{"id":"https://openalex.org/W7162026747","doi":"https://doi.org/10.48550/arxiv.2605.21322","title":"Optimized Federated Knowledge Distillation with Distributed Neural Architecture Search","display_name":"Optimized Federated Knowledge Distillation with Distributed Neural Architecture Search","publication_year":2026,"publication_date":"2026-05-20","ids":{"openalex":"https://openalex.org/W7162026747","doi":"https://doi.org/10.48550/arxiv.2605.21322"},"language":null,"primary_location":{"id":"doi:10.48550/arxiv.2605.21322","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2605.21322","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"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":"article"},"type":"preprint","indexed_in":["datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://doi.org/10.48550/arxiv.2605.21322","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5114567276","display_name":"Chaimaa Medjadji","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Medjadji, Chaimaa","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5136646104","display_name":"Sylvain Kubler","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Kubler, Sylvain","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5136652131","display_name":"Yves Le Traon","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Traon, Yves Le","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5048933905","display_name":"Guilain Leduc","orcid":"https://orcid.org/0009-0005-4411-6982"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Leduc, Guilain","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5136299587","display_name":"Sadi Alawadi","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Alawadi, Sadi","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5065801245","display_name":"Feras M. Awaysheh","orcid":"https://orcid.org/0000-0002-9561-6099"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Awaysheh, Feras M.","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":6,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":0,"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":false,"primary_topic":{"id":"https://openalex.org/T10764","display_name":"Privacy-Preserving Technologies in Data","score":0.6152999997138977,"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":0.6152999997138977,"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/T10273","display_name":"IoT and Edge/Fog Computing","score":0.12540000677108765,"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"}},{"id":"https://openalex.org/T14347","display_name":"Big Data and Digital Economy","score":0.021900000050663948,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/overhead","display_name":"Overhead (engineering)","score":0.5479999780654907},{"id":"https://openalex.org/keywords/distillation","display_name":"Distillation","score":0.5040000081062317},{"id":"https://openalex.org/keywords/federated-learning","display_name":"Federated learning","score":0.4984000027179718},{"id":"https://openalex.org/keywords/adaptability","display_name":"Adaptability","score":0.49729999899864197},{"id":"https://openalex.org/keywords/constraint","display_name":"Constraint (computer-aided design)","score":0.40310001373291016},{"id":"https://openalex.org/keywords/limiting","display_name":"Limiting","score":0.38260000944137573},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.38040000200271606},{"id":"https://openalex.org/keywords/scheme","display_name":"Scheme (mathematics)","score":0.3711000084877014},{"id":"https://openalex.org/keywords/server","display_name":"Server","score":0.3594000041484833}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8073999881744385},{"id":"https://openalex.org/C2779960059","wikidata":"https://www.wikidata.org/wiki/Q7113681","display_name":"Overhead (engineering)","level":2,"score":0.5479999780654907},{"id":"https://openalex.org/C204030448","wikidata":"https://www.wikidata.org/wiki/Q101017","display_name":"Distillation","level":2,"score":0.5040000081062317},{"id":"https://openalex.org/C2992525071","wikidata":"https://www.wikidata.org/wiki/Q50818671","display_name":"Federated learning","level":2,"score":0.4984000027179718},{"id":"https://openalex.org/C177606310","wikidata":"https://www.wikidata.org/wiki/Q5674297","display_name":"Adaptability","level":2,"score":0.49729999899864197},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.4788999855518341},{"id":"https://openalex.org/C120314980","wikidata":"https://www.wikidata.org/wiki/Q180634","display_name":"Distributed computing","level":1,"score":0.46050000190734863},{"id":"https://openalex.org/C2776036281","wikidata":"https://www.wikidata.org/wiki/Q48769818","display_name":"Constraint (computer-aided design)","level":2,"score":0.40310001373291016},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3847000002861023},{"id":"https://openalex.org/C188198153","wikidata":"https://www.wikidata.org/wiki/Q1613840","display_name":"Limiting","level":2,"score":0.38260000944137573},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.38040000200271606},{"id":"https://openalex.org/C77618280","wikidata":"https://www.wikidata.org/wiki/Q1155772","display_name":"Scheme (mathematics)","level":2,"score":0.3711000084877014},{"id":"https://openalex.org/C93996380","wikidata":"https://www.wikidata.org/wiki/Q44127","display_name":"Server","level":2,"score":0.3594000041484833},{"id":"https://openalex.org/C81917197","wikidata":"https://www.wikidata.org/wiki/Q628760","display_name":"Selection (genetic