{"id":"https://openalex.org/W6929518020","doi":"https://doi.org/10.48550/arxiv.2508.09467","title":"Learn to Explore: Meta NAS via Bayesian Optimization Guided Graph Generation","display_name":"Learn to Explore: Meta NAS via Bayesian Optimization Guided Graph Generation","publication_year":2025,"publication_date":"2025-08-13","ids":{"openalex":"https://openalex.org/W6929518020","doi":"https://doi.org/10.48550/arxiv.2508.09467"},"language":"en","primary_location":{"id":"doi:10.48550/arxiv.2508.09467","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2508.09467","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,"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":null,"raw_type":"Preprint"},"type":"preprint","indexed_in":["datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://doi.org/10.48550/arxiv.2508.09467","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":null,"display_name":"Sun, Zijun","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Sun, Zijun","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":null,"display_name":"Shen, Yanning","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Shen, Yanning","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":1,"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":true,"primary_topic":{"id":"https://openalex.org/T10071","display_name":"Bone health and osteoporosis research","score":0.14309999346733093,"subfield":{"id":"https://openalex.org/subfields/2732","display_name":"Orthopedics and Sports Medicine"},"field":{"id":"https://openalex.org/fields/27","display_name":"Medicine"},"domain":{"id":"https://openalex.org/domains/4","display_name":"Health Sciences"}},"topics":[{"id":"https://openalex.org/T10071","display_name":"Bone health and osteoporosis research","score":0.14309999346733093,"subfield":{"id":"https://openalex.org/subfields/2732","display_name":"Orthopedics and Sports Medicine"},"field":{"id":"https://openalex.org/fields/27","display_name":"Medicine"},"domain":{"id":"https://openalex.org/domains/4","display_name":"Health Sciences"}},{"id":"https://openalex.org/T13453","display_name":"Alkaline Phosphatase Research Studies","score":0.06469999998807907,"subfield":{"id":"https://openalex.org/subfields/2712","display_name":"Endocrinology, Diabetes and Metabolism"},"field":{"id":"https://openalex.org/fields/27","display_name":"Medicine"},"domain":{"id":"https://openalex.org/domains/4","display_name":"Health Sciences"}},{"id":"https://openalex.org/T11363","display_name":"Dental Radiography and Imaging","score":0.03750000149011612,"subfield":{"id":"https://openalex.org/subfields/3504","display_name":"Oral Surgery"},"field":{"id":"https://openalex.org/fields/35","display_name":"Dentistry"},"domain":{"id":"https://openalex.org/domains/4","display_name":"Health Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.5371000170707703},{"id":"https://openalex.org/keywords/search-algorithm","display_name":"Search algorithm","score":0.454800009727478},{"id":"https://openalex.org/keywords/bayesian-optimization","display_name":"Bayesian optimization","score":0.4185999929904938},{"id":"https://openalex.org/keywords/generalization","display_name":"Generalization","score":0.41190001368522644},{"id":"https://openalex.org/keywords/bayesian-network","display_name":"Bayesian network","score":0.4088999927043915},{"id":"https://openalex.org/keywords/beam-search","display_name":"Beam search","score":0.39989998936653137},{"id":"https://openalex.org/keywords/graph","display_name":"Graph","score":0.36980000138282776},{"id":"https://openalex.org/keywords/bayesian-probability","display_name":"Bayesian probability","score":0.36820000410079956}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7429999709129333},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6503999829292297},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.5741000175476074},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.5371000170707703},{"id":"https://openalex.org/C125583679","wikidata":"https://www.wikidata.org/wiki/Q755673","display_name":"Search algorithm","level":2,"score":0.454800009727478},{"id":"https://openalex.org/C2778049539","wikidata":"https://www.wikidata.org/wiki/Q17002908","display_name":"Bayesian optimization","level":2,"score":0.4185999929904938},{"id":"https://openalex.org/C177148314","wikidata":"https://www.wikidata.org/wiki/Q170084","display_name":"Generalization","level":2,"score":0.41190001368522644},{"id":"https://openalex.org/C33724603","wikidata":"https://www.wikidata.org/wiki/Q812540","display_name":"Bayesian network","level":2,"score":0.4088999927043915},{"id":"https://openalex.org/C19889080","wikidata":"https://www.wikidata.org/wiki/Q2835852","display_name":"Beam