{"id":"https://openalex.org/W4416251134","doi":"https://doi.org/10.1109/ijcnn64981.2025.11229357","title":"Generalization-Aware Zero-Shot Neural Architecture Search for Self-Supervised Transformers","display_name":"Generalization-Aware Zero-Shot Neural Architecture Search for Self-Supervised Transformers","publication_year":2025,"publication_date":"2025-06-30","ids":{"openalex":"https://openalex.org/W4416251134","doi":"https://doi.org/10.1109/ijcnn64981.2025.11229357"},"language":null,"primary_location":{"id":"doi:10.1109/ijcnn64981.2025.11229357","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ijcnn64981.2025.11229357","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 International Joint Conference on Neural Networks (IJCNN)","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/A5029763295","display_name":"Jun-Hua Ko","orcid":null},"institutions":[{"id":"https://openalex.org/I16733864","display_name":"National Taiwan University","ror":"https://ror.org/05bqach95","country_code":"TW","type":"education","lineage":["https://openalex.org/I16733864"]}],"countries":["TW"],"is_corresponding":true,"raw_author_name":"Jun-Hua Ko","raw_affiliation_strings":["National Taiwan University,Taipei,Taiwan"],"affiliations":[{"raw_affiliation_string":"National Taiwan University,Taipei,Taiwan","institution_ids":["https://openalex.org/I16733864"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5064876889","display_name":"Tzi\u2010Dar Chiueh","orcid":"https://orcid.org/0000-0003-0851-6629"},"institutions":[{"id":"https://openalex.org/I16733864","display_name":"National Taiwan University","ror":"https://ror.org/05bqach95","country_code":"TW","type":"education","lineage":["https://openalex.org/I16733864"]}],"countries":["TW"],"is_corresponding":false,"raw_author_name":"Tzi-Dar Chiueh","raw_affiliation_strings":["National Taiwan University,Taipei,Taiwan"],"affiliations":[{"raw_affiliation_string":"National Taiwan University,Taipei,Taiwan","institution_ids":["https://openalex.org/I16733864"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5029763295"],"corresponding_institution_ids":["https://openalex.org/I16733864"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.18259371,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"8"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11307","display_name":"Domain Adaptation and Few-Shot Learning","score":0.3375000059604645,"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/T11307","display_name":"Domain Adaptation and Few-Shot Learning","score":0.3375000059604645,"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":0.2696000039577484,"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/T11273","display_name":"Advanced Graph Neural Networks","score":0.08889999985694885,"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/transformer","display_name":"Transformer","score":0.5755000114440918},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.5467000007629395},{"id":"https://openalex.org/keywords/architecture","display_name":"Architecture","score":0.4884999990463257},{"id":"https://openalex.org/keywords/generalization","display_name":"Generalization","score":0.4187999963760376},{"id":"https://openalex.org/keywords/deep-neural-networks","display_name":"Deep neural networks","score":0.36640000343322754},{"id":"https://openalex.org/keywords/deep-learning","display_name":"Deep learning","score":0.3571999967098236},{"id":"https://openalex.org/keywords/training-set","display_name":"Training set","score":0.3515999913215637}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7354000210762024},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5802000164985657},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.5755000114440918},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.5601999759674072},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.5467000007629395},{"id":"https://openalex.org/C123657996","wikidata":"https://www.wikidata.org/wiki/Q12271","display_name":"Architecture","level":2,"score":0.4884999990463257},{"id":"https://openalex.org/C177148314","wikidata":"https://www.wikidata.org/wiki/Q170084","display_name":"Generalization","level":2,"score":0.4187999963760376},{"id":"https://openalex.org/C2984842247","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep neural networks","level":3,"score":0.36640000343322754},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.3571999967098236},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.3515999913215637},{"id":"https://openalex.org/C136389625","wikidata":"https://www.wikidata.org/wiki/Q334384","display_name":"Supervised