{"id":"https://openalex.org/W3045204521","doi":null,"title":"PareCO: Pareto-aware Channel Optimization for Slimmable Neural Networks","display_name":"PareCO: Pareto-aware Channel Optimization for Slimmable Neural Networks","publication_year":2021,"publication_date":"2021-05-04","ids":{"openalex":"https://openalex.org/W3045204521","mag":"3045204521"},"language":"en","primary_location":{"id":"mag:3045204521","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/pdf/2007.11752","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"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":null,"is_accepted":false,"is_published":false,"raw_source_name":"arXiv (Cornell University)","raw_type":null},"volume":null,"type":"preprint","is_traditional":true,"indexed_in":[],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2007.11752","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":null,"display_name":"R Chin","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I74973139","display_name":"Carnegie Mellon University","ror":"https://ror.org/05x2bcf33","country_code":"US","type":"education","lineage":["https://openalex.org/I74973139"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"R Chin","raw_affiliation_strings":["Carnegie Mellon University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Carnegie Mellon University","institution_ids":["https://openalex.org/I74973139"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5042062822","display_name":"Ari S. Morcos","orcid":"https://orcid.org/0000-0001-5370-6515","observed_orcids":["https://orcid.org/0000-0001-5370-6515"]},"institutions":[{"id":"https://openalex.org/I4210114444","display_name":"Meta (United States)","ror":"https://ror.org/01zbnvs85","country_code":"US","type":"company","lineage":["https://openalex.org/I4210114444"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Ari S. Morcos","raw_affiliation_strings":["Facebook AI Research (FAIR)"],"raw_orcid":"https://orcid.org/0000-0001-5370-6515","affiliations":[{"raw_affiliation_string":"Facebook AI Research (FAIR)","institution_ids":["https://openalex.org/I4210114444"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5065985595","display_name":"Diana Marculescu","orcid":"https://orcid.org/0000-0002-5734-4221","observed_orcids":["https://orcid.org/0000-0002-5734-4221"]},"institutions":[{"id":"https://openalex.org/I86519309","display_name":"The University of Texas at Austin","ror":"https://ror.org/00hj54h04","country_code":"US","type":"education","lineage":["https://openalex.org/I86519309"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Diana Marculescu","raw_affiliation_strings":["University of Texas-, Austin,"],"raw_orcid":"https://orcid.org/0000-0002-5734-4221","affiliations":[{"raw_affiliation_string":"University of Texas-, Austin,","institution_ids":["https://openalex.org/I86519309"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":5,"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/T10036","display_name":"Advanced Neural Network Applications","score":0.9994999766349792,"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":0.9994999766349792,"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/T11307","display_name":"Domain Adaptation and Few-Shot Learning","score":9.999999747378752e-05,"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/T12535","display_name":"Machine Learning and Data Classification","score":9.999999747378752e-05,"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/multi-objective-optimization","display_name":"multi-objective optimization","score":0.7979999780654907},{"id":"https://openalex.org/keywords/channel-optimization","display_name":"channel optimization","score":0.6639999747276306},{"id":"https://openalex.org/keywords/flops","display_name":"flops","score":0.6499999761581421},{"id":"https://openalex.org/keywords/memory-usage","display_name":"memory usage","score":0.9950000047683716},{"id":"https://openalex.org/keywords/mobilenetv2","display_name":"MobileNetV2","score":0.8529999852180481},{"id":"https://openalex.org/keywords/resource-constrained-devices","display_name":"resource-constrained devices","score":0.7039999961853027}],"concepts":[{"id":"https://openalex.org/C3826847","wikidata":"https://www.wikidata.org/wiki/Q188768","display_name":"FLOPS","level":2,"score":0.8894190788269043},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7666599750518799},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.6222853660583496},{"id":"https://openalex.org/C74912251","wikidata":"https://www.wikidata.org/wiki/Q6815727","display_name":"Memory footprint","level":2,"score":0.5838342308998108},{"id":"https://openalex.org/C132943942","wikidata":"https://www.wikidata.org/wiki/Q2562511","display_name":"Footprint","level":2,"score":0.5212291479110718},{"id":"https://openalex.org/C124584101","wikidata":"https://www.wikidata.org/wiki/Q1053266","display_name":"Multiplier (economics)","level":2,"score":0.5058662295341492},{"id":"https://openalex.org/C127162648","wikidata":"https://www.wikidata.org/wiki/Q16858953","display_name":"Channel (broadcasting)","level":2,"score":0.46291404962539673},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.3721831440925598},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.27122002840042114},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.11347517371177673},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.11103016138076782},{"id":"https://openalex.org/C31258907","wikidata":"https://www.wikidata.org/wiki/Q1301371","display_name":"Computer