{"id":"https://openalex.org/W4312191382","doi":"https://doi.org/10.1109/tpds.2022.3222509","title":"Accelerating Deep Learning Inference via Model Parallelism and Partial Computation Offloading","display_name":"Accelerating Deep Learning Inference via Model Parallelism and Partial Computation Offloading","publication_year":2022,"publication_date":"2022-11-16","ids":{"openalex":"https://openalex.org/W4312191382","doi":"https://doi.org/10.1109/tpds.2022.3222509"},"language":"en","primary_location":{"id":"doi:10.1109/tpds.2022.3222509","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tpds.2022.3222509","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/A5049807322","display_name":"Huan Zhou","orcid":"https://orcid.org/0000-0003-4007-7224"},"institutions":[{"id":"https://openalex.org/I161350542","display_name":"China Three Gorges University","ror":"https://ror.org/0419nfc77","country_code":"CN","type":"education","lineage":["https://openalex.org/I161350542"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Huan Zhou","raw_affiliation_strings":["Hubei Key Laboratory of Intelligent Vision Based Monitoring for Hydroelectric Engineering, College of Computer and Information Technology, China Three Gorges University, Yichang, Hubei, China"],"affiliations":[{"raw_affiliation_string":"Hubei Key Laboratory of Intelligent Vision Based Monitoring for Hydroelectric Engineering, College of Computer and Information Technology, China Three Gorges University, Yichang, Hubei, China","institution_ids":["https://openalex.org/I161350542"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100621995","display_name":"Mingze Li","orcid":"https://orcid.org/0000-0001-7721-0768"},"institutions":[{"id":"https://openalex.org/I161350542","display_name":"China Three Gorges University","ror":"https://ror.org/0419nfc77","country_code":"CN","type":"education","lineage":["https://openalex.org/I161350542"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Mingze Li","raw_affiliation_strings":["Hubei Key Laboratory of Intelligent Vision Based Monitoring for Hydroelectric Engineering, College of Computer and Information Technology, China Three Gorges University, Yichang, Hubei, China"],"affiliations":[{"raw_affiliation_string":"Hubei Key Laboratory of Intelligent Vision Based Monitoring for Hydroelectric Engineering, College of Computer and Information Technology, China Three Gorges University, Yichang, Hubei, China","institution_ids":["https://openalex.org/I161350542"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100387188","display_name":"Ning Wang","orcid":"https://orcid.org/0000-0002-9467-9215"},"institutions":[{"id":"https://openalex.org/I44265643","display_name":"Rowan University","ror":"https://ror.org/049v69k10","country_code":"US","type":"education","lineage":["https://openalex.org/I44265643"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Ning Wang","raw_affiliation_strings":["Department of Computer Science, Rowan University, Glassboro, NJ, USA"],"affiliations":[{"raw_affiliation_string":"Department of Computer Science, Rowan University, Glassboro, NJ, USA","institution_ids":["https://openalex.org/I44265643"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100770003","display_name":"Geyong Min","orcid":"https://orcid.org/0000-0003-1395-7314"},"institutions":[{"id":"https://openalex.org/I23923803","display_name":"University of Exeter","ror":"https://ror.org/03yghzc09","country_code":"GB","type":"education","lineage":["https://openalex.org/I23923803"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Geyong Min","raw_affiliation_strings":["Department of Computer Science, University of Exeter, Exeter, U.K"],"affiliations":[{"raw_affiliation_string":"Department of Computer Science, University of Exeter, Exeter, U.K","institution_ids":["https://openalex.org/I23923803"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100600528","display_name":"Jie Wu","orcid":"https://orcid.org/0000-0002-3472-1717"},"institutions":[{"id":"https://openalex.org/I84392919","display_name":"Temple University","ror":"https://ror.org/00kx1jb78","country_code":"US","type":"education","lineage":["https://openalex.org/I84392919"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Jie Wu","raw_affiliation_strings":["Center for Networked Computing, Temple University, Philadelphia, PA, USA"],"affiliations":[{"raw_affiliation_string":"Center for Networked Computing, Temple University, Philadelphia, PA, USA","institution_ids":["https://openalex.org/I84392919"]}]}],"institutions":[],"countries_distinct_count":3,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5049807322"],"corresponding_institution_ids":["https://openalex.org/I161350542"],"apc_list":null,"apc_paid":null,"fwci":6.2271,"has_fulltext":false,"cited_by_count":63,"citation_normalized_percentile":{"value":0.97551885,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":98,"max":100},"biblio":{"volume":"34","issue":"2","first_page":"475","last_page":"488"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10036","display_name":"Advanced