{"id":"https://openalex.org/W7126054827","doi":"https://doi.org/10.1109/bibm66473.2025.11356902","title":"Toward Fair and Efficient Neural Architecture Search in Heterogeneous Federated Learning","display_name":"Toward Fair and Efficient Neural Architecture Search in Heterogeneous Federated Learning","publication_year":2025,"publication_date":"2025-12-15","ids":{"openalex":"https://openalex.org/W7126054827","doi":"https://doi.org/10.1109/bibm66473.2025.11356902"},"language":null,"primary_location":{"id":"doi:10.1109/bibm66473.2025.11356902","is_oa":false,"landing_page_url":"https://doi.org/10.1109/bibm66473.2025.11356902","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE International Conference on Bioinformatics and Biomedicine (BIBM)","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/A5109282581","display_name":"T. Hu","orcid":null},"institutions":[{"id":"https://openalex.org/I185261750","display_name":"University of Toronto","ror":"https://ror.org/03dbr7087","country_code":"CA","type":"education","lineage":["https://openalex.org/I185261750"]}],"countries":["CA"],"is_corresponding":true,"raw_author_name":"Xinyuan Huang","raw_affiliation_strings":["University of Toronto,Department of Computer Science,Toronto,Canada"],"affiliations":[{"raw_affiliation_string":"University of Toronto,Department of Computer Science,Toronto,Canada","institution_ids":["https://openalex.org/I185261750"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5012051562","display_name":"Jiechao Gao","orcid":"https://orcid.org/0000-0003-0628-1416"},"institutions":[{"id":"https://openalex.org/I97018004","display_name":"Stanford University","ror":"https://ror.org/00f54p054","country_code":"US","type":"education","lineage":["https://openalex.org/I97018004"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Jiechao Gao","raw_affiliation_strings":["Center for SDGC, Stanford University,Stanford,United States"],"affiliations":[{"raw_affiliation_string":"Center for SDGC, Stanford University,Stanford,United States","institution_ids":["https://openalex.org/I97018004"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5109282581"],"corresponding_institution_ids":["https://openalex.org/I185261750"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.87365957,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"7168","last_page":"7175"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10764","display_name":"Privacy-Preserving Technologies in Data","score":0.8436999917030334,"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/T10764","display_name":"Privacy-Preserving Technologies in Data","score":0.8436999917030334,"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/T11307","display_name":"Domain Adaptation and Few-Shot Learning","score":0.03139999881386757,"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/T13702","display_name":"Machine Learning in Healthcare","score":0.017000000923871994,"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/federated-learning","display_name":"Federated learning","score":0.8765000104904175},{"id":"https://openalex.org/keywords/pruning","display_name":"Pruning","score":0.7279000282287598},{"id":"https://openalex.org/keywords/convergence","display_name":"Convergence (economics)","score":0.5562999844551086},{"id":"https://openalex.org/keywords/architecture","display_name":"Architecture","score":0.48899999260902405},{"id":"https://openalex.org/keywords/distributed-learning","display_name":"Distributed learning","score":0.4462999999523163},{"id":"https://openalex.org/keywords/interoperability","display_name":"Interoperability","score":0.3898000121116638},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.37709999084472656},{"id":"https://openalex.org/keywords/differentiable-function","display_name":"Differentiable function","score":0.3499000072479248}],"concepts":[{"id":"https://openalex.org/C2992525071","wikidata":"https://www.wikidata.org/wiki/Q50818671","display_name":"Federated learning","level":2,"score":0.8765000104904175},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8267999887466431},{"id":"https://openalex.org/C108010975","wikidata":"https://www.wikidata.org/wiki/Q500094","display_name":"Pruning","level":2,"score":0.7279000282287598},{"id":"https://openalex.org/C2777303404","wikidata":"https://www.wikidata.org/wiki/Q759757","display_name":"Convergence (economics)","level":2,"score":0.5562999844551086},{"id":"https://openalex.org/C120314980","wikidata":"https://www.wikidata.org/wiki/Q180634","display_name":"Distributed computing","level":1,"score":0.536300003528595},{"id":"https://openalex.org/C123657996","wikidata":"https://www.wikidata.org/wiki/Q12271","display_name":"Architecture","level":2,"score":0.48899999260902405},{"id":"https://openalex.org/C2779582901","wikidata":"https://www.wikidata.org/wiki/Q21013010","display_name":"Distributed learning","level":2,"score":0.4462999999523163},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4318999946117401},{"id":"https://openalex.org/C20136886","wikidata":"https://www.wikidata.org/wiki/Q749647","display_name":"Interoperability","level":2,"score":0.3898000121116638},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.37709999084472656},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3612000048160553},{"id":"https://openalex.org/C202615002","wikidata":"https://www.wikidata.org/wiki/Q783507","display_name":"Differentiable