{"id":"https://openalex.org/W4390968835","doi":"https://doi.org/10.1109/tmc.2024.3355764","title":"SwapNet: Efficient Swapping for DNN Inference on Edge AI Devices Beyond the Memory Budget","display_name":"SwapNet: Efficient Swapping for DNN Inference on Edge AI Devices Beyond the Memory Budget","publication_year":2024,"publication_date":"2024-01-18","ids":{"openalex":"https://openalex.org/W4390968835","doi":"https://doi.org/10.1109/tmc.2024.3355764"},"language":"en","primary_location":{"id":"doi:10.1109/tmc.2024.3355764","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tmc.2024.3355764","pdf_url":null,"source":{"id":"https://openalex.org/S69141925","display_name":"IEEE Transactions on Mobile Computing","issn_l":"1536-1233","issn":["1536-1233","1558-0660","2161-9875"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320439","host_organization_name":"IEEE Computer Society","host_organization_lineage":["https://openalex.org/P4310320439","https://openalex.org/P4310319808"],"host_organization_lineage_names":["IEEE Computer Society","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 Mobile Computing","raw_type":"journal-article"},"type":"article","indexed_in":["arxiv","crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2401.16757","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5102990096","display_name":"Kun Wang","orcid":"https://orcid.org/0000-0002-0149-9857"},"institutions":[{"id":"https://openalex.org/I168719708","display_name":"City University of Hong Kong","ror":"https://ror.org/03q8dnn23","country_code":"HK","type":"education","lineage":["https://openalex.org/I168719708"]}],"countries":["HK"],"is_corresponding":true,"raw_author_name":"Kun Wang","raw_affiliation_strings":["Department of Computer Science, City University of Hong Kong, Hong Kong, China"],"raw_orcid":"https://orcid.org/0000-0002-0149-9857","affiliations":[{"raw_affiliation_string":"Department of Computer Science, City University of Hong Kong, Hong Kong, China","institution_ids":["https://openalex.org/I168719708"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5103143435","display_name":"Jiani Cao","orcid":"https://orcid.org/0000-0002-8211-3564"},"institutions":[{"id":"https://openalex.org/I168719708","display_name":"City University of Hong Kong","ror":"https://ror.org/03q8dnn23","country_code":"HK","type":"education","lineage":["https://openalex.org/I168719708"]}],"countries":["HK"],"is_corresponding":false,"raw_author_name":"Jiani Cao","raw_affiliation_strings":["Department of Computer Science, City University of Hong Kong, Hong Kong, China"],"raw_orcid":"https://orcid.org/0000-0002-8211-3564","affiliations":[{"raw_affiliation_string":"Department of Computer Science, City University of Hong Kong, Hong Kong, China","institution_ids":["https://openalex.org/I168719708"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5011140675","display_name":"Zimu Zhou","orcid":"https://orcid.org/0000-0002-5457-6967"},"institutions":[{"id":"https://openalex.org/I168719708","display_name":"City University of Hong Kong","ror":"https://ror.org/03q8dnn23","country_code":"HK","type":"education","lineage":["https://openalex.org/I168719708"]}],"countries":["HK"],"is_corresponding":false,"raw_author_name":"Zimu Zhou","raw_affiliation_strings":["School of Data Science, City University of Hong Kong, Hong Kong, China"],"raw_orcid":"https://orcid.org/0000-0002-5457-6967","affiliations":[{"raw_affiliation_string":"School of Data Science, City University of Hong Kong, Hong Kong, China","institution_ids":["https://openalex.org/I168719708"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100419083","display_name":"Zhenjiang Li","orcid":"https://orcid.org/0000-0002-3296-3392"},"institutions":[{"id":"https://openalex.org/I168719708","display_name":"City University of Hong Kong","ror":"https://ror.org/03q8dnn23","country_code":"HK","type":"education","lineage":["https://openalex.org/I168719708"]}],"countries":["HK"],"is_corresponding":false,"raw_author_name":"Zhenjiang Li","raw_affiliation_strings":["Department of Computer Science, City University of Hong Kong, Hong Kong, China"],"raw_orcid":"https://orcid.org/0000-0002-3296-3392","affiliations":[{"raw_affiliation_string":"Department of Computer Science, City University of Hong Kong, Hong Kong, China","institution_ids":["https://openalex.org/I168719708"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5102990096"],"corresponding_institution_ids":["https://openalex.org/I168719708"],"apc_list":null,"apc_paid":null,"fwci":3.8961,"has_fulltext":true,"cited_by_count":17,"citation_normalized_percentile":{"value":0.94490657,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":96,"max":99},"biblio":{"volume":"23","issue":"9","first_page":"8935","last_page":"8950"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10036","display_name":"Advanced Neural Network