{"id":"https://openalex.org/W4401507988","doi":"https://doi.org/10.1109/infocom52122.2024.10621120","title":"Minimizing Latency for Multi-DNN Inference on Resource-Limited CPU-Only Edge Devices","display_name":"Minimizing Latency for Multi-DNN Inference on Resource-Limited CPU-Only Edge Devices","publication_year":2024,"publication_date":"2024-05-20","ids":{"openalex":"https://openalex.org/W4401507988","doi":"https://doi.org/10.1109/infocom52122.2024.10621120"},"language":"en","primary_location":{"id":"doi:10.1109/infocom52122.2024.10621120","is_oa":false,"landing_page_url":"https://doi.org/10.1109/infocom52122.2024.10621120","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE INFOCOM 2024 - 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":"https://openalex.org/A5115596151","display_name":"Tao Wang","orcid":"https://orcid.org/0000-0003-4140-8734"},"institutions":[{"id":"https://openalex.org/I162868743","display_name":"Tianjin University","ror":"https://ror.org/012tb2g32","country_code":"CN","type":"education","lineage":["https://openalex.org/I162868743"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Tao Wang","raw_affiliation_strings":["Tianjin University,College of Intelligence and Computing,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tianjin University,College of Intelligence and Computing,China","institution_ids":["https://openalex.org/I162868743"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5042475680","display_name":"Tuo Shi","orcid":"https://orcid.org/0000-0003-3685-2099"},"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":"Tuo Shi","raw_affiliation_strings":["City University of Hong Kong,Department of Computer Science,Hong Kong"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"City University of Hong Kong,Department of Computer Science,Hong Kong","institution_ids":["https://openalex.org/I168719708"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5011357293","display_name":"Keqiu Li","orcid":"https://orcid.org/0000-0003-1758-3030"},"institutions":[{"id":"https://openalex.org/I162868743","display_name":"Tianjin University","ror":"https://ror.org/012tb2g32","country_code":"CN","type":"education","lineage":["https://openalex.org/I162868743"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xiulong Liu","raw_affiliation_strings":["Tianjin University,College of Intelligence and Computing,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tianjin University,College of Intelligence and Computing,China","institution_ids":["https://openalex.org/I162868743"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100356291","display_name":"Jianping Wang","orcid":"https://orcid.org/0000-0002-9318-1482"},"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":"Jianping Wang","raw_affiliation_strings":["City University of Hong Kong,Department of Computer Science,Hong Kong"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"City University of Hong Kong,Department of Computer Science,Hong Kong","institution_ids":["https://openalex.org/I168719708"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100395493","display_name":"Bin Liu","orcid":"https://orcid.org/0000-0002-3977-8800"},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Bin Liu","raw_affiliation_strings":["Tsinghua University,Department of Computer Science and Technology,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tsinghua University,Department of Computer Science and Technology,China","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5046635673","display_name":"Yingshu Li","orcid":"https://orcid.org/0000-0002-1906-7112"},"institutions":[{"id":"https://openalex.org/I181565077","display_name":"Georgia State University","ror":"https://ror.org/03qt6ba18","country_code":"US","type":"education","lineage":["https://openalex.org/I181565077"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Yingshu Li","raw_affiliation_strings":["Georgia State University,Department of Computer Science,USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Georgia State University,Department of Computer Science,USA","institution_ids":["https://openalex.org/I181565077"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5056036421","display_name":"Yechao She","orcid":"https://orcid.org/0000-0002-6951-2392"},"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":"Yechao She","raw_affiliation_strings":["City University of Hong Kong,Department of Computer Science,Hong Kong"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"City University of Hong Kong,Department of Computer Science,Hong Kong","institution_ids":["https://openalex.org/I168719708"]}]}],"institutions":[],"countries_distinct_count":3,"institutions_distinct_count":7,"corresponding_author_ids":["https://openalex.org/A5115596151"],"corresponding_institution_ids":["https://openalex.org/I162868743"],"apc_list":null,"apc_paid":null,"fwci":1.5582,"has_fulltext":false,"cited_by_count":7,"citation_normalized_percentile":{"value":0.83024785,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"2239","last_page":"2248"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12702","display_name":"Brain Tumor Detection and Classification","score":0.9962999820709229,"subfield":{"id":"https://openalex.org/subfields/2808","display_name":"Neurology"},"field":{"id":"https://openalex.org/fields/28","display_name":"Neuroscience"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}},"topics":[{"id":"https://openalex.org/T12702","display_name":"Brain Tumor Detection and Classification","score":0.9962999820709229,"subfield":{"id":"https://openalex.org/subfields/2808","display_name":"Neurology"},"field":{"id":"https://openalex.org/fields/28","display_name":"Neuroscience"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}},{"id":"https://openalex.org/T10036","display_name":"Advanced Neural Network Applications","score":0.9663000106811523,"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":0.9585999846458435,"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":0.7945618629455566},{"id":"https://openalex.org/keywords/latency","display_name":"Latency (audio)","score":0.6999549269676208},{"id":"https://openalex.org/keywords/inference","display_name":"Inference","score":0.6758214235305786},{"id":"https://openalex.org/keywords/enhanced-data-rates-for-gsm-evolution","display_name":"Enhanced Data Rates for GSM Evolution","score":0.5274332165718079},{"id":"https://openalex.org/keywords/embedded-system","display_name":"Embedded system","score":0.4026294946670532},{"id":"https://openalex.org/keywords/computer-architecture","display_name":"Computer architecture","score":0.3533650040626526},{"id":"https://openalex.org/keywords/computer-engineering","display_name":"Computer engineering","score":0.3267141580581665},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.32524946331977844},{"id":"https://openalex.org/keywords/real-time-computing","display_name":"Real-time computing","score":0.320173978805542},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.2796870470046997},{"id":"https://openalex.org/keywords/telecommunications","display_name":"Telecommunications","score":0.08481615781784058}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7945618629455566},{"id":"https://openalex.org/C82876162","wikidata":"https://www.wikidata.org/wiki/Q17096504","display_name":"Latency (audio)","level":2,"score":0.6999549269676208},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.6758214235305786},{"id":"https://openalex.org/C162307627","wikidata":"https://www.wikidata.org/wiki/Q204833","display_name":"Enhanced Data Rates for GSM Evolution","level":2,"score":0.5274332165718079},{"id":"https://openalex.org/C149635348","wikidata":"https://www.wikidata.org/wiki/Q193040","display_name":"Embedded system","level":1,"score":0.4026294946670532},{"id":"https://openalex.org/C118524514","wikidata":"https://www.wikidata.org/wiki/Q173212","display_name":"Computer architecture","level":1,"score":0.3533650040626526},{"id":"https://openalex.org/C113775141","wikidata":"https://www.wikidata.org/wiki/Q428691","display_name":"Computer engineering","level":1,"score":0.3267141580581665},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.32524946331977844},{"id":"https://openalex.org/C79403827","wikidata":"https://www.wikidata.org/wiki/Q3988","display_name":"Real-time computing","level":1,"score":0.320173978805542},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.2796870470046997},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.08481615781784058}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/infocom52122.2024.10621120","is_oa":false,"landing_page_url":"https://doi.org/10.1109/infocom52122.2024.10621120","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE INFOCOM 2024 - IEEE Conference on Computer Communications","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":28,"referenced_works":["https://openalex.org/W2119144962","https://openalex.org/W2194775991","https://openalex.org/W2525951180","https://openalex.org/W2626129225","https://openalex.org/W2885561518","https://openalex.org/W2886851211","https://openalex.org/W2962988160","https://openalex.org/W2963145730","https://openalex.org/W2963728985","https://openalex.org/W2964233199","https://openalex.org/W3004659153","https://openalex.org/W3014810041","https://openalex.org/W3018143107","https://openalex.org/W3034429256","https://openalex.org/W3047589404","https://openalex.org/W3159535809","https://openalex.org/W3164200338","https://openalex.org/W3166404845","https://openalex.org/W4200118636","https://openalex.org/W4223975181","https://openalex.org/W4226137848","https://openalex.org/W4229801112","https://openalex.org/W4288095610","https://openalex.org/W4290993888","https://openalex.org/W4312273859","https://openalex.org/W4312443924","https://openalex.org/W4382500893","https://openalex.org/W6754088871"],"related_works":["https://openalex.org/W2055243143","https://openalex.org/W4321636575","https://openalex.org/W1986418932","https://openalex.org/W2357796999","https://openalex.org/W2045526782","https://openalex.org/W2741131631","https://openalex.org/W2156919374","https://openalex.org/W2307385607","https://openalex.org/W3128807919","https://openalex.org/W3176411177"],"abstract_inverted_index":{"Despite":[0],"considerable":[1],"advancements":[2],"in":[3,53,117],"specialized":[4],"hardware,":[5],"the":[6,23,108,114,120,126,132],"majority":[7],"of":[8,19,103,113,135,140],"IoT":[9,20],"edge":[10,37,99],"devices":[11],"still":[12],"rely":[13],"on":[14,33,81,97],"CPUs.":[15],"The":[16],"burgeoning":[17],"number":[18],"users":[21],"amplifies":[22],"challenges":[24],"associated":[25],"with":[26],"performing":[27],"multiple":[28],"Deep":[29],"Neural":[30],"Network":[31],"inferences":[32],"these":[34,71],"resource-limited,":[35],"CPU-only":[36,98],"devices.":[38,100],"Existing":[39],"strategies,":[40],"including":[41],"model":[42,47],"compression,":[43],"hardware":[44,60],"acceleration,":[45],"and":[46,93,111],"partitioning,":[48],"often":[49],"involve":[50],"a":[51],"trade-off":[52],"inference":[54,91,133],"accuracy,":[55],"are":[56],"unsuitable":[57],"due":[58],"to":[59,64,70,86,119,125],"specificity,":[61],"or":[62],"lead":[63],"inefficient":[65],"resource":[66,88],"utilization.":[67],"In":[68],"response":[69],"challenges,":[72],"this":[73],"paper":[74],"introduces":[75],"L-PIC":[76,115,129],"(Latency":[77],"Minimized":[78],"Parallel":[79],"Inference":[80],"CPU)\u2014a":[82],"framework":[83,116],"expressly":[84],"devised":[85],"optimize":[87],"allocation,":[89],"decrease":[90],"latency,":[92],"maintain":[94],"result":[95],"accuracy":[96],"A":[101],"series":[102],"comprehensive":[104],"experiments":[105],"have":[106],"verified":[107],"superior":[109],"efficiency":[110],"effectiveness":[112],"comparison":[118],"state-of-the-art":[121,127],"method.":[122],"Remarkably,":[123],"compared":[124],"method,":[128],"can":[130],"reduce":[131],"latency":[134],"multi-DNN":[136],"by":[137],"an":[138],"average":[139],"approximately":[141],"30%":[142],"across":[143],"all":[144],"tested":[145],"scenarios.":[146]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":5},{"year":2024,"cited_by_count":1}],"updated_date":"2026-05-23T08:51:43.019350","created_date":"2025-10-10T00:00:00"}