{"id":"https://openalex.org/W4414209643","doi":"https://doi.org/10.1145/3731545.3731587","title":"Weight-Sharing NAS with Architecture-Agnostic Intermediate Representation","display_name":"Weight-Sharing NAS with Architecture-Agnostic Intermediate Representation","publication_year":2025,"publication_date":"2025-07-20","ids":{"openalex":"https://openalex.org/W4414209643","doi":"https://doi.org/10.1145/3731545.3731587"},"language":"en","primary_location":{"id":"doi:10.1145/3731545.3731587","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3731545.3731587","pdf_url":null,"source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 34th International Symposium on High-Performance Parallel and Distributed Computing","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://doi.org/10.1145/3731545.3731587","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5085171738","display_name":"Sixing Yu","orcid":"https://orcid.org/0000-0002-2415-566X"},"institutions":[{"id":"https://openalex.org/I173911158","display_name":"Iowa State University","ror":"https://ror.org/04rswrd78","country_code":"US","type":"education","lineage":["https://openalex.org/I173911158"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Sixing Yu","raw_affiliation_strings":["Department of Computer Science, Iowa State University, Ames, USA"],"raw_orcid":"https://orcid.org/0000-0002-2415-566X","affiliations":[{"raw_affiliation_string":"Department of Computer Science, Iowa State University, Ames, USA","institution_ids":["https://openalex.org/I173911158"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5028887858","display_name":"Arya Mazaheri","orcid":"https://orcid.org/0000-0002-5671-4710"},"institutions":[{"id":"https://openalex.org/I31512782","display_name":"Technische Universit\u00e4t Darmstadt","ror":"https://ror.org/05n911h24","country_code":"DE","type":"education","lineage":["https://openalex.org/I31512782"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Arya Mazaheri","raw_affiliation_strings":["Technical University of Darmstadt, Darmstadt, Germany"],"raw_orcid":"https://orcid.org/0000-0002-5671-4710","affiliations":[{"raw_affiliation_string":"Technical University of Darmstadt, Darmstadt, Germany","institution_ids":["https://openalex.org/I31512782"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5079359777","display_name":"Ali Jannesari","orcid":"https://orcid.org/0000-0001-8672-5317"},"institutions":[{"id":"https://openalex.org/I173911158","display_name":"Iowa State University","ror":"https://ror.org/04rswrd78","country_code":"US","type":"education","lineage":["https://openalex.org/I173911158"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Ali Jannesari","raw_affiliation_strings":["Department of Computer Science, Iowa State University, Ames, USA"],"raw_orcid":"https://orcid.org/0000-0001-8672-5317","affiliations":[{"raw_affiliation_string":"Department of Computer Science, Iowa State University, Ames, USA","institution_ids":["https://openalex.org/I173911158"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.11470476,"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":"13"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10215","display_name":"Semantic Web and Ontologies","score":0.9805999994277954,"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/T10215","display_name":"Semantic Web and Ontologies","score":0.9805999994277954,"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/T10679","display_name":"Service-Oriented Architecture and Web Services","score":0.9794999957084656,"subfield":{"id":"https://openalex.org/subfields/1710","display_name":"Information Systems"},"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/T12127","display_name":"Software System Performance and Reliability","score":0.9635999798774719,"subfield":{"id":"https://openalex.org/subfields/1705","display_name":"Computer Networks and Communications"},"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/executable","display_name":"Executable","score":0.7300999760627747},{"id":"https://openalex.org/keywords/subnet","display_name":"Subnet","score":0.5202000141143799},{"id":"https://openalex.org/keywords/boosting","display_name":"Boosting (machine