{"id":"https://openalex.org/W4402915869","doi":"https://doi.org/10.1109/icip51287.2024.10647243","title":"Set-Nas: Sample-Efficient Training For Neural Architecture Search With Strong Predictor And Stratified Sampling","display_name":"Set-Nas: Sample-Efficient Training For Neural Architecture Search With Strong Predictor And Stratified Sampling","publication_year":2024,"publication_date":"2024-09-27","ids":{"openalex":"https://openalex.org/W4402915869","doi":"https://doi.org/10.1109/icip51287.2024.10647243"},"language":"en","primary_location":{"id":"doi:10.1109/icip51287.2024.10647243","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1109/icip51287.2024.10647243","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 IEEE International Conference on Image Processing (ICIP)","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/A5063766841","display_name":"Y. Zhang","orcid":"https://orcid.org/0009-0007-6675-0436"},"institutions":[{"id":"https://openalex.org/I22265921","display_name":"National Central University","ror":"https://ror.org/00944ve71","country_code":"TW","type":"education","lineage":["https://openalex.org/I22265921"]}],"countries":["TW"],"is_corresponding":true,"raw_author_name":"Yu-Ming Zhang","raw_affiliation_strings":["National Central University,Dep. of Computer Science and Inf. Eng.,Taoyuan,Taiwan"],"affiliations":[{"raw_affiliation_string":"National Central University,Dep. of Computer Science and Inf. Eng.,Taoyuan,Taiwan","institution_ids":["https://openalex.org/I22265921"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5007240491","display_name":"Jun-Wei Hsieh","orcid":"https://orcid.org/0000-0003-4729-0730"},"institutions":[{"id":"https://openalex.org/I148366613","display_name":"National Yang Ming Chiao Tung University","ror":"https://ror.org/00se2k293","country_code":"TW","type":"education","lineage":["https://openalex.org/I148366613"]}],"countries":["TW"],"is_corresponding":false,"raw_author_name":"Jun-Wei Hsieh","raw_affiliation_strings":["National Yang Ming Chiao Tung University,College of AI and Green Energy,Hsinchu,Taiwan"],"affiliations":[{"raw_affiliation_string":"National Yang Ming Chiao Tung University,College of AI and Green Energy,Hsinchu,Taiwan","institution_ids":["https://openalex.org/I148366613"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5022841465","display_name":"Yu-Hsiu Chang","orcid":null},"institutions":[{"id":"https://openalex.org/I22265921","display_name":"National Central University","ror":"https://ror.org/00944ve71","country_code":"TW","type":"education","lineage":["https://openalex.org/I22265921"]}],"countries":["TW"],"is_corresponding":false,"raw_author_name":"Yu-Hsiu Chang","raw_affiliation_strings":["National Central University,Dep. of Computer Science and Inf. Eng.,Taoyuan,Taiwan"],"affiliations":[{"raw_affiliation_string":"National Central University,Dep. of Computer Science and Inf. Eng.,Taoyuan,Taiwan","institution_ids":["https://openalex.org/I22265921"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100354100","display_name":"Xin Li","orcid":"https://orcid.org/0009-0008-1831-7459"},"institutions":[{"id":"https://openalex.org/I392282","display_name":"University at Albany, State University of New York","ror":"https://ror.org/012zs8222","country_code":"US","type":"education","lineage":["https://openalex.org/I392282"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Xin Li","raw_affiliation_strings":["University at Albany,Dep. of Computer Science and Inf. Eng.,New York,USA"],"affiliations":[{"raw_affiliation_string":"University at Albany,Dep. of Computer Science and Inf. Eng.,New York,USA","institution_ids":["https://openalex.org/I392282"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5111705165","display_name":"Ming-Ching Chang","orcid":null},"institutions":[{"id":"https://openalex.org/I392282","display_name":"University at Albany, State University of New York","ror":"https://ror.org/012zs8222","country_code":"US","type":"education","lineage":["https://openalex.org/I392282"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Ming-Ching Chang","raw_affiliation_strings":["University at Albany,Dep. of Computer Science and Inf. Eng.,New York,USA"],"affiliations":[{"raw_affiliation_string":"University at Albany,Dep. of Computer Science and Inf. Eng.,New York,USA","institution_ids":["https://openalex.org/I392282"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5028630366","display_name":"Chun-Chieh Lee","orcid":"https://orcid.org/0000-0002-1285-6100"},"institutions":[{"id":"https://openalex.org/I22265921","display_name":"National