Applications","score":0.9998999834060669,"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":0.9998999834060669,"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":0.9958000183105469,"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":0.9941999912261963,"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":0.6901583075523376},{"id":"https://openalex.org/keywords/inference","display_name":"Inference","score":0.6227808594703674},{"id":"https://openalex.org/keywords/edge-device","display_name":"Edge device","score":0.614216148853302},{"id":"https://openalex.org/keywords/memory-footprint","display_name":"Memory footprint","score":0.5421702265739441},{"id":"https://openalex.org/keywords/enhanced-data-rates-for-gsm-evolution","display_name":"Enhanced Data Rates for GSM Evolution","score":0.5308759212493896},{"id":"https://openalex.org/keywords/latency","display_name":"Latency (audio)","score":0.5068379044532776},{"id":"https://openalex.org/keywords/deep-neural-networks","display_name":"Deep neural networks","score":0.47771477699279785},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.43974971771240234},{"id":"https://openalex.org/keywords/edge-computing","display_name":"Edge computing","score":0.41429704427719116},{"id":"https://openalex.org/keywords/cloud-computing","display_name":"Cloud computing","score":0.3967408537864685},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.37245750427246094},{"id":"https://openalex.org/keywords/theoretical-computer-science","display_name":"Theoretical computer science","score":0.3670307397842407},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.26426026225090027},{"id":"https://openalex.org/keywords/operating-system","display_name":"Operating system","score":0.17398691177368164}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6901583075523376},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.6227808594703674},{"id":"https://openalex.org/C138236772","wikidata":"https://www.wikidata.org/wiki/Q25098575","display_name":"Edge device","level":3,"score":0.614216148853302},{"id":"https://openalex.org/C74912251","wikidata":"https://www.wikidata.org/wiki/Q6815727","display_name":"Memory footprint","level":2,"score":0.5421702265739441},{"id":"https://openalex.org/C162307627","wikidata":"https://www.wikidata.org/wiki/Q204833","display_name":"Enhanced Data Rates for GSM Evolution","level":2,"score":0.5308759212493896},{"id":"https://openalex.org/C82876162","wikidata":"https://www.wikidata.org/wiki/Q17096504","display_name":"Latency (audio)","level":2,"score":0.5068379044532776},{"id":"https://openalex.org/C2984842247","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep neural networks","level":3,"score":0.47771477699279785},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.43974971771240234},{"id":"https://openalex.org/C2778456923","wikidata":"https://www.wikidata.org/wiki/Q5337692","display_name":"Edge computing","level":3,"score":0.41429704427719116},{"id":"https://openalex.org/C79974875","wikidata":"https://www.wikidata.org/wiki/Q483639","display_name":"Cloud computing","level":2,"score":0.3967408537864685},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.37245750427246094},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.3670307397842407},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.26426026225090027},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.17398691177368164},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/tmc.2024.3355764","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tmc.2024.3355764","pdf_url":null,"source":{"id":"https://openalex.org/S69141925","display_name":"IEEE Transactions on Mobile Computing","issn_l":"1536-1233","issn":["1536-1233","1558-0660","2161-9875"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320439","host_organization_name":"IEEE Computer Society","host_organization_lineage":["https://openalex.org/P4310320439","https://openalex.org/P4310319808"],"host_organization_lineage_names":["IEEE Computer Society","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 Mobile Computing","raw_type":"journal-article"},{"id":"pmh:oai:arXiv.org:2401.16757","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2401.16757","pdf_url":"https://arxiv.org/pdf/2401.16757","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2401.16757","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2401.16757","pdf_url":"https://arxiv.org/pdf/2401.16757","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G4569554029","display_name":null,"funder_award_id":"9610633","funder_id":"https://openalex.org/F4320309893","funder_display_name":"City University of Hong Kong"}],"funders":[{"id":"https://openalex.org/F4320309893","display_name":"City University of Hong Kong","ror":"https://ror.org/03q8dnn23"},{"id":"https://openalex.org/F4320319065","display_name":"Aromatic Plant Research