network","level":1,"score":0.09307706356048584},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0},{"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/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"id":"https://openalex.org/C151730666","wikidata":"https://www.wikidata.org/wiki/Q7205","display_name":"Paleontology","level":1,"score":0.0},{"id":"https://openalex.org/C139719470","wikidata":"https://www.wikidata.org/wiki/Q39680","display_name":"Macroeconomics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"mag:3045204521","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/pdf/2007.11752","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"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":null,"is_accepted":false,"is_published":false,"raw_source_name":"arXiv (Cornell University)","raw_type":null}],"best_oa_location":{"id":"mag:3045204521","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/pdf/2007.11752","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"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":null,"is_accepted":false,"is_published":false,"raw_source_name":"arXiv (Cornell University)","raw_type":null},"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":57,"referenced_works":["https://openalex.org/W643078925","https://openalex.org/W1502922572","https://openalex.org/W2126105956","https://openalex.org/W2513419314","https://openalex.org/W2515385951","https://openalex.org/W2612445135","https://openalex.org/W2707890836","https://openalex.org/W2739542029","https://openalex.org/W2767421475","https://openalex.org/W2771655537","https://openalex.org/W2786054724","https://openalex.org/W2808868252","https://openalex.org/W2808938483","https://openalex.org/W2810075754","https://openalex.org/W2885820039","https://openalex.org/W2886851211","https://openalex.org/W2886953980","https://openalex.org/W2888850958","https://openalex.org/W2896409484","https://openalex.org/W2896993302","https://openalex.org/W2905741102","https://openalex.org/W2913190747","https://openalex.org/W2928560789","https://openalex.org/W2938070061","https://openalex.org/W2944779197","https://openalex.org/W2945335799","https://openalex.org/W2947681860","https://openalex.org/W2949644579","https://openalex.org/W2951244744","https://openalex.org/W2954234207","https://openalex.org/W2955419283","https://openalex.org/W2962746461","https://openalex.org/W2962851801","https://openalex.org/W2963163009","https://openalex.org/W2964217527","https://openalex.org/W2964282938","https://openalex.org/W2964331719","https://openalex.org/W2968452475","https://openalex.org/W2970072941","https://openalex.org/W2981698279","https://openalex.org/W2981757109","https://openalex.org/W2981812042","https://openalex.org/W2984618279","https://openalex.org/W2988371863","https://openalex.org/W2995816250","https://openalex.org/W3006772089","https://openalex.org/W3016153040","https://openalex.org/W3034357629","https://openalex.org/W3034714646","https://openalex.org/W3035377608","https://openalex.org/W3035400692","https://openalex.org/W3096533519","https://openalex.org/W3105441357","https://openalex.org/W3108411658","https://openalex.org/W3109946440","https://openalex.org/W3124229194","https://openalex.org/W3132013769"],"related_works":["https://openalex.org/W3203732332","https://openalex.org/W2947681860","https://openalex.org/W2905741102","https://openalex.org/W4310922486","https://openalex.org/W2981698279","https://openalex.org/W4405364096","https://openalex.org/W4283021097","https://openalex.org/W3204397102","https://openalex.org/W7162135189","https://openalex.org/W4390148863"],"abstract_inverted_index":{"Slimmable":[0],"neural":[1,47],"networks":[2,48,115],"provide":[3],"a":[4,29,50,83,117,124],"flexible":[5],"trade-off":[6],"front":[7],"between":[8],"prediction":[9,73],"error":[10],"and":[11,76,133,147,150,158,178,194],"computational":[12],"cost":[13,27,154],"(such":[14],"as":[15,28,41],"the":[16,24,55,71,95,110,130,134,137,163,166,184,201,205,213],"number":[17],"of":[18,97,112,153,165,203],"floating-point":[19],"operations":[20],"or":[21],"FLOPs)":[22],"with":[23,61,144,212],"same":[25],"storage":[26],"single":[30,51],"model.":[31],"They":[32],"have":[33,77],"been":[34],"proposed":[35,167],"recently":[36],"for":[37,53,86,102,127,136,190,208,215],"resource-constrained":[38],"settings":[39],"such":[40],"mobile":[42],"devices.":[43],"However,":[44],"current":[45],"slimmable":[46,98,114,216],"use":[49],"width-multiplier":[52],"all":[54],"layers":[56,69,91,210],"to":[57,123,161,170,176],"arrive":[58],"at":[59],"sub-networks":[60],"different":[62,68,78,90,106,209],"performance":[63,96],"profiles,":[64],"which":[65,121],"neglects":[66],"that":[67],"affect":[70],"network's":[72],"accuracy":[74,182],"differently":[75],"FLOP":[79],"requirements.":[80],"Hence,":[81],"developing":[82],"principled":[84],"approach":[85],"deciding":[87],"width-multipliers":[88,104,135],"across":[89,105],"could":[92],"potentially":[93],"improve":[94],"networks.":[99,217],"To":[100],"allow":[101],"heterogeneous":[103],"layers,":[107],"we":[108],"formulate":[109],"problem":[111],"optimizing":[113,128,204],"from":[116],"multi-objective":[118],"optimization":[119],"lens,":[120],"leads":[122],"novel":[125],"algorithm":[126],"both":[129],"shared":[131],"weights":[132,214],"sub-networks.":[138],"We":[139],"perform":[140],"extensive":[141],"empirical":[142],"analysis":[143],"15":[145],"network":[146],"dataset":[148,186],"combinations":[149],"two":[151],"types":[152],"objectives,":[155],"i.e.,":[156],"FLOPs":[157,193],"memory":[159,195],"footprint,":[160,196],"demonstrate":[162],"effectiveness":[164],"method":[168],"compared":[169],"existing":[171],"alternatives.":[172],"Quantitatively,":[173],"improvements":[174],"up":[175],"1.7%":[177],"8%":[179],"in":[180],"top-1":[181],"on":[183],"ImageNet":[185],"can":[187],"be":[188],"attained":[189],"MobileNetV2":[191],"considering":[192],"respectively.":[197],"Our":[198],"results":[199],"highlight":[200],"potential":[202],"channel":[206],"counts":[207],"jointly":[211]},"counts_by_year":[{"year":2022,"cited_by_count":2},{"year":2021,"cited_by_count":3}],"updated_date":"2026-11-04T10:54:05.112534","created_date":"2020-07-29T00:00:00"}