{"id":"https://openalex.org/W4387687992","doi":"https://doi.org/10.48550/arxiv.2310.09163","title":"Jointly-Learned Exit and Inference for a Dynamic Neural Network : JEI-DNN","display_name":"Jointly-Learned Exit and Inference for a Dynamic Neural Network : JEI-DNN","publication_year":2023,"publication_date":"2023-10-13","ids":{"openalex":"https://openalex.org/W4387687992","doi":"https://doi.org/10.48550/arxiv.2310.09163"},"language":"en","primary_location":{"id":"pmh:oai:arXiv.org:2310.09163","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2310.09163","pdf_url":"https://arxiv.org/pdf/2310.09163","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":"","raw_type":null},"type":"preprint","indexed_in":["arxiv","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2310.09163","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5065633053","display_name":"Florence Regol","orcid":null},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Regol, Florence","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5093073528","display_name":"Joud Chataoui","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Chataoui, Joud","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5009031715","display_name":"Mark Coates","orcid":"https://orcid.org/0000-0001-5030-1379"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Coates, Mark","raw_affiliation_strings":[],"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5065633053"],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11689","display_name":"Adversarial Robustness in Machine Learning","score":0.994700014591217,"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"}},"topics":[{"id":"https://openalex.org/T11689","display_name":"Adversarial Robustness in Machine Learning","score":0.994700014591217,"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/T10320","display_name":"Neural Networks and Applications","score":0.9941999912261963,"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/T10876","display_name":"Fault Detection and Control Systems","score":0.9854999780654907,"subfield":{"id":"https://openalex.org/subfields/2207","display_name":"Control and Systems 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/inference","display_name":"Inference","score":0.8718338012695312},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8376280069351196},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.621359646320343},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.5711925029754639},{"id":"https://openalex.org/keywords/thresholding","display_name":"Thresholding","score":0.5532257556915283},{"id":"https://openalex.org/keywords/gating","display_name":"Gating","score":0.5235459804534912},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.5039011836051941},{"id":"https://openalex.org/keywords/architecture","display_name":"Architecture","score":0.48812398314476013},{"id":"https://openalex.org/keywords/mechanism","display_name":"Mechanism (biology)","score":0.41872546076774597}],"concepts":[{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.8718338012695312},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8376280069351196},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.621359646320343},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.5711925029754639},{"id":"https://openalex.org/C191178318","wikidata":"https://www.wikidata.org/wiki/Q2256906","display_name":"Thresholding","level":3,"score":0.5532257556915283},{"id":"https://openalex.org/C194544171","wikidata":"https://www.wikidata.org/wiki/Q21105679","display_name":"Gating","level":2,"score":0.5235459804534912},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.5039011836051941},{"id":"https://openalex.org/C123657996","wikidata":"https://www.wikidata.org/wiki/Q12271","display_name":"Architecture","level":2,"score":0.48812398314476013},{"id":"https://openalex.org/C89611455","wikidata":"https://www.wikidata.org/wiki/Q6804646","display_name":"Mechanism (biology)","level":2,"score":0.41872546076774597},{"id":"https://openalex.org/C153349607","wikidata":"https://www.wikidata.org/wiki/Q36649","display_name":"Visual