search","level":3,"score":0.39989998936653137},{"id":"https://openalex.org/C132525143","wikidata":"https://www.wikidata.org/wiki/Q141488","display_name":"Graph","level":2,"score":0.36980000138282776},{"id":"https://openalex.org/C107673813","wikidata":"https://www.wikidata.org/wiki/Q812534","display_name":"Bayesian probability","level":2,"score":0.36820000410079956},{"id":"https://openalex.org/C139807058","wikidata":"https://www.wikidata.org/wiki/Q352374","display_name":"Adaptation (eye)","level":2,"score":0.3529999852180481},{"id":"https://openalex.org/C2984842247","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep neural networks","level":3,"score":0.34310001134872437},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.31949999928474426},{"id":"https://openalex.org/C123657996","wikidata":"https://www.wikidata.org/wiki/Q12271","display_name":"Architecture","level":2,"score":0.31380000710487366},{"id":"https://openalex.org/C153258448","wikidata":"https://www.wikidata.org/wiki/Q1199743","display_name":"Gradient descent","level":3,"score":0.3127000033855438},{"id":"https://openalex.org/C135320971","wikidata":"https://www.wikidata.org/wiki/Q1868524","display_name":"Local search (optimization)","level":2,"score":0.3043999969959259},{"id":"https://openalex.org/C135450995","wikidata":"https://www.wikidata.org/wiki/Q820272","display_name":"Hill climbing","level":2,"score":0.28029999136924744},{"id":"https://openalex.org/C147168706","wikidata":"https://www.wikidata.org/wiki/Q1457734","display_name":"Recurrent neural network","level":3,"score":0.2517000138759613},{"id":"https://openalex.org/C109718341","wikidata":"https://www.wikidata.org/wiki/Q1385229","display_name":"Metaheuristic","level":2,"score":0.2508000135421753}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.48550/arxiv.2508.09467","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2508.09467","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,"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":null,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"doi:10.48550/arxiv.2508.09467","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2508.09467","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,"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":null,"raw_type":"Preprint"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/1","score":0.4172961413860321,"display_name":"No poverty"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Neural":[0,27],"Architecture":[1,28],"Search":[2,29],"(NAS)":[3],"automates":[4],"the":[5,115,129,148],"design":[6],"of":[7],"high-performing":[8],"neural":[9,80,102,123],"networks":[10,124],"but":[11],"typically":[12],"targets":[13],"a":[14,34,71,86,133],"single":[15],"predefined":[16,149],"task,":[17],"thereby":[18],"restricting":[19],"its":[20],"real-world":[21],"applicability.":[22],"To":[23],"address":[24],"this,":[25],"Meta":[26],"(Meta-NAS)":[30],"has":[31],"emerged":[32],"as":[33,82],"promising":[35,101],"paradigm":[36],"that":[37,98,155],"leverages":[38],"prior":[39],"knowledge":[40],"across":[41],"tasks":[42],"to":[43,47,92,100,139],"enable":[44],"rapid":[45],"adaptation":[46],"new":[48,96],"ones.":[49],"Nevertheless,":[50],"existing":[51],"Meta-NAS":[52,73,159],"methods":[53],"often":[54],"struggle":[55],"with":[56,118,143],"poor":[57],"generalization,":[58],"limited":[59],"search":[60,88,105,110,116,135,150,165],"spaces,":[61],"or":[62],"high":[63],"computational":[64],"costs.":[65],"In":[66],"this":[67],"paper,":[68],"we":[69],"propose":[70],"novel":[72,122],"framework,":[74],"GraB-NAS.":[75],"Specifically,":[76],"GraB-NAS":[77,138,156],"first":[78],"models":[79],"architectures":[81,142],"graphs,":[83],"and":[84,94,164],"then":[85],"hybrid":[87,134],"strategy":[89,106,136],"is":[90],"developed":[91],"find":[93],"generate":[95],"graphs":[97],"lead":[99],"architectures.":[103],"The":[104],"combines":[107],"global":[108],"architecture":[109],"via":[111,125],"Bayesian":[112],"Optimization":[113],"in":[114,128],"space":[117],"local":[119],"exploration":[120],"for":[121],"gradient":[126],"ascent":[127],"latent":[130],"space.":[131,151],"Such":[132],"allows":[137],"discover":[140],"task-aware":[141],"strong":[144],"performance,":[145],"even":[146],"beyond":[147],"Extensive":[152],"experiments":[153],"demonstrate":[154],"outperforms":[157],"state-of-the-art":[158],"baselines,":[160],"achieving":[161],"better":[162],"generalization":[163],"effectiveness.":[166]},"counts_by_year":[{"year":2025,"cited_by_count":1}],"updated_date":"2026-07-28T07:46:37.118299","created_date":"2025-10-10T00:00:00"}