{"id":"https://openalex.org/W7084103609","doi":"https://doi.org/10.1109/infocom55648.2025.11044632","title":"Accelerating End-Cloud Collaborative Inference via Near Bubble-Free Pipeline Optimization","display_name":"Accelerating End-Cloud Collaborative Inference via Near Bubble-Free Pipeline Optimization","publication_year":2025,"publication_date":"2025-05-19","ids":{"openalex":"https://openalex.org/W7084103609","doi":"https://doi.org/10.1109/infocom55648.2025.11044632"},"language":"en","primary_location":{"id":"doi:10.1109/infocom55648.2025.11044632","is_oa":false,"landing_page_url":"https://doi.org/10.1109/infocom55648.2025.11044632","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE INFOCOM 2025 - IEEE Conference on Computer Communications","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":null,"display_name":"Luyao Gao","orcid":null},"institutions":[{"id":"https://openalex.org/I126520041","display_name":"University of Science and Technology of China","ror":"https://ror.org/04c4dkn09","country_code":"CN","type":"education","lineage":["https://openalex.org/I126520041","https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Luyao Gao","raw_affiliation_strings":["School of Computer Science and Technology, University of Science and Technology of China,China"],"affiliations":[{"raw_affiliation_string":"School of Computer Science and Technology, University of Science and Technology of China,China","institution_ids":["https://openalex.org/I126520041"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Jianchun Liu","orcid":null},"institutions":[{"id":"https://openalex.org/I126520041","display_name":"University of Science and Technology of China","ror":"https://ror.org/04c4dkn09","country_code":"CN","type":"education","lineage":["https://openalex.org/I126520041","https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jianchun Liu","raw_affiliation_strings":["School of Computer Science and Technology, University of Science and Technology of China,China"],"affiliations":[{"raw_affiliation_string":"School of Computer Science and Technology, University of Science and Technology of China,China","institution_ids":["https://openalex.org/I126520041"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Hongli Xu","orcid":null},"institutions":[{"id":"https://openalex.org/I126520041","display_name":"University of Science and Technology of China","ror":"https://ror.org/04c4dkn09","country_code":"CN","type":"education","lineage":["https://openalex.org/I126520041","https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Hongli Xu","raw_affiliation_strings":["School of Computer Science and Technology, University of Science and Technology of China,China"],"affiliations":[{"raw_affiliation_string":"School of Computer Science and Technology, University of Science and Technology of China,China","institution_ids":["https://openalex.org/I126520041"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Sun Xu","orcid":null},"institutions":[{"id":"https://openalex.org/I126520041","display_name":"University of Science and Technology of China","ror":"https://ror.org/04c4dkn09","country_code":"CN","type":"education","lineage":["https://openalex.org/I126520041","https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Sun Xu","raw_affiliation_strings":["School of Computer Science and Technology, University of Science and Technology of China,China"],"affiliations":[{"raw_affiliation_string":"School of Computer Science and Technology, University of Science and Technology of China,China","institution_ids":["https://openalex.org/I126520041"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Qianpiao Ma","orcid":null},"institutions":[{"id":"https://openalex.org/I36399199","display_name":"Nanjing University of Science and Technology","ror":"https://ror.org/00xp9wg62","country_code":"CN","type":"education","lineage":["https://openalex.org/I36399199"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Qianpiao Ma","raw_affiliation_strings":["School of Computer Science and Engineering, Nanjing University of Science and Technology,China"],"affiliations":[{"raw_affiliation_string":"School of Computer Science and Engineering, Nanjing University of Science and Technology,China","institution_ids":["https://openalex.org/I36399199"]}]},{"author_position":"last","author":{"id":null,"display_name":"Liusheng Huang","orcid":null},"institutions":[{"id":"https://openalex.org/I126520041","display_name":"University of Science and Technology of