Neural Network Applications","score":0.9995999932289124,"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":0.9995999932289124,"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/T10273","display_name":"IoT and Edge/Fog Computing","score":0.9994999766349792,"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/T12079","display_name":"IoT Networks and Protocols","score":0.9937000274658203,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8763387203216553},{"id":"https://openalex.org/keywords/computation-offloading","display_name":"Computation offloading","score":0.7604500651359558},{"id":"https://openalex.org/keywords/computation","display_name":"Computation","score":0.6058136224746704},{"id":"https://openalex.org/keywords/scheduling","display_name":"Scheduling (production processes)","score":0.5788508653640747},{"id":"https://openalex.org/keywords/inference","display_name":"Inference","score":0.4502134919166565},{"id":"https://openalex.org/keywords/mobile-device","display_name":"Mobile device","score":0.4410308599472046},{"id":"https://openalex.org/keywords/overhead","display_name":"Overhead (engineering)","score":0.4355732500553131},{"id":"https://openalex.org/keywords/deep-learning","display_name":"Deep learning","score":0.42719414830207825},{"id":"https://openalex.org/keywords/distributed-computing","display_name":"Distributed computing","score":0.41068312525749207},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.36116716265678406},{"id":"https://openalex.org/keywords/edge-computing","display_name":"Edge computing","score":0.32811155915260315},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.154455304145813},{"id":"https://openalex.org/keywords/enhanced-data-rates-for-gsm-evolution","display_name":"Enhanced Data Rates for GSM Evolution","score":0.1472223401069641},{"id":"https://openalex.org/keywords/mathematical-optimization","display_name":"Mathematical optimization","score":0.12982234358787537}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8763387203216553},{"id":"https://openalex.org/C2781041963","wikidata":"https://www.wikidata.org/wiki/Q18348618","display_name":"Computation offloading","level":4,"score":0.7604500651359558},{"id":"https://openalex.org/C45374587","wikidata":"https://www.wikidata.org/wiki/Q12525525","display_name":"Computation","level":2,"score":0.6058136224746704},{"id":"https://openalex.org/C206729178","wikidata":"https://www.wikidata.org/wiki/Q2271896","display_name":"Scheduling (production processes)","level":2,"score":0.5788508653640747},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.4502134919166565},{"id":"https://openalex.org/C186967261","wikidata":"https://www.wikidata.org/wiki/Q5082128","display_name":"Mobile device","level":2,"score":0.4410308599472046},{"id":"https://openalex.org/C2779960059","wikidata":"https://www.wikidata.org/wiki/Q7113681","display_name":"Overhead (engineering)","level":2,"score":0.4355732500553131},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.42719414830207825},{"id":"https://openalex.org/C120314980","wikidata":"https://www.wikidata.org/wiki/Q180634","display_name":"Distributed computing","level":1,"score":0.41068312525749207},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.36116716265678406},{"id":"https://openalex.org/C2778456923","wikidata":"https://www.wikidata.org/wiki/Q5337692","display_name":"Edge computing","level":3,"score":0.32811155915260315},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.154455304145813},{"id":"https://openalex.org/C162307627","wikidata":"https://www.wikidata.org/wiki/Q204833","display_name":"Enhanced Data Rates for GSM Evolution","level":2,"score":0.1472223401069641},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.12982234358787537},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/tpds.2022.3222509","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tpds.2022.3222509","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":[],"awards":[{"id":"https://openalex.org/G3016592842","display_name":null,"funder_award_id":"62172255","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G8451013447","display_name":null,"funder_award_id":"61872221","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":52,"referenced_works":["https://openalex.org/W2029016069","https://openalex.org/W2082081352","https://openalex.org/W2131613989","https://openalex.org/W2133564696","https://openalex.org/W2143612262","https://openalex.org/W2279098554","https://openalex.org/W2344423009","https://openalex.org/W2403440562","https://openalex.org/W2468875367","https://openalex.org/W2567349724","https://openalex.org/W2605258629","https