learning","level":3,"score":0.3375000059604645},{"id":"https://openalex.org/C2776145971","wikidata":"https://www.wikidata.org/wiki/Q30673951","display_name":"Labeled data","level":2,"score":0.3237000107765198},{"id":"https://openalex.org/C195324797","wikidata":"https://www.wikidata.org/wiki/Q33742","display_name":"Natural language","level":2,"score":0.3197000026702881},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.26499998569488525},{"id":"https://openalex.org/C27158222","wikidata":"https://www.wikidata.org/wiki/Q5532422","display_name":"Generalizability theory","level":2,"score":0.2624000012874603},{"id":"https://openalex.org/C2780148112","wikidata":"https://www.wikidata.org/wiki/Q1432581","display_name":"Proxy (statistics)","level":2,"score":0.2612999975681305},{"id":"https://openalex.org/C160920958","wikidata":"https://www.wikidata.org/wiki/Q7662746","display_name":"Synthetic data","level":2,"score":0.2599000036716461},{"id":"https://openalex.org/C47487241","wikidata":"https://www.wikidata.org/wiki/Q5227230","display_name":"Data access","level":2,"score":0.25}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/ijcnn64981.2025.11229357","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ijcnn64981.2025.11229357","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 International Joint Conference on Neural Networks (IJCNN)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320331164","display_name":"National Science and Technology Council","ror":"https://ror.org/00wnb9798"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":20,"referenced_works":["https://openalex.org/W2108598243","https://openalex.org/W2507296351","https://openalex.org/W2884822772","https://openalex.org/W2963918968","https://openalex.org/W3035524453","https://openalex.org/W3040743533","https://openalex.org/W3096533519","https://openalex.org/W3138516171","https://openalex.org/W3175049034","https://openalex.org/W3204801262","https://openalex.org/W4214513763","https://openalex.org/W4226095806","https://openalex.org/W4312312750","https://openalex.org/W4312617935","https://openalex.org/W4313047844","https://openalex.org/W4313156423","https://openalex.org/W4386071640","https://openalex.org/W4392940376","https://openalex.org/W4396523227","https://openalex.org/W4400811569"],"related_works":[],"abstract_inverted_index":{"Neural":[0],"Architecture":[1],"Search":[2],"(NAS)":[3],"aims":[4],"to":[5,70,157],"automate":[6],"the":[7,13,71,132,136,143,151],"design":[8],"of":[9,15,74],"neural":[10],"networks,":[11],"enabling":[12],"discovery":[14],"highly":[16],"effective":[17],"architectures.":[18],"Recent":[19],"advancements":[20],"in":[21,27,65,89],"NAS":[22,42],"have":[23],"shown":[24],"significant":[25],"success":[26],"identifying":[28],"high-performing":[29],"Transformer":[30],"architectures":[31,121,133],"for":[32],"computer":[33],"vision":[34],"and":[35,126,145,159],"natural":[36],"language":[37],"processing":[38],"tasks.":[39],"However,":[40],"most":[41],"research":[43],"has":[44],"focused":[45],"on":[46,53,58,107,142],"supervised":[47],"learning":[48],"frameworks,":[49],"which":[50],"rely":[51],"heavily":[52],"labeled":[54,59,93,153],"data.":[55,94],"This":[56],"dependence":[57],"data":[60,75,154],"makes":[61],"deploying":[62],"these":[63,97],"methods":[64],"real-world":[66],"applications":[67],"challenging":[68],"due":[69],"high":[72],"cost":[73],"annotation.":[76],"Additionally,":[77],"previous":[78],"studies":[79],"often":[80],"prioritize":[81],"model":[82],"performance":[83,141],"while":[84,148],"neglecting":[85],"generalization":[86,124],"ability,":[87],"particularly":[88],"scenarios":[90],"with":[91,114],"limited":[92],"To":[95],"address":[96],"challenges,":[98],"this":[99,112],"study":[100],"introduces":[101],"a":[102,115],"generalization-aware":[103],"zero-shot":[104,117],"proxy":[105,113],"based":[106],"self-supervised":[108],"learning.":[109],"By":[110],"combining":[111],"complementary":[116],"proxy,":[118],"we":[119],"identify":[120],"that":[122,131],"balance":[123],"ability":[125],"expressivity.":[127],"Experimental":[128],"results":[129],"demonstrate":[130],"discovered":[134],"using":[135],"proposed":[137],"approach":[138],"achieve":[139],"competitive":[140],"ImageNet":[144],"Wikitext-2":[146],"datasets":[147],"significantly":[149],"reducing":[150],"required":[152],"by":[155],"up":[156],"75%":[158],"99%,":[160],"respectively.":[161]},"counts_by_year":[],"updated_date":"2026-04-09T08:11:56.329763","created_date":"2025-11-14T00:00:00"}