{"id":"https://openalex.org/W7123640040","doi":"https://doi.org/10.1145/3772052.3772261","title":"CIS: Checkpointed Inference for Data Drift-Resilient Model Serving at Edge Servers","display_name":"CIS: Checkpointed Inference for Data Drift-Resilient Model Serving at Edge Servers","publication_year":2025,"publication_date":"2025-11-19","ids":{"openalex":"https://openalex.org/W7123640040","doi":"https://doi.org/10.1145/3772052.3772261"},"language":null,"primary_location":{"id":"doi:10.1145/3772052.3772261","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3772052.3772261","pdf_url":null,"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 2025 ACM Symposium on Cloud Computing","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://doi.org/10.1145/3772052.3772261","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":["University of Virginia, Charlottesville, USA"],"raw_orcid":"https://orcid.org/0009-0002-9284-507X","affiliations":[{"raw_affiliation_string":"University of Virginia, Charlottesville, USA","institution_ids":["https://openalex.org/I51556381"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5122956632","display_name":"Haiying Shen","orcid":null},"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":["University of Virginia, Charlottesville, USA"],"raw_orcid":"https://orcid.org/0000-0002-7548-6223","affiliations":[{"raw_affiliation_string":"University of Virginia, Charlottesville, USA","institution_ids":["https://openalex.org/I51556381"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5031071237","display_name":"Ganesh Ananthanarayanan","orcid":"https://orcid.org/0000-0002-7479-1664"},"institutions":[{"id":"https://openalex.org/I1290206253","display_name":"Microsoft (United States)","ror":"https://ror.org/00d0nc645","country_code":"US","type":"company","lineage":["https://openalex.org/I1290206253"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Ganesh Ananthanarayanan","raw_affiliation_strings":["Microsoft, Redmond, USA"],"raw_orcid":"https://orcid.org/0000-0002-7479-1664","affiliations":[{"raw_affiliation_string":"Microsoft, Redmond, USA","institution_ids":["https://openalex.org/I1290206253"]}]}],"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":0.63559473,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"600","last_page":"613"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10273","display_name":"IoT and Edge/Fog Computing","score":0.2443999946117401,"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/T10273","display_name":"IoT and Edge/Fog Computing","score":0.2443999946117401,"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/T13553","display_name":"Age of Information Optimization","score":0.10409999638795853,"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/T10101","display_name":"Cloud Computing and Resource Management","score":0.09449999779462814,"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":0.8288999795913696},{"id":"https://openalex.org/keywords/server","display_name":"Server","score":0.7558000087738037},{"id":"https://openalex.org/keywords/latency","display_name":"Latency (audio)","score":0.677299976348877},{"id":"https://openalex.org/keywords/queueing-theory","display_name":"Queueing theory","score":0.48089998960494995},{"id":"https://openalex.org/keywords/enhanced-data-rates-for-gsm-evolution","display_name":"Enhanced Data Rates for GSM Evolution","score":0.45190000534057617},{"id":"https://openalex.org/keywords/retraining","display_name":"Retraining","score":0.4490000009536743},{"id":"https://openalex.org/keywords/edge-device","display_name":"Edge device","score":0.4260999858379364},{"id":"https://openalex.org/keywords/scheduling","display_name":"Scheduling (production processes)","score":0.4023999869823456},{"id":"https://openalex.org/keywords/data-modeling","display_name":"Data