China","ror":"https://ror.org/04c4dkn09","country_code":"CN","type":"education","lineage":["https://openalex.org/I126520041","https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Liusheng Huang","raw_affiliation_strings":["School of Computer Science and Technology, University of Science and Technology of China,China"],"affiliations":[{"raw_affiliation_string":"School of Computer Science and Technology, University of Science and Technology of China,China","institution_ids":["https://openalex.org/I126520041"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":6,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I126520041"],"apc_list":null,"apc_paid":null,"fwci":0.7428,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.79254557,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":91,"max":95},"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"10"},"is_retracted":false,"is_paratext":false,"is_xpac":true,"primary_topic":{"id":"https://openalex.org/T10232","display_name":"Optical Network Technologies","score":0.3587000072002411,"subfield":{"id":"https://openalex.org/subfields/2208","display_name":"Electrical and Electronic Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},"topics":[{"id":"https://openalex.org/T10232","display_name":"Optical Network Technologies","score":0.3587000072002411,"subfield":{"id":"https://openalex.org/subfields/2208","display_name":"Electrical and Electronic Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T12611","display_name":"Neural Networks and Reservoir Computing","score":0.1673000007867813,"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/T10988","display_name":"Advanced Fiber Laser Technologies","score":0.1096000000834465,"subfield":{"id":"https://openalex.org/subfields/3107","display_name":"Atomic and Molecular Physics, and Optics"},"field":{"id":"https://openalex.org/fields/31","display_name":"Physics and Astronomy"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/inference","display_name":"Inference","score":0.6879000067710876},{"id":"https://openalex.org/keywords/pipeline","display_name":"Pipeline (software)","score":0.633400022983551},{"id":"https://openalex.org/keywords/cloud-computing","display_name":"Cloud computing","score":0.6136999726295471},{"id":"https://openalex.org/keywords/component","display_name":"Component (thermodynamics)","score":0.4984999895095825},{"id":"https://openalex.org/keywords/scheduling","display_name":"Scheduling (production processes)","score":0.4677000045776367},{"id":"https://openalex.org/keywords/quantization","display_name":"Quantization (signal processing)","score":0.453900009393692},{"id":"https://openalex.org/keywords/workload","display_name":"Workload","score":0.4514999985694885},{"id":"https://openalex.org/keywords/latency","display_name":"Latency (audio)","score":0.4180999994277954}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7368000149726868},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.6879000067710876},{"id":"https://openalex.org/C43521106","wikidata":"https://www.wikidata.org/wiki/Q2165493","display_name":"Pipeline (software)","level":2,"score":0.633400022983551},{"id":"https://openalex.org/C79974875","wikidata":"https://www.wikidata.org/wiki/Q483639","display_name":"Cloud computing","level":2,"score":0.6136999726295471},{"id":"https://openalex.org/C168167062","wikidata":"https://www.wikidata.org/wiki/Q1117970","display_name":"Component (thermodynamics)","level":2,"score":0.4984999895095825},{"id":"https://openalex.org/C120314980","wikidata":"https://www.wikidata.org/wiki/Q180634","display_name":"Distributed computing","level":1,"score":0.47380000352859497},{"id":"https://openalex.org/C206729178","wikidata":"https://www.wikidata.org/wiki/Q2271896","display_name":"Scheduling (production processes)","level":2,"score":0.4677000045776367},{"id":"https://openalex.org/C28855332","wikidata":"https://www.wikidata.org/wiki/Q198099","display_name":"Quantization (signal processing)","level":2,"score":0.453900009393692},{"id":"https://openalex.org/C2778476105","wikidata":"https://www.wikidata.org/wiki/Q628539","display_name":"Workload","level":2,"score":0.4514999985694885},{"id":"https://openalex.org/C82876162","wikidata":"https://www.wikidata.org/wiki/Q17096504","display_name":"Latency (audio)","level":2,"score":0.4180999994277954},{"id":"https://openalex.org/C79403827","wikidata":"https://www.wikidata.org/wiki/Q3988","display_name":"Real-time computing","level":1,"score":0.4180000126361847},{"id":"https://openalex.org/C46743427","wikidata":"https://www.wikidata.org/wiki/Q1341685","display_name":"Inference