Center","ror":"https://ror.org/05eebgw43"}],"has_content":{"grobid_xml":false,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4390968835.pdf"},"referenced_works_count":41,"referenced_works":["https://openalex.org/W1686810756","https://openalex.org/W1903029394","https://openalex.org/W2146881125","https://openalex.org/W2194775991","https://openalex.org/W2604319603","https://openalex.org/W2860338957","https://openalex.org/W2907882680","https://openalex.org/W2919064223","https://openalex.org/W2942806183","https://openalex.org/W2946547492","https://openalex.org/W2964203871","https://openalex.org/W2979332426","https://openalex.org/W2979832172","https://openalex.org/W2980856918","https://openalex.org/W3012479151","https://openalex.org/W3080950018","https://openalex.org/W3091953123","https://openalex.org/W3109233295","https://openalex.org/W3123875677","https://openalex.org/W3128736549","https://openalex.org/W3144271226","https://openalex.org/W3200236657","https://openalex.org/W3209827161","https://openalex.org/W3211771663","https://openalex.org/W3212621679","https://openalex.org/W4236099117","https://openalex.org/W4282970339","https://openalex.org/W4282974189","https://openalex.org/W4283020086","https://openalex.org/W4293584584","https://openalex.org/W4306178486","https://openalex.org/W4309130566","https://openalex.org/W4312191382","https://openalex.org/W4320060064","https://openalex.org/W4385245566","https://openalex.org/W6637373629","https://openalex.org/W6677580257","https://openalex.org/W6713134421","https://openalex.org/W6748163181","https://openalex.org/W6750227808","https://openalex.org/W6790499563"],"related_works":["https://openalex.org/W4322761281","https://openalex.org/W4238233472","https://openalex.org/W4313526662","https://openalex.org/W3111395152","https://openalex.org/W4312996489","https://openalex.org/W3106131444","https://openalex.org/W3216099748","https://openalex.org/W4205963435","https://openalex.org/W4313463379","https://openalex.org/W4295943704"],"abstract_inverted_index":{"Executing":[0],"deep":[1,145],"neural":[2],"networks":[3],"(DNNs)":[4],"on":[5,92,170,229],"edge":[6,22,93,111,127,154,230],"artificial":[7],"intelligence":[8],"(AI)":[9],"devices":[10,24,95,232],"enables":[11],"various":[12],"autonomous":[13],"mobile":[14],"computing":[15],"applications.":[16,35],"However,":[17],"the":[18,26,46,53,101,106,133,144,160,183,187,210,234],"memory":[19,47,87,103,135,191,208],"budget":[20],"of":[21,30,49,55,153,162,215],"AI":[23,94,112,128,155,231],"restricts":[25],"number":[27],"and":[28,70,74,150,220],"complexity":[29],"DNNs":[31,81,194],"allowed":[32],"in":[33,73,76,105,175,233],"such":[34,38,78],"Existing":[36],"solutions,":[37],"as":[39,186],"model":[40,57],"compression":[41],"or":[42,59],"cloud":[43],"offloading,":[44],"reduce":[45],"footprint":[48],"DNN":[50,67,107,122,172],"inference":[51,173],"at":[52],"cost":[54],"decreased":[56],"accuracy":[58],"autonomy.":[60],"To":[61,114],"avoid":[62],"these":[63],"drawbacks,":[64],"we":[65,117],"divide":[66],"into":[68],"blocks":[69],"swap":[71],"them":[72],"out":[75],"order,":[77],"that":[79,179],"large":[80,225],"can":[82],"execute":[83],"within":[84],"a":[85,165],"small":[86],"budget.":[88,212],"Nevertheless,":[89],"naive":[90],"swapping":[91,124,139],"induces":[96],"significant":[97],"delays":[98],"due":[99],"to":[100],"redundant":[102],"operations":[104,136],"development":[108],"ecosystem":[109],"for":[110,126,223],"devices.":[113,129,156],"this":[115],"end,":[116],"develop":[118],"SwapNet,":[119],"an":[120],"efficient":[121],"block":[123,138],"middleware":[125],"We":[130,157],"systematically":[131],"eliminate":[132],"unnecessary":[134],"during":[137],"while":[140],"retaining":[141],"compatible":[142],"with":[143,189],"learning":[146],"frameworks,":[147],"GPU":[148],"backends,":[149],"hardware":[151],"architectures":[152],"further":[158],"showcase":[159],"utility":[161],"SwapNet":[163,180,216],"via":[164],"multi-DNN":[166],"scheduling":[167],"scheme.":[168],"Evaluations":[169],"eleven":[171],"tasks":[174],"three":[176],"applications":[177],"demonstrate":[178],"achieves":[181],"almost":[182],"same":[184],"latency":[185],"case":[188],"sufficient":[190],"even":[192],"when":[193],"demand":[195],"<inline-formula":[196,200,204],"xmlns:mml=\"http://www.w3.org/1998/Math/MathML\"":[197,201,205],"xmlns:xlink=\"http://www.w3.org/1999/xlink\"><tex-math":[198,202,206],"notation=\"LaTeX\">$2.32\\times$</tex-math></inline-formula>":[199],"notation=\"LaTeX\">$\\sim$</tex-math></inline-formula>":[203],"notation=\"LaTeX\">$5.81\\times$</tex-math></inline-formula>":[207],"beyond":[209],"available":[211],"The":[213],"design":[214],"also":[217],"provides":[218],"novel":[219],"feasible":[221],"insights":[222],"deploying":[224],"language":[226],"models":[227],"(LLMs)":[228],"future.":[235]},"counts_by_year":[{"year":2026,"cited_by_count":3},{"year":2025,"cited_by_count":11},{"year":2024,"cited_by_count":3}],"updated_date":"2026-05-09T13:55:54.758798","created_date":"2024-01-19T00:00:00"}