learning)","score":0.47189998626708984},{"id":"https://openalex.org/keywords/graph","display_name":"Graph","score":0.44859999418258667},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.3447999954223633},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.3425999879837036},{"id":"https://openalex.org/keywords/latency","display_name":"Latency (audio)","score":0.3334999978542328},{"id":"https://openalex.org/keywords/architecture","display_name":"Architecture","score":0.3212999999523163}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8115000128746033},{"id":"https://openalex.org/C160145156","wikidata":"https://www.wikidata.org/wiki/Q778586","display_name":"Executable","level":2,"score":0.7300999760627747},{"id":"https://openalex.org/C21099817","wikidata":"https://www.wikidata.org/wiki/Q7631721","display_name":"Subnet","level":2,"score":0.5202000141143799},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.47749999165534973},{"id":"https://openalex.org/C46686674","wikidata":"https://www.wikidata.org/wiki/Q466303","display_name":"Boosting (machine learning)","level":2,"score":0.47189998626708984},{"id":"https://openalex.org/C132525143","wikidata":"https://www.wikidata.org/wiki/Q141488","display_name":"Graph","level":2,"score":0.44859999418258667},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.4099000096321106},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3589000105857849},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.3447999954223633},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.3425999879837036},{"id":"https://openalex.org/C82876162","wikidata":"https://www.wikidata.org/wiki/Q17096504","display_name":"Latency (audio)","level":2,"score":0.3334999978542328},{"id":"https://openalex.org/C113775141","wikidata":"https://www.wikidata.org/wiki/Q428691","display_name":"Computer engineering","level":1,"score":0.3246999979019165},{"id":"https://openalex.org/C123657996","wikidata":"https://www.wikidata.org/wiki/Q12271","display_name":"Architecture","level":2,"score":0.3212999999523163},{"id":"https://openalex.org/C156884757","wikidata":"https://www.wikidata.org/wiki/Q798554","display_name":"Backtracking","level":2,"score":0.3149999976158142},{"id":"https://openalex.org/C41608201","wikidata":"https://www.wikidata.org/wiki/Q980509","display_name":"Embedding","level":2,"score":0.3093000054359436},{"id":"https://openalex.org/C36503486","wikidata":"https://www.wikidata.org/wiki/Q11235244","display_name":"Domain (mathematical analysis)","level":2,"score":0.30889999866485596},{"id":"https://openalex.org/C147764199","wikidata":"https://www.wikidata.org/wiki/Q6865248","display_name":"Minification","level":2,"score":0.30230000615119934},{"id":"https://openalex.org/C3826847","wikidata":"https://www.wikidata.org/wiki/Q188768","display_name":"FLOPS","level":2,"score":0.29809999465942383},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.290800005197525},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.27239999175071716},{"id":"https://openalex.org/C118524514","wikidata":"https://www.wikidata.org/wiki/Q173212","display_name":"Computer architecture","level":1,"score":0.2635999917984009},{"id":"https://openalex.org/C43126263","wikidata":"https://www.wikidata.org/wiki/Q128751","display_name":"Source code","level":2,"score":0.262800008058548},{"id":"https://openalex.org/C59404180","wikidata":"https://www.wikidata.org/wiki/Q17013334","display_name":"Feature learning","level":2,"score":0.26010000705718994},{"id":"https://openalex.org/C118505674","wikidata":"https://www.wikidata.org/wiki/Q42586063","display_name":"Encoder","level":2,"score":0.2551000118255615},{"id":"https://openalex.org/C2776760102","wikidata":"https://www.wikidata.org/wiki/Q5139990","display_name":"Code (set theory)","level":3,"score":0.2549999952316284},{"id":"https://openalex.org/C133162039","wikidata":"https://www.wikidata.org/wiki/Q1061077","display_name":"Code generation","level":3,"score":0.2524000108242035}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3731545.3731587","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3731545.3731587","pdf_url":null,"source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 34th International Symposium on