engine","level":3,"score":0.37950000166893005},{"id":"https://openalex.org/C5119721","wikidata":"https://www.wikidata.org/wiki/Q220501","display_name":"Quality of service","level":2,"score":0.3668000102043152},{"id":"https://openalex.org/C186108316","wikidata":"https://www.wikidata.org/wiki/Q352530","display_name":"Adaptive neuro fuzzy inference system","level":4,"score":0.3328999876976013},{"id":"https://openalex.org/C157764524","wikidata":"https://www.wikidata.org/wiki/Q1383412","display_name":"Throughput","level":3,"score":0.328900009393692},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.3240000009536743},{"id":"https://openalex.org/C31258907","wikidata":"https://www.wikidata.org/wiki/Q1301371","display_name":"Computer network","level":1,"score":0.2662000060081482},{"id":"https://openalex.org/C557945733","wikidata":"https://www.wikidata.org/wiki/Q389772","display_name":"Data transmission","level":2,"score":0.25529998540878296},{"id":"https://openalex.org/C68694590","wikidata":"https://www.wikidata.org/wiki/Q267558","display_name":"Original equipment manufacturer","level":2,"score":0.2524000108242035},{"id":"https://openalex.org/C45374587","wikidata":"https://www.wikidata.org/wiki/Q12525525","display_name":"Computation","level":2,"score":0.251800000667572},{"id":"https://openalex.org/C761482","wikidata":"https://www.wikidata.org/wiki/Q118093","display_name":"Transmission (telecommunications)","level":2,"score":0.2515000104904175}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/infocom55648.2025.11044632","is_oa":false,"landing_page_url":"https://doi.org/10.1109/infocom55648.2025.11044632","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE INFOCOM 2025 - IEEE Conference on Computer Communications","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":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"End-cloud":[0],"collaboration":[1],"offers":[2],"a":[3,65,127],"promising":[4],"strategy":[5,130],"to":[6,26,99,108,131,187],"enhance":[7],"the":[8,20,30,32,110,116,139,149,156,167],"Quality":[9],"of":[10,19,112,169],"Service":[11],"(QoS)":[12],"in":[13,48,52,119,148,171],"DNN":[14],"inference":[15,21,80,173,190],"by":[16],"offloading":[17],"portions":[18],"workload":[22],"from":[23],"end":[24],"devices":[25],"cloud":[27],"servers.":[28],"Despite":[29],"potential,":[31],"complex":[33],"model":[34,102],"architectures":[35],"and":[36,56,82,104,126,144,175,191],"dynamic":[37],"network":[38,162],"conditions":[39],"will":[40],"introduce":[41,64],"numerous":[42],"bubbles":[43],"(i.e.,":[44],"idle":[45],"waiting":[46],"time)":[47],"pipeline":[49,74,113,134],"execution,":[50],"resulting":[51],"inefficient":[53],"resource":[54],"utilization":[55],"degraded":[57],"QoS.":[58],"To":[59],"address":[60],"these":[61],"challenges,":[62],"we":[63],"novel":[66],"framework":[67],"named":[68],"COACH,":[69],"designed":[70],"for":[71],"near":[72],"bubble-free":[73],"collaborative":[75],"inference,":[76],"thereby":[77,159],"achieving":[78],"low":[79],"latency":[81,174],"high":[83],"system":[84,177,194],"throughput.":[85,178],"Initially,":[86],"COACH":[87,120,137,170,184],"employs":[88,121],"an":[89,94,122],"offline":[90],"component":[91,118],"that":[92],"utilizes":[93],"efficient":[95],"recursive":[96],"divide-and-conquer":[97],"algorithm":[98],"optimize":[100],"both":[101],"partitioning":[103],"transmission":[105],"quantization,":[106],"aiming":[107],"minimize":[109],"occurrence":[111],"bubbles.":[114],"Subsequently,":[115],"online":[117],"adaptive":[123],"quantization":[124,157],"adjustment":[125],"context-aware":[128],"caching":[129],"further":[132],"stabilize":[133],"execution.":[135],"Specifically,":[136],"analyzes":[138],"correlation":[140],"between":[141],"intermediate":[142],"data":[143],"label":[145],"semantic":[146],"centers":[147],"cache,":[150],"along":[151],"with":[152],"its":[153],"influence":[154],"on":[155],"adjustment,":[158],"effectively":[160],"accommodating":[161],"fluctuations.":[163],"Our":[164],"experiments":[165],"demonstrate":[166],"efficacy":[168],"reducing":[172],"enhancing":[176],"Notably,":[179],"while":[180],"maintaining":[181],"comparable":[182],"accuracy,":[183],"achieves":[185],"up":[186],"1.7\u00d7":[188],"faster":[189],"2.1\u00d7":[192],"higher":[193],"throughput":[195],"than":[196],"baselines.":[197]},"counts_by_year":[{"year":2025,"cited_by_count":1}],"updated_date":"2025-12-19T19:40:27.379048","created_date":"2025-10-10T00:00:00"}