{"id":"https://openalex.org/W4411285952","doi":"https://doi.org/10.32604/cmc.2025.064544","title":"Neural Architecture Search via Hierarchical Evaluation of Surrogate Models","display_name":"Neural Architecture Search via Hierarchical Evaluation of Surrogate Models","publication_year":2025,"publication_date":"2025-01-01","ids":{"openalex":"https://openalex.org/W4411285952","doi":"https://doi.org/10.32604/cmc.2025.064544"},"language":"en","primary_location":{"id":"doi:10.32604/cmc.2025.064544","is_oa":true,"landing_page_url":"https://doi.org/10.32604/cmc.2025.064544","pdf_url":null,"source":{"id":"https://openalex.org/S4210191605","display_name":"Computers, materials & continua/Computers, materials & continua (Print)","issn_l":"1546-2218","issn":["1546-2218","1546-2226"],"is_oa":true,"is_in_doaj":false,"is_core":true,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Computers, Materials & Continua","raw_type":"journal-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"diamond","oa_url":"https://doi.org/10.32604/cmc.2025.064544","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5100664024","display_name":"Xiaofeng Liu","orcid":"https://orcid.org/0000-0002-8378-9558"},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Xiaofeng Liu","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102879175","display_name":"Yubin Bao","orcid":"https://orcid.org/0000-0001-7350-0610"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yubin Bao","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5079692051","display_name":"Fangling Leng","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Fangling Leng","raw_affiliation_strings":[],"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5100664024"],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":2.8843,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.91418643,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":91,"max":95},"biblio":{"volume":"84","issue":"2","first_page":"3503","last_page":"3517"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12535","display_name":"Machine Learning and Data Classification","score":0.982699990272522,"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/T12535","display_name":"Machine Learning and Data Classification","score":0.982699990272522,"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":0.9035999774932861,"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/computer-science","display_name":"Computer science","score":0.5492106676101685},{"id":"https://openalex.org/keywords/architecture","display_name":"Architecture","score":0.5450747609138489},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4870896339416504},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.3345911502838135},{"id":"https://openalex.org/keywords/geography","display_name":"Geography","score":0.10126453638076782}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5492106676101685},{"id":"https://openalex.org/C123657996","wikidata":"https://www.wikidata.org/wiki/Q12271","display_name":"Architecture","level":2,"score":0.5450747609138489},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4870896339416504},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3345911502838135},{"id":"https://openalex.org/C205649164","wikidata":"https://www.wikidata.org/wiki/Q1071","display_name":"Geography","level":0,"score":0.10126453638076782},{"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:10.32604/cmc.2025.064544","is_oa":true,"landing_page_url":"https://doi.org/10.32604/cmc.2025.064544","pdf_url":null,"source":{"id":"https://openalex.org/S4210191605","display_name":"Computers, materials & continua/Computers, materials & continua (Print)","issn_l":"1546-2218","issn":["1546-2218","1546-2226"],"is_oa":true,"is_in_doaj":false,"is_core":true,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Computers, Materials & Continua","raw_type":"journal-article"}],"best_oa_location":{"id":"doi:10.32604/cmc.2025.064544","is_oa":true,"landing_page_url":"https://doi.org/10.32604/cmc.2025.064544","pdf_url":null,"source":{"id":"https://openalex.org/S4210191605","display_name":"Computers, materials & continua/Computers, materials & continua (Print)","issn_l":"1546-2218","issn":["1546-2218","1546-2226"],"is_oa":true,"is_in_doaj":false,"is_core":true,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Computers, Materials & Continua","raw_type":"journal-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":23,"referenced_works":["https://openalex.org/W2016023958","https://openalex.org/W2953308748","https://openalex.org/W3000881061","https://openalex.org/W3038678879","https://openalex.org/W3088798822","https://openalex.org/W3165895193","https://openalex.org/W3209827161","https://openalex.org/W3213749028","https://openalex.org/W4205379581","https://openalex.org/W4220956472","https://openalex.org/W4281639156","https://openalex.org/W4283833515","https://openalex.org/W4289523236","https://openalex.org/W4320474661","https://openalex.org/W4385411194","https://openalex.org/W4386087181","https://openalex.org/W4386281793","https://openalex.org/W4390753745","https://openalex.org/W4391853495","https://openalex.org/W4392666373","https://openalex.org/W4393144919","https://openalex.org/W4406113408","https://openalex.org/W4406176023"],"related_works":["https://openalex.org/W2961085424","https://openalex.org/W4306674287","https://openalex.org/W4387369504","https://openalex.org/W4394896187","https://openalex.org/W3170094116","https://openalex.org/W4386462264","https://openalex.org/W3107602296","https://openalex.org/W4364306694","https://openalex.org/W4312192474","https://openalex.org/W4283697347"],"abstract_inverted_index":{"The":[0,125,159,217],"rapid":[1,107],"development":[2],"of":[3,12,38,139,180,241],"evolutionary":[4,164],"deep":[5],"learning":[6],"has":[7],"led":[8],"to":[9,20,34,94,115,171,206],"the":[10,35,117,129,137,150,173,178,181,187,194,200,234,239,242],"emergence":[11],"various":[13],"Neural":[14],"Architecture":[15],"Search":[16],"(NAS)":[17],"algorithms":[18,27],"designed":[19],"optimize":[21],"neural":[22,40],"network":[23],"structures.":[24],"However,":[25],"these":[26,72],"often":[28],"face":[29],"significant":[30],"computational":[31,123],"costs":[32,204],"due":[33],"time-consuming":[36],"process":[37,175,236],"training":[39,56,154],"networks":[41],"and":[42,54,97,122,169,176,189,203],"evaluating":[43],"their":[44],"performance.":[45,216],"Traditional":[46],"NAS":[47,79,235],"approaches,":[48],"which":[49],"rely":[50],"on":[51,88,186],"exhaustive":[52],"evaluations":[53,110,114,185],"large":[55],"datasets,":[57],"are":[58],"inefficient":[59],"for":[60,132,152,156,232],"solving":[61],"complex":[62],"image":[63],"classification":[64],"tasks":[65],"within":[66],"limited":[67],"time":[68,130,202],"frames.":[69],"To":[70],"address":[71],"challenges,":[73],"this":[74,221],"paper":[75],"proposes":[76],"a":[77,83,143,229],"novel":[78],"algorithm":[80,126],"that":[81,193,220],"integrates":[82],"hierarchical":[84,104,196],"evaluation":[85,134,197],"strategy":[86,198],"based":[87],"Surrogate":[89,108,146],"models,":[90],"specifically":[91],"using":[92,142],"supernet":[93],"pre-train":[95],"weights":[96],"random":[98,144],"forests":[99],"as":[100,167],"performance":[101,120],"predictors.":[102],"This":[103],"framework":[105],"combines":[106],"model":[109,133,215],"with":[111],"traditional,":[112],"precise":[113],"balance":[116],"trade-off":[118],"between":[119],"accuracy":[121,179],"efficiency.":[124],"significantly":[127],"reduces":[128,199],"required":[131],"by":[135],"predicting":[136],"fitness":[138],"candidate":[140],"architectures":[141],"forest":[145],"model,":[147],"thus":[148],"alleviating":[149],"need":[151],"full":[153],"cycles":[155],"each":[157],"architecture.":[158],"proposed":[160,195],"method":[161],"also":[162],"incorporates":[163],"operations":[165],"such":[166],"mutation":[168],"crossover":[170],"refine":[172],"search":[174,201],"improve":[177],"resulting":[182],"architectures.":[183,244],"Experimental":[184],"CIFAR-10":[188],"CIFAR-100":[190],"datasets":[191],"demonstrate":[192],"compared":[205],"traditional":[207],"methods,":[208],"while":[209],"achieving":[210],"comparable":[211],"or":[212],"even":[213],"superior":[214],"results":[218],"suggest":[219],"approach":[222],"can":[223],"efficiently":[224],"handle":[225],"resource-constrained":[226],"tasks,":[227],"providing":[228],"promising":[230],"solution":[231],"accelerating":[233],"without":[237],"compromising":[238],"quality":[240],"generated":[243]},"counts_by_year":[{"year":2025,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}