{"id":"https://openalex.org/W3110777925","doi":"https://doi.org/10.1109/tnet.2020.3042320","title":"CoEdge: Cooperative DNN Inference With Adaptive Workload Partitioning Over Heterogeneous Edge Devices","display_name":"CoEdge: Cooperative DNN Inference With Adaptive Workload Partitioning Over Heterogeneous Edge Devices","publication_year":2020,"publication_date":"2020-12-17","ids":{"openalex":"https://openalex.org/W3110777925","doi":"https://doi.org/10.1109/tnet.2020.3042320","mag":"3110777925"},"language":"en","primary_location":{"id":"doi:10.1109/tnet.2020.3042320","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tnet.2020.3042320","pdf_url":null,"source":{"id":"https://openalex.org/S62238642","display_name":"IEEE/ACM Transactions on Networking","issn_l":"1063-6692","issn":["1063-6692","1558-2566"],"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/ACM Transactions on Networking","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/A5055161955","display_name":"Liekang Zeng","orcid":"https://orcid.org/0000-0003-4800-8768"},"institutions":[{"id":"https://openalex.org/I157773358","display_name":"Sun Yat-sen University","ror":"https://ror.org/0064kty71","country_code":"CN","type":"education","lineage":["https://openalex.org/I157773358"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Liekang Zeng","raw_affiliation_strings":["School of Computer Science and Engineering, Sun Yat-sen University, Guangzhou, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Computer Science and Engineering, Sun Yat-sen University, Guangzhou, China","institution_ids":["https://openalex.org/I157773358"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100385692","display_name":"Xu Chen","orcid":"https://orcid.org/0000-0001-9943-6020"},"institutions":[{"id":"https://openalex.org/I157773358","display_name":"Sun Yat-sen University","ror":"https://ror.org/0064kty71","country_code":"CN","type":"education","lineage":["https://openalex.org/I157773358"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xu Chen","raw_affiliation_strings":["School of Computer Science and Engineering, Sun Yat-sen University, Guangzhou, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Computer Science and Engineering, Sun Yat-sen University, Guangzhou, China","institution_ids":["https://openalex.org/I157773358"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100760218","display_name":"Zhi Zhou","orcid":"https://orcid.org/0000-0002-0987-9344"},"institutions":[{"id":"https://openalex.org/I157773358","display_name":"Sun Yat-sen University","ror":"https://ror.org/0064kty71","country_code":"CN","type":"education","lineage":["https://openalex.org/I157773358"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhi Zhou","raw_affiliation_strings":["School of Computer Science and Engineering, Sun Yat-sen University, Guangzhou, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Computer Science and Engineering, Sun Yat-sen University, Guangzhou, China","institution_ids":["https://openalex.org/I157773358"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5072565301","display_name":"Lei Yang","orcid":"https://orcid.org/0000-0002-5176-003X"},"institutions":[{"id":"https://openalex.org/I134113660","display_name":"University of Nevada, Reno","ror":"https://ror.org/01keh0577","country_code":"US","type":"education","lineage":["https://openalex.org/I134113660"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Lei Yang","raw_affiliation_strings":["University of Nevada, Reno, NV, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Nevada, Reno, NV, USA","institution_ids":["https://openalex.org/I134113660"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5027033026","display_name":"Junshan Zhang","orcid":"https://orcid.org/0000-0002-3840-1753"},"institutions":[{"id":"https://openalex.org/I55732556","display_name":"Arizona State University","ror":"https://ror.org/03efmqc40","country_code":"US","type":"education","lineage":["https://openalex.org/I55732556"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Junshan Zhang","raw_affiliation_strings":["School of Electrical, Computer and Energy Engineering, Arizona State University, Tempe, AZ, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Electrical, Computer and Energy Engineering, Arizona State University, Tempe, AZ, USA","institution_ids":["https://openalex.org/I55732556"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":9.91,"has_fulltext":false,"cited_by_count":282,"citation_normalized_percentile":{"value":0.98884523,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":99,"max":100},"biblio":{"volume":"29","issue":"2","first_page":"595","last_page":"608"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10036","display_name":"Advanced Neural Network Applications","score":0.9997000098228455,"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":0.9997000098228455,"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/T10502","display_name":"Advanced Memory and Neural Computing","score":0.9994000196456909,"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/T10273","display_name":"IoT and Edge/Fog