{"id":"https://openalex.org/W4411430099","doi":"https://doi.org/10.32604/cmc.2025.064969","title":"Graph-Embedded Neural Architecture Search: A Variational Approach for Optimized Model Design","display_name":"Graph-Embedded Neural Architecture Search: A Variational Approach for Optimized Model Design","publication_year":2025,"publication_date":"2025-01-01","ids":{"openalex":"https://openalex.org/W4411430099","doi":"https://doi.org/10.32604/cmc.2025.064969"},"language":"en","primary_location":{"id":"doi:10.32604/cmc.2025.064969","is_oa":true,"landing_page_url":"https://doi.org/10.32604/cmc.2025.064969","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.2025.064969","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5109801169","display_name":"K. Hemmi","orcid":null},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Kazuki Hemmi","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5070679258","display_name":"Yuki Tanigaki","orcid":"https://orcid.org/0000-0002-4058-4480"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yuki Tanigaki","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5104120613","display_name":"Kaisei Hara","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Kaisei Hara","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5031341888","display_name":"Masaki Onishi","orcid":"https://orcid.org/0000-0002-4580-4868"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Masaki Onishi","raw_affiliation_strings":[],"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5109801169"],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.07521114,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"84","issue":"2","first_page":"2245","last_page":"2271"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10320","display_name":"Neural Networks and Applications","score":0.8321999907493591,"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":0.8321999907493591,"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":0.5867700576782227},{"id":"https://openalex.org/keywords/architecture","display_name":"Architecture","score":0.5551198720932007},{"id":"https://openalex.org/keywords/graph","display_name":"Graph","score":0.5210477709770203},{"id":"https://openalex.org/keywords/theoretical-computer-science","display_name":"Theoretical computer science","score":0.42018458247184753},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3402404487133026}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5867700576782227},{"id":"https://openalex.org/C123657996","wikidata":"https://www.wikidata.org/wiki/Q12271","display_name":"Architecture","level":2,"score":0.5551198720932007},{"id":"https://openalex.org/C132525143","wikidata":"https://www.wikidata.org/wiki/Q141488","display_name":"Graph","level":2,"score":0.5210477709770203},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.42018458247184753},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3402404487133026},{"id":"https://openalex.org/C142362112","wikidata":"https://www.wikidata.org/wiki/Q735","display_name":"Art","level":0,"score":0.0},{"id":"https://openalex.org/C153349607","wikidata":"https://www.wikidata.org/wiki/Q36649","display_name":"Visual arts","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.32604/cmc.2025.064969","is_oa":true,"landing_page_url":"https://doi.org/10.32604/cmc.2025.064969","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.2025.064969","is_oa":true,"landing_page_url":"https://doi.org/10.32604/cmc.2025.064969","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":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":20,"referenced_works":["https://openalex.org/W2001141328","https://openalex.org/W2053186076","https://openalex.org/W2100659887","https://openalex.org/W2112796928","https://openalex.org/W2116341502","https://openalex.org/W2117539524","https://openalex.org/W2152825437","https://openalex.org/W2294798173","https://openalex.org/W2618999197","https://openalex.org/W2889326414","https://openalex.org/W2968898024","https://openalex.org/W3002669799","https://openalex.org/W3006432778","https://openalex.org/W3024880312","https://openalex.org/W3045164669","https://openalex.org/W3116202926","https://openalex.org/W3137525302","https://openalex.org/W3164107346","https://openalex.org/W4313149554","https://openalex.org/W4390753745"],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2899084033","https://openalex.org/W2748952813","https://openalex.org/W2390279801","https://openalex.org/W4391913857","https://openalex.org/W2358668433","https://openalex.org/W4396701345","https://openalex.org/W2376932109","https://openalex.org/W2001405890","https://openalex.org/W4396696052"],"abstract_inverted_index":{"Neural":[0],"architecture":[1,68],"search":[2,45,203],"(NAS)":[3],"optimizes":[4],"neural":[5],"network":[6],"architectures":[7,82,89,171],"to":[8,64,84,122,176],"align":[9],"with":[10],"specific":[11],"data":[12],"and":[13,38,165,192,205],"objectives,":[14],"thereby":[15],"enabling":[16],"the":[17,53,66,70,95,158,167,185],"design":[18,168],"of":[19,29,56,169,211],"high-performance":[20],"models":[21],"without":[22],"specialized":[23],"expertise.":[24],"However,":[25],"a":[26,42,77,99,162],"significant":[27],"limitation":[28],"NAS":[30,104,147],"is":[31,50,60,105],"that":[32,80,90,198],"it":[33,142],"requires":[34],"extensive":[35],"computational":[36],"resources":[37],"time.":[39],"Consequently,":[40],"performing":[41],"comprehensive":[43],"architectural":[44],"for":[46,69,145,172],"each":[47],"new":[48],"dataset":[49,97,191],"inefficient.":[51],"Given":[52],"continuous":[54],"expansion":[55],"available":[57],"datasets,":[58],"there":[59],"an":[61,113],"urgent":[62],"need":[63],"predict":[65],"optimal":[67,170],"previously":[71],"unknown":[72,85],"datasets.":[73,174],"This":[74],"study":[75],"proposes":[76],"novel":[78],"framework":[79],"generates":[81],"tailored":[83],"datasets":[86],"by":[87,188],"mapping":[88,146],"have":[91],"demonstrated":[92],"effectiveness":[93],"on":[94,118,154],"existing":[96,155],"into":[98],"latent":[100,125,163,186],"feature":[101,126],"space.":[102],"As":[103],"inherently":[106],"represented":[107],"as":[108],"graph":[109,120,139,152],"structures,":[110,140],"we":[111,182],"employed":[112],"encoder-decoder":[114,129],"transformation":[115,130],"model":[116,131,212],"based":[117],"variational":[119,151],"auto-encoders":[121,153],"perform":[123],"this":[124],"mapping.":[127],"The":[128],"demonstrates":[132],"strong":[133],"capability":[134],"in":[135,209],"extracting":[136],"features":[137],"from":[138],"making":[141],"particularly":[143],"well-suited":[144],"architectures.":[148],"By":[149],"training":[150],"high-quality":[156],"architectures,":[157,181],"proposed":[159],"method":[160],"constructs":[161],"space":[164,187],"facilitates":[166],"diverse":[173],"Furthermore,":[175],"effectively":[177],"define":[178],"similarity":[179],"among":[180],"propose":[183],"constructing":[184],"incorporating":[189],"both":[190],"task":[193],"features.":[194],"Experimental":[195],"results":[196],"indicate":[197],"our":[199],"approach":[200],"significantly":[201],"enhances":[202],"efficiency":[204],"outperforms":[206],"conventional":[207],"methods":[208],"terms":[210],"performance.":[213]},"counts_by_year":[],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}