{"id":"https://openalex.org/W7123338972","doi":"https://doi.org/10.1109/tpds.2026.3652171","title":"MEOCI: Model Partitioning and Early-Exit Point Selection Joint Optimization for Collaborative Inference in Vehicular Edge Computing","display_name":"MEOCI: Model Partitioning and Early-Exit Point Selection Joint Optimization for Collaborative Inference in Vehicular Edge Computing","publication_year":2026,"publication_date":"2026-01-12","ids":{"openalex":"https://openalex.org/W7123338972","doi":"https://doi.org/10.1109/tpds.2026.3652171"},"language":null,"primary_location":{"id":"doi:10.1109/tpds.2026.3652171","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tpds.2026.3652171","pdf_url":null,"source":{"id":"https://openalex.org/S97130795","display_name":"IEEE Transactions on Parallel and Distributed Systems","issn_l":"1045-9219","issn":["1045-9219","1558-2183","2161-9883"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Parallel and Distributed Systems","raw_type":"journal-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/A5122884021","display_name":"Chunlin Li","orcid":null},"institutions":[{"id":"https://openalex.org/I196699116","display_name":"Wuhan University of Technology","ror":"https://ror.org/03fe7t173","country_code":"CN","type":"education","lineage":["https://openalex.org/I196699116"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Chunlin Li","raw_affiliation_strings":["School of Computer and Artificial Intelligence, Wuhan University of Technology, Wuhan, China"],"affiliations":[{"raw_affiliation_string":"School of Computer and Artificial Intelligence, Wuhan University of Technology, Wuhan, China","institution_ids":["https://openalex.org/I196699116"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Jiaqi Wang","orcid":"https://orcid.org/0009-0002-9228-8971"},"institutions":[{"id":"https://openalex.org/I196699116","display_name":"Wuhan University of Technology","ror":"https://ror.org/03fe7t173","country_code":"CN","type":"education","lineage":["https://openalex.org/I196699116"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jiaqi Wang","raw_affiliation_strings":["School of Computer and Artificial Intelligence, Wuhan University of Technology, Wuhan, China"],"affiliations":[{"raw_affiliation_string":"School of Computer and Artificial Intelligence, Wuhan University of Technology, Wuhan, China","institution_ids":["https://openalex.org/I196699116"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5122880049","display_name":"Kun Jiang","orcid":null},"institutions":[{"id":"https://openalex.org/I196699116","display_name":"Wuhan University of Technology","ror":"https://ror.org/03fe7t173","country_code":"CN","type":"education","lineage":["https://openalex.org/I196699116"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Kun Jiang","raw_affiliation_strings":["School of Computer and Artificial Intelligence, Wuhan University of Technology, Wuhan, China"],"affiliations":[{"raw_affiliation_string":"School of Computer and Artificial Intelligence, Wuhan University of Technology, Wuhan, China","institution_ids":["https://openalex.org/I196699116"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5047942583","display_name":"Cheng Chen Xiong","orcid":null},"institutions":[{"id":"https://openalex.org/I196699116","display_name":"Wuhan University of Technology","ror":"https://ror.org/03fe7t173","country_code":"CN","type":"education","lineage":["https://openalex.org/I196699116"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Cheng Xiong","raw_affiliation_strings":["School of Computer and Artificial Intelligence, Wuhan University of Technology, Wuhan, China"],"affiliations":[{"raw_affiliation_string":"School of Computer and Artificial Intelligence, Wuhan University of Technology, Wuhan, China","institution_ids":["https://openalex.org/I196699116"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5122859351","display_name":"Shaohua Wan","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Shaohua Wan","raw_affiliation_strings":["Shenzhen Institute for Advanced Study, University of Electronic Science and Technology of China, Shenzhen, China"],"affiliations":[{"raw_affiliation_string":"Shenzhen Institute for Advanced Study, University of Electronic Science and Technology of China, Shenzhen, China","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5122884021"],"corresponding_institution_ids":["https://openalex.org/I196699116"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.07023393,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"37","issue":"3","first_page":"666","last_page":"679"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10273","display_name":"IoT