Computing","score":0.9990000128746033,"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/computer-science","display_name":"Computer science","score":0.8802381157875061},{"id":"https://openalex.org/keywords/edge-computing","display_name":"Edge computing","score":0.7294985055923462},{"id":"https://openalex.org/keywords/distributed-computing","display_name":"Distributed computing","score":0.6910656690597534},{"id":"https://openalex.org/keywords/edge-device","display_name":"Edge device","score":0.6811102032661438},{"id":"https://openalex.org/keywords/cloud-computing","display_name":"Cloud computing","score":0.6759263277053833},{"id":"https://openalex.org/keywords/inference","display_name":"Inference","score":0.608109176158905},{"id":"https://openalex.org/keywords/enhanced-data-rates-for-gsm-evolution","display_name":"Enhanced Data Rates for GSM Evolution","score":0.5766055583953857},{"id":"https://openalex.org/keywords/workload","display_name":"Workload","score":0.5763682723045349},{"id":"https://openalex.org/keywords/computation-offloading","display_name":"Computation offloading","score":0.5359874963760376},{"id":"https://openalex.org/keywords/computation","display_name":"Computation","score":0.44457700848579407},{"id":"https://openalex.org/keywords/latency","display_name":"Latency (audio)","score":0.436876118183136},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.297613263130188},{"id":"https://openalex.org/keywords/operating-system","display_name":"Operating system","score":0.09056085348129272},{"id":"https://openalex.org/keywords/telecommunications","display_name":"Telecommunications","score":0.08007201552391052}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8802381157875061},{"id":"https://openalex.org/C2778456923","wikidata":"https://www.wikidata.org/wiki/Q5337692","display_name":"Edge computing","level":3,"score":0.7294985055923462},{"id":"https://openalex.org/C120314980","wikidata":"https://www.wikidata.org/wiki/Q180634","display_name":"Distributed computing","level":1,"score":0.6910656690597534},{"id":"https://openalex.org/C138236772","wikidata":"https://www.wikidata.org/wiki/Q25098575","display_name":"Edge device","level":3,"score":0.6811102032661438},{"id":"https://openalex.org/C79974875","wikidata":"https://www.wikidata.org/wiki/Q483639","display_name":"Cloud computing","level":2,"score":0.6759263277053833},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.608109176158905},{"id":"https://openalex.org/C162307627","wikidata":"https://www.wikidata.org/wiki/Q204833","display_name":"Enhanced Data Rates for GSM Evolution","level":2,"score":0.5766055583953857},{"id":"https://openalex.org/C2778476105","wikidata":"https://www.wikidata.org/wiki/Q628539","display_name":"Workload","level":2,"score":0.5763682723045349},{"id":"https://openalex.org/C2781041963","wikidata":"https://www.wikidata.org/wiki/Q18348618","display_name":"Computation offloading","level":4,"score":0.5359874963760376},{"id":"https://openalex.org/C45374587","wikidata":"https://www.wikidata.org/wiki/Q12525525","display_name":"Computation","level":2,"score":0.44457700848579407},{"id":"https://openalex.org/C82876162","wikidata":"https://www.wikidata.org/wiki/Q17096504","display_name":"Latency (audio)","level":2,"score":0.436876118183136},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.297613263130188},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.09056085348129272},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.08007201552391052},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/tnet.2020.3042320","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tnet.2020.3042320","pdf_url":null,"source":{"id":"https://openalex.org/S62238642","display_name":"IEEE/ACM Transactions on Networking","issn_l":"1063-6692","issn":["1063-6692","1558-2566"],"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/ACM Transactions on Networking","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G3566375052","display_name":null,"funder_award_id":"IIS-1838024","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G3583843466","display_name":"\u9762\u5411\u79fb\u52a8\u5927\u6570\u636e\u5e94\u7528\u7684\u591a\u5c42\u6b21\u878d\u5408\u9ad8\u6548\u8fb9\u7f18\u8ba1\u7b97\u7814\u7a76","funder_award_id":"61972432","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G5121664804","display_name":null,"funder_award_id":"U1711265","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G5124095047","display_name":null,"funder_award_id":"EEC-1801727","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G645405385","display_name":null,"funder_award_id":"U20A20159","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G7465972502","display_name":null,"funder_award_id":"CNS-1950485","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G969433377","display_name":null,"funder_award_id":"2017GC010465","funder_id":"https://openalex.org/F4320334009","funder_display_name":"Guangdong Provincial Pearl River Talents Program"}],"funders":[{"id":"https://openalex.org/F4320306076","display_name":"National Science Foundation","ror":"https://ror.org/021nxhr62"},{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"},{"id":"https://openalex.org/F4320334009","display_name":"Guangdong