{"id":"https://openalex.org/W4313526199","doi":"https://doi.org/10.1109/latincom56090.2022.10000430","title":"Decision Early-Exit: An Efficient Approach to Hasten Offloading in BranchyNets","display_name":"Decision Early-Exit: An Efficient Approach to Hasten Offloading in BranchyNets","publication_year":2022,"publication_date":"2022-11-30","ids":{"openalex":"https://openalex.org/W4313526199","doi":"https://doi.org/10.1109/latincom56090.2022.10000430"},"language":"en","primary_location":{"id":"doi:10.1109/latincom56090.2022.10000430","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1109/latincom56090.2022.10000430","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2022 IEEE Latin-American Conference on Communications (LATINCOM)","raw_type":"proceedings-article"},"type":"conference-paper","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/A5055484203","display_name":"Mariana S. M. Barbosa","orcid":"https://orcid.org/0000-0001-5636-9956"},"institutions":[{"id":"https://openalex.org/I122140584","display_name":"Universidade Federal do Rio de Janeiro","ror":"https://ror.org/03490as77","country_code":"BR","type":"education","lineage":["https://openalex.org/I122140584"]}],"countries":["BR"],"is_corresponding":false,"raw_author_name":"Mariana S. M. Barbosa","raw_affiliation_strings":["GTA/PEE-COPPE/DEL-Poli – Universidade Federal do Rio de Janeiro (UFRJ),Rio de Janeiro,Brazil"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"GTA/PEE-COPPE/DEL-Poli – Universidade Federal do Rio de Janeiro (UFRJ),Rio de Janeiro,Brazil","institution_ids":["https://openalex.org/I122140584"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5081714773","display_name":"Roberto G. Pacheco","orcid":"https://orcid.org/0000-0002-6763-7255"},"institutions":[{"id":"https://openalex.org/I122140584","display_name":"Universidade Federal do Rio de Janeiro","ror":"https://ror.org/03490as77","country_code":"BR","type":"education","lineage":["https://openalex.org/I122140584"]}],"countries":["BR"],"is_corresponding":false,"raw_author_name":"Roberto G. Pacheco","raw_affiliation_strings":["GTA/PEE-COPPE/DEL-Poli – Universidade Federal do Rio de Janeiro (UFRJ),Rio de Janeiro,Brazil"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"GTA/PEE-COPPE/DEL-Poli – Universidade Federal do Rio de Janeiro (UFRJ),Rio de Janeiro,Brazil","institution_ids":["https://openalex.org/I122140584"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5044922664","display_name":"Rodrigo S. Couto","orcid":"https://orcid.org/0000-0002-6921-7756"},"institutions":[{"id":"https://openalex.org/I122140584","display_name":"Universidade Federal do Rio de Janeiro","ror":"https://ror.org/03490as77","country_code":"BR","type":"education","lineage":["https://openalex.org/I122140584"]}],"countries":["BR"],"is_corresponding":false,"raw_author_name":"Rodrigo S. Couto","raw_affiliation_strings":["GTA/PEE-COPPE/DEL-Poli – Universidade Federal do Rio de Janeiro (UFRJ),Rio de Janeiro,Brazil"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"GTA/PEE-COPPE/DEL-Poli – Universidade Federal do Rio de Janeiro (UFRJ),Rio de Janeiro,Brazil","institution_ids":["https://openalex.org/I122140584"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5055579099","display_name":"Dianne S. V. Medeiros","orcid":"https://orcid.org/0000-0002-0361-5903"},"institutions":[{"id":"https://openalex.org/I161127581","display_name":"Universidade Federal Fluminense","ror":"https://ror.org/02rjhbb08","country_code":"BR","type":"education","lineage":["https://openalex.org/I161127581"]}],"countries":["BR"],"is_corresponding":false,"raw_author_name":"Dianne S. V. Medeiros","raw_affiliation_strings":["MídiaCom/PPGEET – Universidade Federal Fluminense (UFF),Rio de Janeiro,Brazil"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"MídiaCom/PPGEET – Universidade Federal Fluminense (UFF),Rio de Janeiro,Brazil","institution_ids":["https://openalex.org/I161127581"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5083970479","display_name":"Miguel