Central University","ror":"https://ror.org/00944ve71","country_code":"TW","type":"education","lineage":["https://openalex.org/I22265921"]}],"countries":["TW"],"is_corresponding":false,"raw_author_name":"Chun-Chieh Lee","raw_affiliation_strings":["National Central University,Dep. of Computer Science and Inf. Eng.,Taoyuan,Taiwan"],"affiliations":[{"raw_affiliation_string":"National Central University,Dep. of Computer Science and Inf. Eng.,Taoyuan,Taiwan","institution_ids":["https://openalex.org/I22265921"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5041444982","display_name":"Kuo-Chin Fan","orcid":null},"institutions":[{"id":"https://openalex.org/I22265921","display_name":"National Central University","ror":"https://ror.org/00944ve71","country_code":"TW","type":"education","lineage":["https://openalex.org/I22265921"]}],"countries":["TW"],"is_corresponding":false,"raw_author_name":"Kuo-Chin Fan","raw_affiliation_strings":["National Central University,Dep. of Computer Science and Inf. Eng.,Taoyuan,Taiwan"],"affiliations":[{"raw_affiliation_string":"National Central University,Dep. of Computer Science and Inf. Eng.,Taoyuan,Taiwan","institution_ids":["https://openalex.org/I22265921"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":7,"corresponding_author_ids":["https://openalex.org/A5063766841"],"corresponding_institution_ids":["https://openalex.org/I22265921"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.14440662,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"34","issue":null,"first_page":"680","last_page":"686"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10320","display_name":"Neural Networks and Applications","score":0.9824000000953674,"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/T10320","display_name":"Neural Networks and Applications","score":0.9824000000953674,"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":0.9735000133514404,"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/T10036","display_name":"Advanced Neural Network Applications","score":0.9391999840736389,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/stratified-sampling","display_name":"Stratified sampling","score":0.8293421268463135},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6605693697929382},{"id":"https://openalex.org/keywords/architecture","display_name":"Architecture","score":0.5751045346260071},{"id":"https://openalex.org/keywords/sample","display_name":"Sample (material)","score":0.5651459097862244},{"id":"https://openalex.org/keywords/sampling","display_name":"Sampling (signal processing)","score":0.5434423685073853},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.47640931606292725},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.45337554812431335},{"id":"https://openalex.org/keywords/training","display_name":"Training (meteorology)","score":0.4345391094684601},{"id":"https://openalex.org/keywords/training-set","display_name":"Training set","score":0.4293312430381775},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.32765090465545654},{"id":"https://openalex.org/keywords/statistics","display_name":"Statistics","score":0.25094738602638245},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.13476943969726562},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.09231138229370117},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.07060584425926208},{"id":"https://openalex.org/keywords/geography","display_name":"Geography","score":0.057819664478302}],"concepts":[{"id":"https://openalex.org/C49898467","wikidata":"https://www.wikidata.org/wiki/Q1517706","display_name":"Stratified sampling","level":2,"score":0.8293421268463135},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6605693697929382},{"id":"https://openalex.org/C123657996","wikidata":"https://www.wikidata.org/wiki/Q12271","display_name":"Architecture","level":2,"score":0.5751045346260071},{"id":"https://openalex.org/C198531522","wikidata":"https://www.wikidata.org/wiki/Q485146","display_name":"Sample (material)","level":2,"score":0.5651459097862244},{"id":"https://openalex.org/C140779682","wikidata":"https://www.wikidata.org/wiki/Q210868","display_name":"Sampling (signal processing)","level":3,"score":0.5434423685073853},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.47640931606292725},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.45337554812431335},{"id":"https://openalex.org/C2777211547","wikidata":"https://www.wikidata.org/wiki/Q17141490","display_name":"Training (meteorology)","level":2,"score":0.4345391094684601},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.4293312430381775},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.32765090465545654},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.25094738602638245},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.13476943969726562},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.09231138229370117},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.07060584425926208},{"id":"https://openalex.org/C205649164","wikidata":"https://www.wikidata.org/wiki/Q1071","display_name":"Geography","level":0,"score":0.057819664478302},{"id":"https://openalex.org/C106131492","wikidata":"https://www.wikidata.org/wiki/Q3072260","display_name":"Filter (signal processing)","level":2,"score":0.0},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0},{"id":"https://openalex.org/C153294291","wikidata":"https://www.wikidata.org/wiki/Q25261","display_name":"Meteorology","level":1,"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/C166957645","wikidata":"https://www.wikidata.org/wiki/Q23498","display_name":"Archaeology","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icip51287.2024.10647243","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1109/icip51287.2024.10647243","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 IEEE International Conference on Image Processing (ICIP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":19,"referenced_works":["https://openalex.org/W2012451526","https://openalex.org/W2061144551","https://openalex.org/W2965658867","https://openalex.org/W2981406437","https://openalex.org/W3094801149","https://openalex.org/W3141259390","https://openalex.org/W4234228486","https://openalex.org/W4252003911","https://openalex.org/W4382203144","https://openalex.org/W4382317874","https://openalex.org/W4382461437","https://openalex.org/W6751209437","https://openalex.org/W6759402996","https://openalex.org/W6764988152","https://openalex.org/W6771859737","https://openalex.org/W6788673338","https://openalex.org/W6790224847","https://openalex.org/W6793646068","https://openalex.org/W6797304698"],"related_works":["https://openalex.org/W2387471420","https://openalex.org/W3042964584","https://openalex.org/W2356880469","https://openalex.org/W2383809451","https://openalex.org/W4206840145","https://openalex.org/W2370014976","https://openalex.org/W2350399852","https://openalex.org/W2378407977","https://openalex.org/W3047864323","https://openalex.org/W2075598034"],"abstract_inverted_index":{"Sample-efficient":[0],"neural":[1,14,81],"architecture":[2],"search":[3],"(NAS)":[4],"techniques":[5],"have":[6,19],"advanced":[7],"rapidly.":[8],"Two":[9],"lines":[10],"of":[11,28,98,120,157,160],"methods,":[12],"namely":[13],"predictor":[15,82,96,106],"and":[16,55,74,153],"sequential":[17],"search,":[18],"shown":[20],"promising":[21,168],"performance":[22],"in":[23,101,136],"improving":[24],"the":[25,42,51,84,95,99,124,134,142,167],"sample":[26],"efficiency":[27],"NAS.":[29,138],"However,":[30],"as":[31,33,141],"far":[32],"we":[34,58],"know,":[35],"little":[36],"attention":[37],"has":[38],"been":[39],"paid":[40],"to":[41,115,133,165],"middle":[43],"ground":[44],"between":[45,53],"these":[46],"two":[47],"lines.":[48],"Inspired":[49],"by":[50],"analogy":[52],"NAS":[54,65],"evolutionary":[56,90],"optimization,":[57],"propose":[59],"a":[60,79,118],"new":[61],"Sample-Efficient":[62],"Training":[63],"for":[64],"(SETNAS)":[66],"based":[67],"on":[68],"strategies":[69],"that":[70,92],"improve":[71],"fitness":[72],"scores":[73],"sampling":[75,113],"mechanisms.":[76],"We":[77],"develop":[78],"strong":[80],"called":[83],"Fully":[85],"Bidirectional":[86],"Graph":[87],"Convolutional":[88],"Network":[89],"(Fully-BiGCN)":[91],"significantly":[93],"enhances":[94],"capability":[97],"features":[100],"each":[102],"layer.":[103],"The":[104],"developed":[105],"is":[107],"embedded":[108],"into":[109],"an":[110],"iterative":[111],"stratified":[112],"process":[114],"retain":[116],"only":[117,146],"subset":[119],"best-fit":[121],"architectures":[122],"using":[123],"same":[125],"training":[126,158],"budget.":[127],"SET-NAS":[128,144],"achieves":[129],"remarkable":[130],"results":[131],"compared":[132],"state-of-the-art":[135,162],"predictor-based":[137,163],"Using":[139],"NASBench-201":[140],"benchmark,":[143],"takes":[145],"$27.1":[147],"\\%$":[148,151,155],"(CIFAR-10),":[149],"$49.0":[150],"(CIFAR-100),":[152],"$51.75":[154],"(ImageNet-16)":[156],"cost":[159],"other":[161],"methods":[164],"find":[166],"network":[169],"architecture.":[170]},"counts_by_year":[],"updated_date":"2025-12-22T23:10:17.713674","created_date":"2025-10-10T00:00:00"}