Provincial Pearl River Talents Program","ror":null}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":61,"referenced_works":["https://openalex.org/W182605591","https://openalex.org/W1571707585","https://openalex.org/W1686810756","https://openalex.org/W2014939786","https://openalex.org/W2045271686","https://openalex.org/W2069211379","https://openalex.org/W2091432990","https://openalex.org/W2097117768","https://openalex.org/W2108598243","https://openalex.org/W2119144962","https://openalex.org/W2137693329","https://openalex.org/W2163605009","https://openalex.org/W2165473669","https://openalex.org/W2194775991","https://openalex.org/W2468875367","https://openalex.org/W2529556398","https://openalex.org/W2587594232","https://openalex.org/W2604319603","https://openalex.org/W2605258629","https://openalex.org/W2612193523","https://openalex.org/W2612445135","https://openalex.org/W2748902594","https://openalex.org/W2786652201","https://openalex.org/W2883863832","https://openalex.org/W2889744664","https://openalex.org/W2890928364","https://openalex.org/W2892952080","https://openalex.org/W2896180420","https://openalex.org/W2897070804","https://openalex.org/W2901502597","https://openalex.org/W2931092525","https://openalex.org/W2945558825","https://openalex.org/W2946719914","https://openalex.org/W2950865323","https://openalex.org/W2962883027","https://openalex.org/W2963911037","https://openalex.org/W2964299589","https://openalex.org/W2979679572","https://openalex.org/W2980856918","https://openalex.org/W2983440318","https://openalex.org/W3005276590","https://openalex.org/W3017807730","https://openalex.org/W3026206397","https://openalex.org/W3029325105","https://openalex.org/W3031262103","https://openalex.org/W3035208698","https://openalex.org/W3047565185","https://openalex.org/W3048486781","https://openalex.org/W3105608950","https://openalex.org/W3140772298","https://openalex.org/W3183780328","https://openalex.org/W4236099117","https://openalex.org/W4289305285","https://openalex.org/W4297775537","https://openalex.org/W4300462944","https://openalex.org/W6607432528","https://openalex.org/W6637373629","https://openalex.org/W6638444622","https://openalex.org/W6677580257","https://openalex.org/W6684191040","https://openalex.org/W6737664043"],"related_works":["https://openalex.org/W2894114519","https://openalex.org/W4282941432","https://openalex.org/W4322761281","https://openalex.org/W2920581164","https://openalex.org/W4309428690","https://openalex.org/W4238233472","https://openalex.org/W3200145713","https://openalex.org/W4313463218","https://openalex.org/W4312996489","https://openalex.org/W3111395152"],"abstract_inverted_index":{"Recent":[0],"advances":[1],"in":[2,156],"artificial":[3],"intelligence":[4],"have":[5,37],"driven":[6],"increasing":[7],"intelligent":[8],"applications":[9],"at":[10,50,125],"the":[11,44,51,56,61,68,75,83,126,131],"network":[12,141],"edge,":[13],"such":[14],"as":[15],"smart":[16,18,21],"home,":[17],"factory,":[19],"and":[20,63,67,122,128,140],"city.":[22],"To":[23],"deploy":[24],"computationally":[25],"intensive":[26],"Deep":[27],"Neural":[28],"Networks":[29],"(DNNs)":[30],"on":[31,39,146],"resource-constrained":[32],"edge":[33,81,116,127],"devices,":[34],"traditional":[35],"approaches":[36,58,71,155],"relied":[38],"either":[40],"offloading":[41],"workload":[42,134],"to":[43,136,165],"remote":[45],"cloud":[46],"or":[47],"optimizing":[48],"computation":[49,121],"end":[52],"device":[53],"locally.":[54],"However,":[55],"cloud-assisted":[57],"suffer":[59],"from":[60],"unreliable":[62],"delay-significant":[64],"wide-area":[65],"network,":[66],"local":[69],"computing":[70,77,107,138],"are":[72],"limited":[73],"by":[74],"constrained":[76],"capability.":[78],"Towards":[79],"high-performance":[80],"intelligence,":[82],"cooperative":[84,111],"execution":[85],"mechanism":[86],"offers":[87],"a":[88,104,147],"new":[89],"paradigm,":[90],"which":[91],"has":[92],"attracted":[93],"growing":[94],"research":[95],"interest":[96],"recently.":[97],"In":[98],"this":[99],"paper,":[100],"we":[101],"propose":[102],"CoEdge,":[103],"distributed":[105],"DNN":[106,112,132],"system":[108],"that":[109,151],"orchestrates":[110],"inference":[113,133,161],"over":[114],"heterogeneous":[115],"devices.":[117],"CoEdge":[118,152],"utilizes":[119],"available":[120],"communication":[123],"resources":[124],"dynamically":[129],"partitions":[130],"adaptive":[135],"devices'":[137],"capabilities":[139],"conditions.":[142],"Experimental":[143],"evaluations":[144],"based":[145],"realistic":[148],"prototype":[149],"show":[150],"outperforms":[153],"status-quo":[154],"saving":[157],"energy":[158,169],"with":[159],"close":[160],"latency,":[162],"achieving":[163],"up":[164],"25.5%":[166],"~":[167],"66.9%":[168],"reduction":[170],"for":[171],"four":[172],"widely-adopted":[173],"CNN":[174],"models.":[175]},"counts_by_year":[{"year":2026,"cited_by_count":27},{"year":2025,"cited_by_count":81},{"year":2024,"cited_by_count":71},{"year":2023,"cited_by_count":56},{"year":2022,"cited_by_count":38},{"year":2021,"cited_by_count":9}],"updated_date":"2026-07-17T09:13:05.818461","created_date":"2025-10-10T00:00:00"}