{"id":"https://openalex.org/W7123836324","doi":"https://doi.org/10.1145/3772052.3772217","title":"SneakPeek: Data-Aware Model Selection and Scheduling for Inference Serving on the Edge","display_name":"SneakPeek: Data-Aware Model Selection and Scheduling for Inference Serving on the Edge","publication_year":2025,"publication_date":"2025-11-19","ids":{"openalex":"https://openalex.org/W7123836324","doi":"https://doi.org/10.1145/3772052.3772217"},"language":null,"primary_location":{"id":"doi:10.1145/3772052.3772217","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3772052.3772217","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2025 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/A5053038544","display_name":"Joel Wolfrath","orcid":"https://orcid.org/0000-0002-7251-3740"},"institutions":[{"id":"https://openalex.org/I130238516","display_name":"University of Minnesota","ror":"https://ror.org/017zqws13","country_code":"US","type":"education","lineage":["https://openalex.org/I130238516"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Joel Wolfrath","raw_affiliation_strings":["University of Minnesota, Minneapolis, USA"],"raw_orcid":"https://orcid.org/0000-0002-7251-3740","affiliations":[{"raw_affiliation_string":"University of Minnesota, Minneapolis, USA","institution_ids":["https://openalex.org/I130238516"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5120861757","display_name":"Daniel Frink","orcid":null},"institutions":[{"id":"https://openalex.org/I130238516","display_name":"University of Minnesota","ror":"https://ror.org/017zqws13","country_code":"US","type":"education","lineage":["https://openalex.org/I130238516"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Daniel Frink","raw_affiliation_strings":["University of Minnesota, Minneapolis, USA"],"raw_orcid":"https://orcid.org/0009-0006-8197-0536","affiliations":[{"raw_affiliation_string":"University of Minnesota, Minneapolis, USA","institution_ids":["https://openalex.org/I130238516"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5006850370","display_name":"Abhishek Chandra","orcid":"https://orcid.org/0000-0001-9914-2604"},"institutions":[{"id":"https://openalex.org/I130238516","display_name":"University of Minnesota","ror":"https://ror.org/017zqws13","country_code":"US","type":"education","lineage":["https://openalex.org/I130238516"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Abhishek Chandra","raw_affiliation_strings":["University of Minnesota, Minneapolis, USA"],"raw_orcid":"https://orcid.org/0000-0001-9914-2604","affiliations":[{"raw_affiliation_string":"University of Minnesota, Minneapolis, USA","institution_ids":["https://openalex.org/I130238516"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.75419136,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"748","last_page":"761"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T14347","display_name":"Big Data and Digital Economy","score":0.19040000438690186,"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/T14347","display_name":"Big Data and Digital Economy","score":0.19040000438690186,"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/T10036","display_name":"Advanced Neural Network Applications","score":0.16300000250339508,"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/T10101","display_name":"Cloud Computing and Resource Management","score":0.07819999754428864,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/inference","display_name":"Inference","score":0.7414000034332275},{"id":"https://openalex.org/keywords/scheduling","display_name":"Scheduling (production processes)","score":0.6714000105857849},{"id":"https://openalex.org/keywords/approximate-inference","display_name":"Approximate inference","score":0.4862000048160553},{"id":"https://openalex.org/keywords/scaling","display_name":"Scaling","score":0.3774999976158142},{"id":"https://openalex.org/keywords/model-selection","display_name":"Model selection","score":0.37139999866485596},{"id":"https://openalex.org/keywords/data-modeling","display_name":"Data modeling","score":0.3465000092983246},{"id":"https://openalex.org/keywords/selection","display_name":"Selection (genetic algorithm)","score":0.34459999203681946},{"id":"https://openalex.org/keywords/enhanced-data-rates-for-gsm-evolution","display_name":"Enhanced Data Rates for GSM Evolution","score":0.32170000672340393}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8226000070571899},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.7414000034332275},{"id":"https://openalex.org/C206729178","wikidata":"https://www.wikidata.org/wiki/Q2271896","display_name":"Scheduling (production processes)","level":2,"score":0.6714000105857849},{"id":"https://openalex.org/C2777472644","wikidata":"https://www.wikidata.org/wiki/Q16968992","display_name":"Approximate inference","level":3,"score":0.4862000048160553},{"id":"https://openalex.org/C120314980","wikidata":"https://www.wikidata.org/wiki/Q180634","display_name":"Distributed computing","level":1,"score":0.4000000059604645},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3953999876976013},{"id":"https://openalex.org/C99844830","wikidata":"https://www.wikidata.org/wiki/Q102441924","display_name":"Scaling","level":2,"score":0.3774999976158142},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.37290000915527344},{"id":"https://openalex.org/C93959086","wikidata":"https://www.wikidata.org/wiki/Q6888345","display_name":"Model