Elias M. Campista","orcid":"https://orcid.org/0000-0002-8752-9382"},"institutions":[{"id":"https://openalex.org/I122140584","display_name":"Universidade Federal do Rio de Janeiro","ror":"https://ror.org/03490as77","country_code":"BR","type":"education","lineage":["https://openalex.org/I122140584"]}],"countries":["BR"],"is_corresponding":false,"raw_author_name":"Miguel Elias M. Campista","raw_affiliation_strings":["GTA/PEE-COPPE/DEL-Poli – Universidade Federal do Rio de Janeiro (UFRJ),Rio de Janeiro,Brazil"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"GTA/PEE-COPPE/DEL-Poli – Universidade Federal do Rio de Janeiro (UFRJ),Rio de Janeiro,Brazil","institution_ids":["https://openalex.org/I122140584"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.19518565,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"6"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10036","display_name":"Advanced Neural Network Applications","score":0.9998000264167786,"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":0.9998000264167786,"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/T11689","display_name":"Adversarial Robustness in Machine Learning","score":0.9965000152587891,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"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/T11612","display_name":"Stochastic Gradient Optimization Techniques","score":0.9943000078201294,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"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":0.8972340822219849},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7953822612762451},{"id":"https://openalex.org/keywords/sample","display_name":"Sample (material)","score":0.6356386542320251},{"id":"https://openalex.org/keywords/enhanced-data-rates-for-gsm-evolution","display_name":"Enhanced Data Rates for GSM Evolution","score":0.5607354044914246},{"id":"https://openalex.org/keywords/cloud-computing","display_name":"Cloud computing","score":0.48945581912994385},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4170971214771271},{"id":"https://openalex.org/keywords/statistical-inference","display_name":"Statistical inference","score":0.41217613220214844},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.3868415057659149},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.35757237672805786},{"id":"https://openalex.org/keywords/statistics","display_name":"Statistics","score":0.15649762749671936},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.06774091720581055}],"concepts":[{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.8972340822219849},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7953822612762451},{"id":"https://openalex.org/C198531522","wikidata":"https://www.wikidata.org/wiki/Q485146","display_name":"Sample (material)","level":2,"score":0.6356386542320251},{"id":"https://openalex.org/C162307627","wikidata":"https://www.wikidata.org/wiki/Q204833","display_name":"Enhanced Data Rates for GSM Evolution","level":2,"score":0.5607354044914246},{"id":"https://openalex.org/C79974875","wikidata":"https://www.wikidata.org/wiki/Q483639","display_name":"Cloud computing","level":2,"score":0.48945581912994385},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4170971214771271},{"id":"https://openalex.org/C134261354","wikidata":"https://www.wikidata.org/wiki/Q938438","display_name":"Statistical inference","level":2,"score":0.41217613220214844},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3868415057659149},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.35757237672805786},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.15649762749671936},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.06774091720581055},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0},{"id":"https://openalex.org/C43617362","wikidata":"https://www.wikidata.org/wiki/Q170050","display_name":"Chromatography","level":1,"score":0.0},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/latincom56090.2022.10000430","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1109/latincom56090.2022.10000430","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2022 