algorithm)","level":2,"score":0.35409998893737793},{"id":"https://openalex.org/C123657996","wikidata":"https://www.wikidata.org/wiki/Q12271","display_name":"Architecture","level":2,"score":0.3483999967575073},{"id":"https://openalex.org/C190839683","wikidata":"https://www.wikidata.org/wiki/Q2448197","display_name":"Train","level":2,"score":0.3456999957561493},{"id":"https://openalex.org/C137635306","wikidata":"https://www.wikidata.org/wiki/Q182667","display_name":"Pareto principle","level":2,"score":0.33809998631477356},{"id":"https://openalex.org/C18762648","wikidata":"https://www.wikidata.org/wiki/Q42213","display_name":"Work (physics)","level":2,"score":0.3310000002384186},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.3271999955177307},{"id":"https://openalex.org/C206588197","wikidata":"https://www.wikidata.org/wiki/Q846574","display_name":"Reuse","level":2,"score":0.3249000012874603},{"id":"https://openalex.org/C136389625","wikidata":"https://www.wikidata.org/wiki/Q334384","display_name":"Supervised learning","level":3,"score":0.30219998955726624},{"id":"https://openalex.org/C47487241","wikidata":"https://www.wikidata.org/wiki/Q5227230","display_name":"Data access","level":2,"score":0.295199990272522},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.287200003862381},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.28060001134872437},{"id":"https://openalex.org/C98025372","wikidata":"https://www.wikidata.org/wiki/Q477538","display_name":"Systems architecture","level":3,"score":0.2718999981880188},{"id":"https://openalex.org/C173801870","wikidata":"https://www.wikidata.org/wiki/Q201413","display_name":"Heuristic","level":2,"score":0.2685999870300293},{"id":"https://openalex.org/C67186912","wikidata":"https://www.wikidata.org/wiki/Q367664","display_name":"Data modeling","level":2,"score":0.2632000148296356},{"id":"https://openalex.org/C202477664","wikidata":"https://www.wikidata.org/wiki/Q1352449","display_name":"Client-side","level":2,"score":0.2628999948501587},{"id":"https://openalex.org/C62469222","wikidata":"https://www.wikidata.org/wiki/Q17092103","display_name":"Hybrid algorithm (constraint satisfaction)","level":5,"score":0.25760000944137573},{"id":"https://openalex.org/C79403827","wikidata":"https://www.wikidata.org/wiki/Q3988","display_name":"Real-time computing","level":1,"score":0.25760000944137573}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.48550/arxiv.2605.21322","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2605.21322","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"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":"article"}],"best_oa_location":{"id":"doi:10.48550/arxiv.2605.21322","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2605.21322","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"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":"article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Federated":[0],"Learning":[1],"(FL)":[2],"enables":[3],"collaborative":[4],"model":[5,102],"training":[6],"without":[7],"centralizing":[8],"data.":[9],"However,":[10],"real-world":[11,74],"deployments":[12],"must":[13],"simultaneously":[14],"address":[15],"statistical":[16],"heterogeneity":[17,23],"across":[18],"client":[19,50,97,188],"data":[20,56],"(non-IID),":[21],"system":[22],"in":[24,73],"device":[25],"capabilities,":[26],"and":[27,58,71,118,121,134,194],"communication":[28,196],"efficiency.":[29],"Existing":[30],"FL":[31,75,83,162],"approaches":[32],"mitigate":[33],"these":[34,136],"challenges":[35],"through":[36],"improved":[37],"aggregation,":[38],"personalization,":[39],"or":[40],"knowledge":[41,119],"distillation,":[42],"but":[43],"they":[44],"almost":[45],"universally":[46],"assume":[47],"a":[48,81,100,112,126,142],"fixed":[49],"architecture,":[51],"limiting":[52],"adaptability":[53],"to":[54,66,145,182,200],"heterogeneous":[55],"complexity":[57],"hardware":[59],"constraints.":[60,105],"This":[61,77],"architectural":[62],"constraint":[63],"often":[64],"leads":[65],"suboptimal":[67],"trade-offs":[68],"between":[69],"accuracy":[70,179],"efficiency":[72],"systems.":[76],"work":[78],"introduces":[79],"FedKDNAS,":[80],"distillation-driven":[82],"framework":[84],"that":[85,171],"combines":[86],"client-side":[87],"neural":[88],"architecture":[89],"selection":[90],"with":[91,141],"distillation":[92,120,148],"of":[93],"server-coordinated":[94],"knowledge.":[95],"Each":[96],"autonomously":[98],"selects":[99],"lightweight":[101,205],"under":[103,184],"accuracy-resource":[104],"It":[106],"then":[107,132],"trains":[108],"it":[109],"locally":[110],"using":[111],"hybrid":[113],"objective":[114],"combining":[115,139],"supervised":[116],"learning":[117],"shares":[122],"only":[123],"predictions":[124],"on":[125,156],"public":[127],"reference":[128],"set.":[129],"The":[130],"server":[131],"aggregates":[133],"smooths":[135],"predictions,":[137],"optionally":[138],"them":[140],"teacher":[143],"model,":[144],"produce":[146],"stable":[147],"targets":[149],"for":[150],"the":[151],"next":[152],"round.":[153],"Extensive":[154],"evaluation":[155],"six":[157,160],"datasets":[158],"against":[159],"representative":[161],"baselines":[163],"(FedAvg,":[164],"Ditto,":[165],"FedMD,":[166],"FedDF,":[167],"FedDistill,":[168],"Local-KD)":[169],"demonstrates":[170],"FedKDNAS":[172],"consistently":[173],"achieves":[174],"superior":[175],"Pareto":[176],"efficiency,":[177],"improving":[178],"by":[180,191,198],"up":[181,199],"15\\%":[183],"non-IID":[185],"conditions,":[186],"reducing":[187],"CPU":[189],"usage":[190],"approximately":[192],"28\\%,":[193],"decreasing":[195],"overhead":[197],"44":[201],"times":[202],"while":[203],"maintaining":[204],"logit-based":[206],"communication.":[207]},"counts_by_year":[],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2026-05-22T00:00:00"}