High-Performance Parallel and Distributed Computing","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.1145/3731545.3731587","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3731545.3731587","pdf_url":null,"source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 34th International Symposium on High-Performance Parallel and Distributed Computing","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G2397154826","display_name":null,"funder_award_id":"2243775 and\uc2a02211982","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"}],"funders":[{"id":"https://openalex.org/F4320306076","display_name":"National Science Foundation","ror":"https://ror.org/021nxhr62"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":16,"referenced_works":["https://openalex.org/W2108598243","https://openalex.org/W2750779823","https://openalex.org/W2946609015","https://openalex.org/W2953604046","https://openalex.org/W3107893198","https://openalex.org/W3121523901","https://openalex.org/W3201174429","https://openalex.org/W3202742610","https://openalex.org/W3204801262","https://openalex.org/W3205652345","https://openalex.org/W4226437046","https://openalex.org/W4312340826","https://openalex.org/W4312349930","https://openalex.org/W4312772337","https://openalex.org/W4387746080","https://openalex.org/W4387910965"],"related_works":[],"abstract_inverted_index":{"Weight-sharing":[0],"supernet":[1,45,116],"has":[2],"been":[3],"widely":[4],"adopted":[5],"in":[6,198,202],"Neural":[7],"Architecture":[8],"Search":[9],"(NAS)":[10],"as":[11],"a":[12,44,50,86,121,135,199],"promising":[13,128],"strategy":[14,123],"to":[15,29],"obtain":[16],"smaller":[17],"and":[18,37,42,69,105,133,172,180,204],"more":[19],"efficient":[20],"high-performance":[21],"models.":[22],"However,":[23],"constructing":[24],"supernets":[25,104,165],"requires":[26],"domain":[27],"expertise":[28],"design":[30],"architecture-specific":[31],"rules":[32,34],"(e.g.,":[33],"for":[35,39,184],"CNNs":[36],"Transformers)":[38],"generating":[40],"subnets,":[41,55],"training":[43,117,138,149],"demands":[46],"joint":[47],"optimization":[48],"over":[49],"vast":[51],"sample":[52],"space":[53],"of":[54,98,101,108,150],"which":[56],"is":[57],"computationally":[58],"expensive.":[59],"This":[60],"paper":[61],"presents":[62],"OSF":[63,162,188],"(Optimized":[64],"Supernet":[65],"Formation),":[66],"an":[67],"automated":[68],"architecture-agnostic":[70],"approach":[71,139],"that":[72,93,124,143,161],"transforms":[73],"predefined/pretrained":[74],"models":[75,102],"into":[76,103],"weight-sharing":[77],"supernets.":[78],"Specifically,":[79],"we":[80,119],"propose":[81,134],"representing":[82],"neural":[83],"architectures":[84,153,168],"using":[85],"high-level":[87],"computational":[88],"graph":[89,112],"intermediate":[90],"representation":[91],"(IR)":[92],"enables":[94],"both":[95],"the":[96,106,126,195],"conversion":[97],"different":[99],"types":[100],"extraction":[107],"executable":[109],"subnets":[110],"via":[111],"traversal.":[113],"To":[114],"improve":[115],"efficiency,":[118],"introduce":[120],"sampling":[122],"prioritizes":[125],"most":[127],"subnet":[129,152],"candidates":[130],"during":[131],"training,":[132],"fork-join":[136],"parallel":[137],"with":[140,154],"gradient":[141],"accumulation":[142],"resolves":[144],"write-after-write":[145],"dependencies,":[146],"enabling":[147],"concurrent":[148],"multiple":[151],"shared":[155],"weights.":[156],"Our":[157],"empirical":[158],"evaluations":[159],"demonstrate":[160],"successfully":[163],"builds":[164],"from":[166],"various":[167],"(CNNs,":[169],"Transformers,":[170],"SSMs,":[171],"MLPs)":[173],"while":[174,193],"achieving":[175],"superior":[176],"performance":[177],"across":[178],"language":[179],"vision":[181],"benchmarks.":[182],"Notably,":[183],"Vision":[185],"Transformers":[186],"(ViT),":[187],"reduces":[189],"FLOPs":[190],"by":[191],"49%":[192],"maintaining":[194],"accuracy,":[196],"resulting":[197],"155%":[200],"increase":[201],"throughput":[203],"35%":[205],"latency":[206],"reduction.":[207],"Code":[208],"Open-sourced":[209],"at:":[210],"https://github.com/yusx-swapp/OSF":[211]},"counts_by_year":[],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}