and Edge/Fog Computing","score":0.31940001249313354,"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":0.31940001249313354,"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/T10761","display_name":"Vehicular Ad Hoc Networks (VANETs)","score":0.2045000046491623,"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/T13553","display_name":"Age of Information Optimization","score":0.10300000011920929,"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/inference","display_name":"Inference","score":0.8148000240325928},{"id":"https://openalex.org/keywords/enhanced-data-rates-for-gsm-evolution","display_name":"Enhanced Data Rates for GSM Evolution","score":0.526199996471405},{"id":"https://openalex.org/keywords/server","display_name":"Server","score":0.5234000086784363},{"id":"https://openalex.org/keywords/selection","display_name":"Selection (genetic algorithm)","score":0.45890000462532043},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.44850000739097595},{"id":"https://openalex.org/keywords/edge-computing","display_name":"Edge computing","score":0.44530001282691956},{"id":"https://openalex.org/keywords/approximate-inference","display_name":"Approximate inference","score":0.4318000078201294},{"id":"https://openalex.org/keywords/edge-device","display_name":"Edge device","score":0.4293999969959259}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8812000155448914},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.8148000240325928},{"id":"https://openalex.org/C162307627","wikidata":"https://www.wikidata.org/wiki/Q204833","display_name":"Enhanced Data Rates for GSM Evolution","level":2,"score":0.526199996471405},{"id":"https://openalex.org/C93996380","wikidata":"https://www.wikidata.org/wiki/Q44127","display_name":"Server","level":2,"score":0.5234000086784363},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.48240000009536743},{"id":"https://openalex.org/C81917197","wikidata":"https://www.wikidata.org/wiki/Q628760","display_name":"Selection (genetic algorithm)","level":2,"score":0.45890000462532043},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.44850000739097595},{"id":"https://openalex.org/C2778456923","wikidata":"https://www.wikidata.org/wiki/Q5337692","display_name":"Edge computing","level":3,"score":0.44530001282691956},{"id":"https://openalex.org/C2777472644","wikidata":"https://www.wikidata.org/wiki/Q16968992","display_name":"Approximate inference","level":3,"score":0.4318000078201294},{"id":"https://openalex.org/C138236772","wikidata":"https://www.wikidata.org/wiki/Q25098575","display_name":"Edge device","level":3,"score":0.4293999969959259},{"id":"https://openalex.org/C18555067","wikidata":"https://www.wikidata.org/wiki/Q8375051","display_name":"Joint (building)","level":2,"score":0.4185999929904938},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.4034999907016754},{"id":"https://openalex.org/C137836250","wikidata":"https://www.wikidata.org/wiki/Q984063","display_name":"Optimization problem","level":2,"score":0.40139999985694885},{"id":"https://openalex.org/C28719098","wikidata":"https://www.wikidata.org/wiki/Q44946","display_name":"Point (geometry)","level":2,"score":0.38199999928474426},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.3596999943256378},{"id":"https://openalex.org/C120314980","wikidata":"https://www.wikidata.org/wiki/Q180634","display_name":"Distributed computing","level":1,"score":0.3483999967575073},{"id":"https://openalex.org/C117896860","wikidata":"https://www.wikidata.org/wiki/Q11376","display_name":"Acceleration","level":2,"score":0.33180001378059387},{"id":"https://openalex.org/C134261354","wikidata":"https://www.wikidata.org/wiki/Q938438","display_name":"Statistical inference","level":2,"score":0.2971000075340271},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.29440000653266907},{"id":"https://openalex.org/C2775973920","wikidata":"https://www.wikidata.org/wiki/Q3252726","display_name":"Selection algorithm","level":3,"score":0.27970001101493835},{"id":"https://openalex.org/C2776036281","wikidata":"https://www.wikidata.org/wiki/Q48769818","display_name":"Constraint (computer-aided design)","level":2,"score":0.2727000117301941}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/tpds.2026.3652171","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tpds.2026.3652171","pdf_url":null,"source":{"id":"https://openalex.org/S97130795","display_name":"IEEE Transactions on Parallel and Distributed Systems","issn_l":"1045-9219","issn":["1045-9219","1558-2183","2161-9883"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Parallel and Distributed