://openalex.org/W2751904527","https://openalex.org/W2790167166","https://openalex.org/W2794026873","https://openalex.org/W2803421549","https://openalex.org/W2888816167","https://openalex.org/W2920031528","https://openalex.org/W2971229345","https://openalex.org/W2971714613","https://openalex.org/W2980856918","https://openalex.org/W2981618170","https://openalex.org/W2996568029","https://openalex.org/W3013536937","https://openalex.org/W3037830434","https://openalex.org/W3038089015","https://openalex.org/W3047392327","https://openalex.org/W3092319711","https://openalex.org/W3097692969","https://openalex.org/W3103591951","https://openalex.org/W3110777925","https://openalex.org/W3110962653","https://openalex.org/W3130616654","https://openalex.org/W3135028423","https://openalex.org/W3157114665","https://openalex.org/W3167969180","https://openalex.org/W3174997142","https://openalex.org/W3187219391","https://openalex.org/W3197003950","https://openalex.org/W3197857810","https://openalex.org/W3202549149","https://openalex.org/W3212518961","https://openalex.org/W4213413389","https://openalex.org/W4226018382","https://openalex.org/W4249932213","https://openalex.org/W4255951808","https://openalex.org/W4285820401","https://openalex.org/W4297775537","https://openalex.org/W4323897035","https://openalex.org/W6679434410","https://openalex.org/W6684191040","https://openalex.org/W6695314431","https://openalex.org/W6737664043"],"related_works":["https://openalex.org/W2751308120","https://openalex.org/W2954039338","https://openalex.org/W4399169206","https://openalex.org/W2966556967","https://openalex.org/W2896883851","https://openalex.org/W4380356430","https://openalex.org/W3034137700","https://openalex.org/W2894114519","https://openalex.org/W4282941432","https://openalex.org/W3200145713"],"abstract_inverted_index":{"With":[0],"the":[1,8,34,125,148,154,181,202,205,216,221,233,244,249,255],"rapid":[2],"development":[3],"of":[4,11,37,80,204,228,257],"Internet-of-Things":[5],"(IoT)":[6],"and":[7,85,121,153,157,179,187,195,239],"explosive":[9],"advance":[10],"deep":[12,21],"learning,":[13],"there":[14,131],"is":[15,49,59,101,132,240],"an":[16,226],"urgent":[17],"need":[18],"to":[19,61,95,109,115,191,232,243],"enable":[20],"learning":[22],"inference":[23,223],"on":[24],"IoT":[25,38],"devices":[26,39],"in":[27,40,67,113,160,208],"Mobile":[28],"Edge":[29],"Computing":[30],"(MEC).":[31],"To":[32],"address":[33],"computation":[35,47,57,83,118,127,136,162],"limitation":[36],"processing":[41],"complex":[42],"Deep":[43],"Neural":[44],"Networks":[45],"(DNNs),":[46],"offloading":[48,58,119,128,137,158,189],"proposed":[50,206,217],"as":[51,139,141],"a":[52,87,103,133,168],"promising":[53],"approach.":[54],"Recently,":[55],"partial":[56,117,161],"developed":[60],"dynamically":[62],"adjust":[63],"task":[64],"assignment":[65],"strategy":[66,190],"different":[68],"channel":[69],"conditions":[70],"for":[71],"better":[72,126],"performance.":[73],"In":[74,164],"this":[75],"paper,":[76],"we":[77,146,166,200],"take":[78],"advantage":[79],"intrinsic":[81],"DNN":[82,91,104,150,222],"characteristics":[84],"propose":[86,167],"novel":[88],"Fused-Layer-based":[89],"(FL-based)":[90],"model":[92,142,151],"parallelism":[93,143,152],"method":[94,207,218],"accelerate":[96],"inference.":[97],"The":[98,212],"key":[99],"idea":[100],"that":[102,215],"layer":[105],"can":[106,219],"be":[107],"converted":[108],"several":[110],"smaller":[111],"layers":[112],"order":[114],"increase":[116],"flexibility,":[120],"thus":[122],"further":[123],"create":[124],"solution.":[129],"However,":[130],"trade-off":[134],"between":[135],"flexibility":[138],"well":[140],"overhead.":[144],"Then,":[145],"investigate":[147],"optimal":[149,245],"corresponding":[155],"scheduling":[156,185],"strategies":[159],"offloading.":[163],"particular,":[165],"Particle":[169],"Swarm":[170],"Optimization":[171],"with":[172,254],"Minimizing":[173],"Waiting":[174],"(PSOMW)":[175],"method,":[176],"which":[177],"explores":[178],"updates":[180],"FL":[182,236],"strategy,":[183,186],"path":[184,188],"reduce":[192,220],"time":[193,224],"complexity":[194],"avoid":[196],"invalid":[197],"solutions.":[198],"Finally,":[199],"validate":[201],"effectiveness":[203],"commonly":[209],"used":[210],"DNNs.":[211],"results":[213],"show":[214],"by":[225,248],"average":[227],"12.75":[229],"times":[230],"compared":[231],"legacy":[234],"No":[235],"(NFL)":[237],"algorithm,":[238],"very":[241],"close":[242],"solution":[246],"achieved":[247],"Brute":[250],"Force":[251],"(BF)":[252],"algorithm":[253],"difference":[256],"less":[258],"than":[259],"0.04%.":[260]},"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2025,"cited_by_count":20},{"year":2024,"cited_by_count":29},{"year":2023,"cited_by_count":12}],"updated_date":"2026-04-09T08:11:56.329763","created_date":"2025-10-10T00:00:00"}