arts","level":1,"score":0.0},{"id":"https://openalex.org/C42407357","wikidata":"https://www.wikidata.org/wiki/Q521","display_name":"Physiology","level":1,"score":0.0},{"id":"https://openalex.org/C111472728","wikidata":"https://www.wikidata.org/wiki/Q9471","display_name":"Epistemology","level":1,"score":0.0},{"id":"https://openalex.org/C142362112","wikidata":"https://www.wikidata.org/wiki/Q735","display_name":"Art","level":0,"score":0.0},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"pmh:oai:arXiv.org:2310.09163","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2310.09163","pdf_url":"https://arxiv.org/pdf/2310.09163","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":"","raw_type":null},{"id":"doi:10.48550/arxiv.2310.09163","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2310.09163","pdf_url":null,"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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"article"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2310.09163","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2310.09163","pdf_url":"https://arxiv.org/pdf/2310.09163","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":"","raw_type":null},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/9","display_name":"Industry, innovation and infrastructure","score":0.4399999976158142}],"awards":[{"id":"https://openalex.org/G2165548363","display_name":null,"funder_award_id":"Canada","funder_id":"https://openalex.org/F4320334593","funder_display_name":"Natural Sciences and Engineering Research Council of Canada"},{"id":"https://openalex.org/G3690537240","display_name":null,"funder_award_id":"260250","funder_id":"https://openalex.org/F4320334593","funder_display_name":"Natural Sciences and Engineering Research Council of Canada"},{"id":"https://openalex.org/G8284766523","display_name":null,"funder_award_id":"(NSERC)","funder_id":"https://openalex.org/F4320334593","funder_display_name":"Natural Sciences and Engineering Research Council of Canada"}],"funders":[{"id":"https://openalex.org/F4320334593","display_name":"Natural Sciences and Engineering Research Council of Canada","ror":"https://ror.org/01h531d29"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W2031449089","https://openalex.org/W1542224353","https://openalex.org/W1661087619","https://openalex.org/W2112596406","https://openalex.org/W2125499229","https://openalex.org/W2116854923","https://openalex.org/W2750730210","https://openalex.org/W4385304246","https://openalex.org/W2236974868","https://openalex.org/W4387096269"],"abstract_inverted_index":{"Large":[0],"pretrained":[1],"models,":[2],"coupled":[3],"with":[4],"fine-tuning,":[5],"are":[6,137],"slowly":[7],"becoming":[8],"established":[9],"as":[10,69],"the":[11,31,76,85,108,115,120,132,135,148,157],"dominant":[12],"architecture":[13,66,172],"in":[14],"machine":[15],"learning.":[16],"Even":[17],"though":[18],"these":[19,175],"models":[20],"offer":[21],"impressive":[22],"performance,":[23],"their":[24],"practical":[25],"application":[26],"is":[27,67],"often":[28],"limited":[29],"by":[30,48],"prohibitive":[32],"amount":[33],"of":[34,55,72],"resources":[35],"required":[36],"for":[37,107],"every":[38],"inference.":[39],"Early-exiting":[40],"dynamic":[41],"neural":[42],"networks":[43],"(EDNN)":[44],"circumvent":[45],"this":[46,125],"issue":[47],"allowing":[49],"a":[50,97,143,153,170],"model":[51],"to":[52,113,142,163,180],"make":[53],"some":[54],"its":[56],"predictions":[57],"from":[58,93],"intermediate":[59,86,94],"layers":[60],"(i.e.,":[61],"early-exit).":[62],"Training":[63],"an":[64],"EDNN":[65],"challenging":[68],"it":[70,161],"consists":[71],"two":[73,128,176],"intertwined":[74],"components:":[75],"gating":[77,109,150],"mechanism":[78,110,151],"(GM)":[79],"that":[80,90,173],"controls":[81],"early-exiting":[82],"decisions":[83],"and":[84,111,119,134,146,187],"inference":[87,92,121],"modules":[88],"(IMs)":[89],"perform":[91],"representations.":[95],"As":[96],"result,":[98],"most":[99],"existing":[100],"approaches":[101],"rely":[102],"on":[103,184],"thresholding":[104,149],"confidence":[105],"metrics":[106],"strive":[112],"improve":[114],"underlying":[116],"backbone":[117],"network":[118],"modules.":[122,177],"Although":[123],"successful,":[124],"approach":[126],"has":[127],"fundamental":[129],"shortcomings:":[130],"1)":[131],"GMs":[133],"IMs":[136],"decoupled":[138],"during":[139],"training,":[140],"leading":[141],"train-test":[144],"mismatch;":[145],"2)":[147],"introduces":[152],"positive":[154],"bias":[155],"into":[156],"predictive":[158],"probabilities,":[159],"making":[160],"difficult":[162],"readily":[164],"extract":[165],"uncertainty":[166,190],"information.":[167],"We":[168],"propose":[169],"novel":[171],"connects":[174],"This":[178],"leads":[179],"significant":[181],"performance":[182],"improvements":[183],"classification":[185],"datasets":[186],"enables":[188],"better":[189],"characterization":[191],"capabilities.":[192]},"counts_by_year":[],"updated_date":"2026-04-10T15:06:20.359241","created_date":"2025-10-10T00:00:00"}