Systems","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/11","score":0.7902721762657166,"display_name":"Sustainable cities and communities"}],"awards":[{"id":"https://openalex.org/G3494558276","display_name":null,"funder_award_id":"62172438","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G6780035490","display_name":null,"funder_award_id":"62171330","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G6827686631","display_name":null,"funder_award_id":"62372344","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":38,"referenced_works":["https://openalex.org/W2094889932","https://openalex.org/W2594110377","https://openalex.org/W2600230189","https://openalex.org/W2604119386","https://openalex.org/W2901631215","https://openalex.org/W2980856918","https://openalex.org/W3004718830","https://openalex.org/W3011134162","https://openalex.org/W3035564946","https://openalex.org/W3047565185","https://openalex.org/W3109459504","https://openalex.org/W3134357852","https://openalex.org/W3167883061","https://openalex.org/W3182828306","https://openalex.org/W3200083976","https://openalex.org/W4221139753","https://openalex.org/W4236099117","https://openalex.org/W4285257856","https://openalex.org/W4285328302","https://openalex.org/W4312854700","https://openalex.org/W4313162985","https://openalex.org/W4388040616","https://openalex.org/W4389352526","https://openalex.org/W4389544459","https://openalex.org/W4394598054","https://openalex.org/W4394863036","https://openalex.org/W4395006897","https://openalex.org/W4401415014","https://openalex.org/W4401507016","https://openalex.org/W4402156376","https://openalex.org/W4402401656","https://openalex.org/W4404293892","https://openalex.org/W4407272600","https://openalex.org/W4407376412","https://openalex.org/W4409014188","https://openalex.org/W4409760044","https://openalex.org/W4412605616","https://openalex.org/W4416061157"],"related_works":[],"abstract_inverted_index":{"In":[0,34],"recent":[1],"years,":[2],"deep":[3],"neural":[4],"networks":[5],"(DNNs)":[6],"have":[7],"been":[8],"widely":[9],"used":[10],"in":[11],"Vehicular":[12],"Edge":[13],"Computing":[14],"(VEC),":[15],"becoming":[16],"the":[17,53,96,102,115,121,131,136,143,154,165,186],"core":[18],"technology":[19],"for":[20,88,196,200],"most":[21],"intelligent":[22],"applications.":[23],"However,":[24],"these":[25,69],"DNN":[26,177],"inference":[27,62,76,133,137,192],"tasks":[28,46],"are":[29],"usually":[30],"computation-intensive":[31],"and":[32,61,82,108,112,157,198],"latency-sensitive.":[33],"urban":[35],"autonomous":[36],"driving":[37],"scenarios,":[38],"when":[39],"a":[40],"large":[41],"number":[42],"of":[43,55,58,104,161],"vehicles":[44],"offload":[45],"to":[47,114,119,129,163,203],"roadside":[48],"units":[49],"(RSUs),":[50],"they":[51],"face":[52],"problem":[54],"computational":[56],"overload":[57],"edge":[59],"servers":[60],"delay":[63,134,193],"beyond":[64],"tolerable":[65],"limits.":[66],"To":[67],"address":[68],"challenges,":[70],"we":[71,93,141],"propose":[72,142],"an":[73],"edge-vehicle":[74],"collaborative":[75],"acceleration":[77],"mechanism,":[78],"namely":[79],"Model":[80],"partitioning":[81,99],"Early-exit":[83],"point":[84],"selection":[85],"joint":[86],"Optimization":[87],"Collaborative":[89],"Inference":[90],"(MEOCI).":[91],"Specifically,":[92],"dynamically":[94],"select":[95],"optimal":[97],"model":[98],"points":[100],"with":[101],"constraint":[103],"RSU":[105],"computing":[106,110],"resources":[107],"vehicle":[109],"capabilities;":[111],"according":[113],"accuracy":[116,138],"threshold":[117],"set":[118],"choose":[120],"appropriate":[122],"early":[123],"exit":[124],"point.":[125],"The":[126],"goal":[127],"is":[128],"minimize":[130],"average":[132,191],"under":[135],"constraint.":[139],"Therefore,":[140],"Adaptive":[144],"Dual-Pool":[145],"Dueling":[146],"Double":[147],"Deep":[148],"Q-Network":[149],"(ADP-D3QN)":[150],"algorithm,":[151],"which":[152],"enhances":[153],"exploration":[155],"strategy":[156],"experience":[158],"replay":[159],"mechanism":[160,168],"D3QN":[162],"implement":[164],"proposed":[166,187],"optimization":[167],"MEOCI.":[169],"We":[170],"conduct":[171],"comprehensive":[172],"performance":[173],"evaluations":[174],"using":[175],"four":[176],"models:":[178],"AlexNet,":[179],"VGG16,":[180],"ResNet50,":[181],"YOLOv10n.":[182],"Experimental":[183],"results":[184],"show":[185],"ADP-D3QN":[188],"algorithm":[189],"reduces":[190],"by":[194],"15.8%":[195],"AlexNet":[197],"8.7%":[199],"VGG16":[201],"compared":[202],"Edgent":[204],"algorithm.":[205]},"counts_by_year":[],"updated_date":"2026-04-09T08:11:56.329763","created_date":"2026-01-14T00:00:00"}