],"more":[244],"resources":[246],"server":[250],"method.":[254]},"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2025,"cited_by_count":16},{"year":2024,"cited_by_count":7}],"updated_date":"2026-06-26T08:34:08.712188","created_date":"2025-10-10T00:00:00"}