{"id":"https://openalex.org/W4402979732","doi":"https://doi.org/10.1109/icme57554.2024.10688064","title":"Training-free Neural Architectural Search on Transformer via Evaluating Expressivity and Trainability","display_name":"Training-free Neural Architectural Search on Transformer via Evaluating Expressivity and Trainability","publication_year":2024,"publication_date":"2024-07-15","ids":{"openalex":"https://openalex.org/W4402979732","doi":"https://doi.org/10.1109/icme57554.2024.10688064"},"language":"en","primary_location":{"id":"doi:10.1109/icme57554.2024.10688064","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1109/icme57554.2024.10688064","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 Multimedia and Expo (ICME)","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/A5091075435","display_name":"Y. Z. Fan","orcid":"https://orcid.org/0000-0002-9039-719X"},"institutions":[{"id":"https://openalex.org/I881766915","display_name":"Nanjing University","ror":"https://ror.org/01rxvg760","country_code":"CN","type":"education","lineage":["https://openalex.org/I881766915"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Yi Fan","raw_affiliation_strings":["Nanjing University,State Key Laboratory for Novel Software Technology,Nanjing,China"],"affiliations":[{"raw_affiliation_string":"Nanjing University,State Key Laboratory for Novel Software Technology,Nanjing,China","institution_ids":["https://openalex.org/I881766915"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5101439866","display_name":"Yu-Bin Yang","orcid":null},"institutions":[{"id":"https://openalex.org/I881766915","display_name":"Nanjing University","ror":"https://ror.org/01rxvg760","country_code":"CN","type":"education","lineage":["https://openalex.org/I881766915"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yu-Bin Yang","raw_affiliation_strings":["Nanjing University,State Key Laboratory for Novel Software Technology,Nanjing,China"],"affiliations":[{"raw_affiliation_string":"Nanjing University,State Key Laboratory for Novel Software Technology,Nanjing,China","institution_ids":["https://openalex.org/I881766915"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5091075435"],"corresponding_institution_ids":["https://openalex.org/I881766915"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.22255489,"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":"6"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12111","display_name":"Industrial Vision Systems and Defect Detection","score":0.942799985408783,"subfield":{"id":"https://openalex.org/subfields/2209","display_name":"Industrial and Manufacturing Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},"topics":[{"id":"https://openalex.org/T12111","display_name":"Industrial Vision Systems and Defect Detection","score":0.942799985408783,"subfield":{"id":"https://openalex.org/subfields/2209","display_name":"Industrial and Manufacturing Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T10320","display_name":"Neural Networks and Applications","score":0.9254000186920166,"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":0.6706040501594543},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6256505250930786},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.4387659430503845},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3652914762496948},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.1970011591911316},{"id":"https://openalex.org/keywords/electrical-engineering","display_name":"Electrical engineering","score":0.1194782555103302},{"id":"https://openalex.org/keywords/voltage","display_name":"Voltage","score":0.0610654354095459}],"concepts":[{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.6706040501594543},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6256505250930786},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.4387659430503845},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3652914762496948},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.1970011591911316},{"id":"https://openalex.org/C119599485","wikidata":"https://www.wikidata.org/wiki/Q43035","display_name":"Electrical engineering","level":1,"score":0.1194782555103302},{"id":"https://openalex.org/C165801399","wikidata":"https://www.wikidata.org/wiki/Q25428","display_name":"Voltage","level":2,"score":0.0610654354095459}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icme57554.2024.10688064","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1109/icme57554.2024.10688064","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 Multimedia and Expo (ICME)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.4099999964237213,"display_name":"Sustainable cities and communities","id":"https://metadata.un.org/sdg/11"}],"awards":[],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2748952813","https://openalex.org/W2390279801","https://openalex.org/W2358668433","https://openalex.org/W4396701345","https://openalex.org/W2376932109","https://openalex.org/W2001405890","https://openalex.org/W4396696052","https://openalex.org/W2382290278","https://openalex.org/W4395014643"],"abstract_inverted_index":{"Recently,":[0],"training-free":[1,29,68],"Neural":[2,18],"Architecture":[3],"Search":[4],"(NAS)":[5],"methods":[6,39],"have":[7],"proven":[8],"to":[9,26,88,102],"be":[10],"effective":[11],"and":[12,91,98,118,138],"efficient":[13],"in":[14,33,94,123],"searching":[15],"for":[16,73],"Convolutional":[17],"Networks":[19],"(CNN)":[20],"architectures.":[21],"However,":[22],"when":[23],"it":[24],"comes":[25],"Transformer-based":[27,74],"models,":[28,48,51],"NAS":[30,69],"is":[31],"still":[32],"its":[34],"early":[35],"stages,":[36],"with":[37],"limited":[38],"available.":[40],"Existing":[41],"approaches":[42],"either":[43],"focus":[44],"solely":[45],"on":[46,116,136,140],"language":[47],"neglecting":[49],"visual":[50,75],"or":[52],"overlook":[53],"the":[54,80,92,112,119],"core":[55],"component":[56],"of":[57,85,134],"Transformers,":[58],"attention":[59,83,95],"map.":[60],"In":[61],"this":[62],"paper,":[63],"we":[64],"propose":[65],"a":[66,108,130],"novel":[67],"method":[70,78],"specifically":[71],"designed":[72],"models.":[76],"Our":[77],"utilizes":[79],"distance":[81],"between":[82,111],"maps":[84,96],"different":[86],"samples":[87],"measure":[89,103],"expressivity,":[90],"difference":[93],"before":[97],"after":[99],"one":[100],"iteration":[101],"trainability.":[104],"Experimental":[105],"results":[106,128],"demonstrate":[107],"strong":[109],"correlation":[110],"top-1":[113,131],"classification":[114,132],"accuracy":[115,133],"ImageNet-1K":[117],"proxy":[120],"metric":[121],"used":[122],"our":[124],"method.":[125],"The":[126],"search":[127],"achieve":[129],"82.9%":[135],"AutoFormer":[137],"80.8%":[139],"PIT.":[141]},"counts_by_year":[],"updated_date":"2025-12-21T23:12:01.093139","created_date":"2025-10-10T00:00:00"}