function","level":2,"score":0.3499000072479248},{"id":"https://openalex.org/C67186912","wikidata":"https://www.wikidata.org/wiki/Q367664","display_name":"Data modeling","level":2,"score":0.3199000060558319},{"id":"https://openalex.org/C141513077","wikidata":"https://www.wikidata.org/wiki/Q378542","display_name":"Independent and identically distributed random variables","level":3,"score":0.3077999949455261},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.3068000078201294},{"id":"https://openalex.org/C2984842247","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep neural networks","level":3,"score":0.30059999227523804},{"id":"https://openalex.org/C70061542","wikidata":"https://www.wikidata.org/wiki/Q989016","display_name":"Distributed database","level":2,"score":0.2996000051498413},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.29030001163482666},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.2897999882698059},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.28540000319480896},{"id":"https://openalex.org/C89611455","wikidata":"https://www.wikidata.org/wiki/Q6804646","display_name":"Mechanism (biology)","level":2,"score":0.28360000252723694},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.2757999897003174},{"id":"https://openalex.org/C72634772","wikidata":"https://www.wikidata.org/wiki/Q386824","display_name":"Data integration","level":2,"score":0.27309998869895935},{"id":"https://openalex.org/C98025372","wikidata":"https://www.wikidata.org/wiki/Q477538","display_name":"Systems architecture","level":3,"score":0.25769999623298645},{"id":"https://openalex.org/C115903868","wikidata":"https://www.wikidata.org/wiki/Q80993","display_name":"Software engineering","level":1,"score":0.2533999979496002}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/bibm66473.2025.11356902","is_oa":false,"landing_page_url":"https://doi.org/10.1109/bibm66473.2025.11356902","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE International Conference on Bioinformatics and Biomedicine (BIBM)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/9","score":0.4644254148006439,"display_name":"Industry, innovation and infrastructure"},{"id":"https://metadata.un.org/sdg/17","score":0.40566182136535645,"display_name":"Partnerships for the goals"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":11,"referenced_works":["https://openalex.org/W2108598243","https://openalex.org/W2946547492","https://openalex.org/W2982083293","https://openalex.org/W3034309359","https://openalex.org/W3086809868","https://openalex.org/W3196371845","https://openalex.org/W3202972745","https://openalex.org/W4255158661","https://openalex.org/W4377293783","https://openalex.org/W4386709695","https://openalex.org/W4410140521"],"related_works":[],"abstract_inverted_index":{"Federated":[0],"learning":[1],"(FL)":[2],"enables":[3],"collaborative":[4],"model":[5,34,77],"training":[6],"across":[7,145],"distributed":[8,15],"data":[9,38],"silos,":[10],"but":[11],"non-independent":[12],"and":[13,68,79,121,136,151],"identically":[14],"(non-IID)":[16],"heterogeneity":[17],"among":[18],"clients":[19],"often":[20],"leads":[21],"to":[22,36],"biased":[23],"or":[24],"underperforming":[25],"global":[26],"models.":[27],"Neural":[28],"Architecture":[29],"Search":[30],"(NAS)":[31],"can":[32],"adapt":[33],"structures":[35],"diverse":[37,148],"distributions,":[39],"yet":[40],"conventional":[41],"two-stage":[42],"search-retrain":[43],"pipelines":[44],"remain":[45],"prohibitively":[46],"expensive":[47],"for":[48,103],"federated":[49,138],"settings.":[50],"We":[51],"propose":[52],"OSMONAS":[53,74,116,130],"(One-Stage":[54],"Meta-Optimization":[55],"NAS),":[56],"a":[57,69,82,132],"unified":[58],"framework":[59],"that":[60,115],"integrates":[61],"Model-Agnostic":[62],"Meta-Learning":[63],"(MAML)":[64],"with":[65,147],"differentiable":[66],"NAS":[67],"progressive":[70],"soft":[71],"pruning":[72,93],"strategy.":[73],"jointly":[75],"optimizes":[76],"weights":[78],"architectures":[80,142],"within":[81],"single-stage":[83],"search,":[84,99],"accelerating":[85],"convergence":[86,123],"while":[87],"preserving":[88],"performance":[89],"stability.":[90],"The":[91],"integrated":[92],"mechanism":[94],"removes":[95],"redundant":[96],"operations":[97],"during":[98],"eliminating":[100],"the":[101],"need":[102],"post-hoc":[104],"retraining.":[105],"Evaluations":[106],"on":[107],"standard":[108],"benchmarks":[109],"under":[110],"varying":[111],"non-IID":[112],"conditions":[113],"demonstrate":[114],"consistently":[117],"achieves":[118],"higher":[119],"accuracy":[120],"faster":[122],"than":[124],"state-of-the-art":[125],"baselines.":[126],"Beyond":[127],"computational":[128],"gains,":[129],"offers":[131],"pathway":[133],"toward":[134],"equitable":[135],"inclusive":[137],"healthcare,":[139],"where":[140],"adaptable":[141],"enable":[143],"collaboration":[144],"institutions":[146],"data,":[149],"devices,":[150],"resources.":[152]},"counts_by_year":[],"updated_date":"2026-02-01T03:34:12.195049","created_date":"2026-01-30T00:00:00"}