modeling","score":0.3905999958515167}],"concepts":[{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.8288999795913696},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8075000047683716},{"id":"https://openalex.org/C93996380","wikidata":"https://www.wikidata.org/wiki/Q44127","display_name":"Server","level":2,"score":0.7558000087738037},{"id":"https://openalex.org/C82876162","wikidata":"https://www.wikidata.org/wiki/Q17096504","display_name":"Latency (audio)","level":2,"score":0.677299976348877},{"id":"https://openalex.org/C22684755","wikidata":"https://www.wikidata.org/wiki/Q847526","display_name":"Queueing theory","level":2,"score":0.48089998960494995},{"id":"https://openalex.org/C162307627","wikidata":"https://www.wikidata.org/wiki/Q204833","display_name":"Enhanced Data Rates for GSM Evolution","level":2,"score":0.45190000534057617},{"id":"https://openalex.org/C2778712577","wikidata":"https://www.wikidata.org/wiki/Q3505966","display_name":"Retraining","level":2,"score":0.4490000009536743},{"id":"https://openalex.org/C138236772","wikidata":"https://www.wikidata.org/wiki/Q25098575","display_name":"Edge device","level":3,"score":0.4260999858379364},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4228000044822693},{"id":"https://openalex.org/C206729178","wikidata":"https://www.wikidata.org/wiki/Q2271896","display_name":"Scheduling (production processes)","level":2,"score":0.4023999869823456},{"id":"https://openalex.org/C67186912","wikidata":"https://www.wikidata.org/wiki/Q367664","display_name":"Data modeling","level":2,"score":0.3905999958515167},{"id":"https://openalex.org/C79403827","wikidata":"https://www.wikidata.org/wiki/Q3988","display_name":"Real-time computing","level":1,"score":0.37540000677108765},{"id":"https://openalex.org/C2777472644","wikidata":"https://www.wikidata.org/wiki/Q16968992","display_name":"Approximate inference","level":3,"score":0.37540000677108765},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.35499998927116394},{"id":"https://openalex.org/C134261354","wikidata":"https://www.wikidata.org/wiki/Q938438","display_name":"Statistical inference","level":2,"score":0.3481999933719635},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.33889999985694885},{"id":"https://openalex.org/C31258907","wikidata":"https://www.wikidata.org/wiki/Q1301371","display_name":"Computer network","level":1,"score":0.33709999918937683},{"id":"https://openalex.org/C120314980","wikidata":"https://www.wikidata.org/wiki/Q180634","display_name":"Distributed computing","level":1,"score":0.3352999985218048},{"id":"https://openalex.org/C196921405","wikidata":"https://www.wikidata.org/wiki/Q786431","display_name":"Online algorithm","level":2,"score":0.3176000118255615},{"id":"https://openalex.org/C2778456923","wikidata":"https://www.wikidata.org/wiki/Q5337692","display_name":"Edge computing","level":3,"score":0.3118000030517578},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.2987000048160553},{"id":"https://openalex.org/C160403385","wikidata":"https://www.wikidata.org/wiki/Q220543","display_name":"Queue","level":2,"score":0.29030001163482666},{"id":"https://openalex.org/C29202148","wikidata":"https://www.wikidata.org/wiki/Q287260","display_name":"Resource allocation","level":2,"score":0.29019999504089355},{"id":"https://openalex.org/C175154964","wikidata":"https://www.wikidata.org/wiki/Q380077","display_name":"Task analysis","level":3,"score":0.28870001435279846},{"id":"https://openalex.org/C206952183","wikidata":"https://www.wikidata.org/wiki/Q1193100","display_name":"Preemption","level":2,"score":0.26910001039505005},{"id":"https://openalex.org/C46637626","wikidata":"https://www.wikidata.org/wiki/Q6693015","display_name":"Low latency (capital markets)","level":2,"score":0.26669999957084656},{"id":"https://openalex.org/C102408133","wikidata":"https://www.wikidata.org/wiki/Q5156350","display_name":"Competitive analysis","level":3,"score":0.26179999113082886},{"id":"https://openalex.org/C123201435","wikidata":"https://www.wikidata.org/wiki/Q456632","display_name":"Information