IEEE Latin-American Conference on Communications (LATINCOM)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.699999988079071,"id":"https://metadata.un.org/sdg/16","display_name":"Peace, Justice and strong institutions"}],"awards":[],"funders":[{"id":"https://openalex.org/F4320321091","display_name":"Coordena\u00e7\u00e3o de Aperfei\u00e7oamento de Pessoal de N\u00edvel Superior","ror":"https://ror.org/00x0ma614"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":14,"referenced_works":["https://openalex.org/W2909099954","https://openalex.org/W2962677625","https://openalex.org/W2962883027","https://openalex.org/W2979679572","https://openalex.org/W3021083954","https://openalex.org/W3030840723","https://openalex.org/W3049640275","https://openalex.org/W3093589362","https://openalex.org/W3102767875","https://openalex.org/W3118608800","https://openalex.org/W3189069895","https://openalex.org/W3200649648","https://openalex.org/W3206423279","https://openalex.org/W6787972765"],"related_works":["https://openalex.org/W4244478748","https://openalex.org/W4223488648","https://openalex.org/W2134969820","https://openalex.org/W137830373","https://openalex.org/W3000984192","https://openalex.org/W2103073163","https://openalex.org/W4286952477","https://openalex.org/W4321348134","https://openalex.org/W4237128662","https://openalex.org/W4255444043"],"abstract_inverted_index":{"Many":[0],"works":[1],"study":[2],"partitioning":[3],"and":[4,161,204],"early":[5,42,80,118,132],"exits":[6,18,43],"in":[7,24,66,209],"Deep":[8],"Neural":[9],"Networks":[10],"(DNNs)":[11],"to":[12,56,75,121,138],"improve":[13,139],"the":[14,20,28,50,54,59,62,67,76,86,96,116,123,140,146,154,164,178,184,188,201,205,216,224,229],"inference":[15,21,88,125,189,202,217],"time.":[16,89,190],"Early":[17,111],"allow":[19],"of":[22,41,53,180],"samples":[23,71,230],"advance,":[25],"based":[26],"on":[27,187],"fact":[29],"that":[30,176,194],"some":[31],"features":[32],"are":[33,231],"learned":[34],"at":[35,58,78,115,131],"DNNs\u2019":[36],"initial":[37],"layers.":[38],"However,":[39],"usage":[40],"can":[44,214],"slightly":[45],"decrease":[46],"performance.":[47,142],"Partitioning":[48],"enables":[49],"shallowest":[51],"part":[52],"model":[55,97],"reside":[57,65],"edge":[60],"while":[61,94,222],"deeper":[63],"layers":[64],"cloud.":[68],"Deciding":[69],"whether":[70,163],"must":[72,166],"be":[73,167],"sent":[74],"cloud":[77],"each":[79,159],"exit":[81],"is":[82,99,196],"time":[83,93,126,203,218],"consuming,":[84],"increasing":[85],"total":[87,124],"Hence,":[90],"reducing":[91],"this":[92,105,144],"maintaining":[95,223],"performance":[98],"currently":[100],"an":[101],"open":[102],"challenge.":[103],"In":[104],"paper,":[106],"we":[107,213],"propose":[108],"a":[109,149,173,197,210],"Decision":[110],"Exit":[112],"(DEEx),":[113],"implemented":[114],"first":[117],"exit,":[119],"aiming":[120],"reduce":[122,215],"by":[127,219],"skipping":[128],"unnecessary":[129],"evaluations":[130],"exits,":[133],"which":[134],"may":[135],"not":[136],"able":[137],"model\u2019s":[141],"To":[143],"end,":[145],"DEEx":[147,171,208],"compares":[148],"predefined":[150],"decision":[151,185],"threshold":[152,186],"with":[153],"prediction":[155],"confidence":[156],"level":[157],"for":[158,183],"sample":[160,165],"decides":[162],"offloaded.":[168,232],"We":[169],"assess":[170],"through":[172],"comparative":[174],"analysis":[175],"investigates":[177],"influence":[179],"different":[181],"values":[182],"Our":[191],"results":[192],"show":[193],"there":[195],"cost":[198],"benefit":[199],"between":[200],"threshold.":[206],"Using":[207],"simulated":[211],"BranchyNet,":[212],"around":[220],"20%":[221],"same":[225],"accuracy":[226],"achieved":[227],"when":[228]},"counts_by_year":[],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}