selection","level":2,"score":0.37139999866485596},{"id":"https://openalex.org/C67186912","wikidata":"https://www.wikidata.org/wiki/Q367664","display_name":"Data modeling","level":2,"score":0.3465000092983246},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.3450999855995178},{"id":"https://openalex.org/C81917197","wikidata":"https://www.wikidata.org/wiki/Q628760","display_name":"Selection (genetic algorithm)","level":2,"score":0.34459999203681946},{"id":"https://openalex.org/C162307627","wikidata":"https://www.wikidata.org/wiki/Q204833","display_name":"Enhanced Data Rates for GSM Evolution","level":2,"score":0.32170000672340393},{"id":"https://openalex.org/C2779960059","wikidata":"https://www.wikidata.org/wiki/Q7113681","display_name":"Overhead (engineering)","level":2,"score":0.3206000030040741},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.31929999589920044},{"id":"https://openalex.org/C107568181","wikidata":"https://www.wikidata.org/wiki/Q5319000","display_name":"Dynamic priority scheduling","level":3,"score":0.31150001287460327},{"id":"https://openalex.org/C31689143","wikidata":"https://www.wikidata.org/wiki/Q733809","display_name":"Fair-share scheduling","level":3,"score":0.3082999885082245},{"id":"https://openalex.org/C138236772","wikidata":"https://www.wikidata.org/wiki/Q25098575","display_name":"Edge device","level":3,"score":0.30570000410079956},{"id":"https://openalex.org/C55416958","wikidata":"https://www.wikidata.org/wiki/Q6206757","display_name":"Job shop scheduling","level":3,"score":0.29829999804496765},{"id":"https://openalex.org/C48044578","wikidata":"https://www.wikidata.org/wiki/Q727490","display_name":"Scalability","level":2,"score":0.2639000117778778},{"id":"https://openalex.org/C114289077","wikidata":"https://www.wikidata.org/wiki/Q3284399","display_name":"Statistical model","level":2,"score":0.26019999384880066}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3772052.3772217","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3772052.3772217","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2025 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":28,"referenced_works":["https://openalex.org/W5599802","https://openalex.org/W2075889702","https://openalex.org/W2162800060","https://openalex.org/W2605258629","https://openalex.org/W2678047256","https://openalex.org/W2794670651","https://openalex.org/W2924706891","https://openalex.org/W2950601690","https://openalex.org/W3030870789","https://openalex.org/W3042619474","https://openalex.org/W3047268902","https://openalex.org/W3081360282","https://openalex.org/W3104334086","https://openalex.org/W3165292244","https://openalex.org/W3186289964","https://openalex.org/W3217455057","https://openalex.org/W4280633167","https://openalex.org/W4282577879","https://openalex.org/W4285197124","https://openalex.org/W4312199008","https://openalex.org/W4377224985","https://openalex.org/W4390738727","https://openalex.org/W4393904734","https://openalex.org/W4394892775","https://openalex.org/W4400433711","https://openalex.org/W4400770592","https://openalex.org/W4402044606","https://openalex.org/W4415124086"],"related_works":[],"abstract_inverted_index":{"Modern":[0],"applications":[1,32],"increasingly":[2],"rely":[3,34],"on":[4,35,114],"inference":[5,122],"serving":[6],"systems":[7,21],"to":[8,26,62,106,127],"provide":[9],"low-latency":[10],"insights":[11],"with":[12,28],"a":[13,52,146],"diverse":[14],"set":[15],"of":[16,110,134,140,149],"machine":[17],"learning":[18],"models.":[19],"Existing":[20],"often":[22],"utilize":[23],"resource":[24],"elasticity":[25],"scale":[27],"demand.":[29],"However,":[30],"many":[31],"cannot":[33],"hardware":[36],"scaling":[37,61],"when":[38],"deployed":[39],"at":[40],"the":[41,85,90,115,132,154],"edge":[42],"or":[43],"other":[44],"resource-constrained":[45],"environments.":[46,188],"In":[47],"this":[48,95],"work,":[49],"we":[50,97,102,119,171],"propose":[51,98],"model":[53,80,111],"selection":[54],"and":[55,130,138,160,165,181],"scheduling":[56,125],"algorithm":[57],"that":[58,72,75,173],"implements":[59],"accuracy":[60,81,159,183],"increase":[63],"efficiency":[64],"for":[65],"these":[66,186],"more":[67],"constrained":[68],"deployments.":[69],"We":[70],"show":[71,172],"existing":[73],"schedulers":[74],"make":[76],"decisions":[77,126],"using":[78,99],"profiled":[79],"are":[82],"biased":[83],"toward":[84],"label":[86],"distribution":[87],"present":[88],"in":[89,137,178,185],"test":[91],"dataset.":[92],"To":[93],"address":[94],"problem,":[96],"ML":[100],"models-which":[101],"call":[103],"SneakPeek":[104],"models-":[105],"dynamically":[107],"adjust":[108],"estimates":[109],"accuracy,":[112],"based":[113],"underlying":[116],"data.":[117],"Furthermore,":[118],"greedily":[120],"incorporate":[121],"batching":[123],"into":[124],"improve":[128],"throughput":[129],"avoid":[131],"overhead":[133],"swapping":[135],"models":[136,166],"out":[139],"GPU":[141],"memory.":[142],"Our":[143],"approach":[144],"employs":[145],"new":[147],"notion":[148],"request":[150],"priority,":[151],"which":[152],"navigates":[153],"trade-off":[155],"between":[156],"attaining":[157],"high":[158],"satisfying":[161],"deadlines.":[162],"Using":[163],"data":[164],"from":[167],"three":[168],"real-world":[169],"applications,":[170],"our":[174],"proposed":[175],"approaches":[176],"result":[177],"higher-utility":[179],"schedules":[180],"higher":[182],"inferences":[184],"hardware-constrained":[187]},"counts_by_year":[],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2026-01-14T00:00:00"}