privacy","level":2,"score":0.2581000030040741},{"id":"https://openalex.org/C206345919","wikidata":"https://www.wikidata.org/wiki/Q20380951","display_name":"Resource (disambiguation)","level":2,"score":0.25450000166893005},{"id":"https://openalex.org/C75684735","wikidata":"https://www.wikidata.org/wiki/Q858810","display_name":"Big data","level":2,"score":0.2540000081062317},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.2500999867916107}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3772052.3772261","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3772052.3772261","pdf_url":null,"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 2025 ACM Symposium on Cloud Computing","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.1145/3772052.3772261","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3772052.3772261","pdf_url":null,"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 2025 ACM Symposium on Cloud Computing","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":19,"referenced_works":["https://openalex.org/W2105767494","https://openalex.org/W2194775991","https://openalex.org/W2763148304","https://openalex.org/W2950601690","https://openalex.org/W2963125010","https://openalex.org/W2964189064","https://openalex.org/W3205898353","https://openalex.org/W3212832037","https://openalex.org/W4213332096","https://openalex.org/W4236362309","https://openalex.org/W4285212262","https://openalex.org/W4293025059","https://openalex.org/W4386365401","https://openalex.org/W4387321091","https://openalex.org/W4393406915","https://openalex.org/W4394892775","https://openalex.org/W4394922627","https://openalex.org/W4394998727","https://openalex.org/W4405845698"],"related_works":[],"abstract_inverted_index":{"Small":[0],"deep":[1],"learning":[2],"models":[3,78],"deployed":[4],"at":[5],"edge":[6],"servers":[7],"suffer":[8],"from":[9,123],"decreasing":[10,29],"accuracy":[11,30,42,71,153],"due":[12],"to":[13,23,39,75,101,113,126,129,150,165],"data":[14,60],"drift":[15],"and":[16,31,43,58,98,158],"hence":[17],"require":[18],"continual":[19],"learning,":[20],"which":[21],"leads":[22],"resource":[24],"competition":[25],"with":[26,138],"inference":[27,68,86,107,127],"execution,":[28,108],"latency":[32,87],"service-level-objective":[33],"(SLO)":[34],"fulfillment.":[35,45],"Previous":[36],"methods":[37],"fail":[38],"maximize":[40],"both":[41],"SLO":[44,156],"To":[46,89],"address":[47,130],"this":[48],"problem,":[49],"we":[50],"propose":[51],"a":[52,95],"Checkpointed":[53],"Inference-based":[54],"system":[55],"for":[56],"accurate":[57],"SLO-guaranteed":[59],"drift-resilient":[61],"model":[62,82],"Serving":[63],"(CIS).":[64],"CIS":[65,93,109,147],"incorporates":[66],"checkpointed":[67],"-":[69],"maximizing":[70],"by":[72,135],"continuously":[73],"switching":[74,83,103,115],"intermediately":[76],"retrained":[77],"during":[79,106],"inference.":[80],"However,":[81],"introduces":[84],"significant":[85],"overhead.":[88],"mitigate":[90],"this,":[91],"first,":[92],"proposes":[94],"lightweight":[96],"allocation":[97],"placement":[99],"scheduler":[100],"minimize":[102],"time.":[104],"Second,":[105],"reorders":[110],"retraining":[111,124],"samples":[112],"reduce":[114],"frequency.":[116],"Third,":[117],"it":[118],"temporarily":[119],"reallocates":[120],"GPU":[121,162],"space":[122],"tasks":[125,128],"request":[131],"queuing":[132],"issue":[133],"caused":[134],"the":[136,166],"switching,":[137],"minimal":[139],"impact":[140],"on":[141],"accuracy.":[142,174],"Trace-driven":[143],"experiments":[144],"show":[145],"that":[146],"achieves":[148],"up":[149],"25.1%":[151],"higher":[152,173],"without":[154],"affecting":[155],"fulfillment,":[157],"requires":[159],"4\u00d7":[160],"lower":[161],"cost":[163],"compared":[164],"existing":[167],"method":[168],"in":[169],"achieving":[170],"similar":[171],"or":[172]},"counts_by_year":[],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2026-01-14T00:00:00"}