{"id":"https://openalex.org/W7152684989","doi":"https://doi.org/10.48550/arxiv.2604.06631","title":"SubFLOT: Submodel Extraction for Efficient and Personalized Federated Learning via Optimal Transport","display_name":"SubFLOT: Submodel Extraction for Efficient and Personalized Federated Learning via Optimal Transport","publication_year":2026,"publication_date":"2026-04-08","ids":{"openalex":"https://openalex.org/W7152684989","doi":"https://doi.org/10.48550/arxiv.2604.06631"},"language":null,"primary_location":{"id":"doi:10.48550/arxiv.2604.06631","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2604.06631","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.2604.06631","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5133284072","display_name":"Zheng Jiang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Jiang, Zheng","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5133266762","display_name":"Nan He","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"He, Nan","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5133314223","display_name":"Yiming Chen","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Chen, Yiming","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5103585545","display_name":"Lifeng Sun","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Sun, Lifeng","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":4,"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":0.9125999808311462,"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":0.9125999808311462,"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":0.008799999952316284,"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":0.008500000461935997,"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/pruning","display_name":"Pruning","score":0.7985000014305115},{"id":"https://openalex.org/keywords/regularization","display_name":"Regularization (linguistics)","score":0.526199996471405},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.4242999851703644},{"id":"https://openalex.org/keywords/path","display_name":"Path (computing)","score":0.4221000075340271},{"id":"https://openalex.org/keywords/minification","display_name":"Minification","score":0.41280001401901245},{"id":"https://openalex.org/keywords/parametric-statistics","display_name":"Parametric statistics","score":0.39899998903274536},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.3813999891281128},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.36970001459121704},{"id":"https://openalex.org/keywords/raw-data","display_name":"Raw data","score":0.36239999532699585}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8173999786376953},{"id":"https://openalex.org/C108010975","wikidata":"https://www.wikidata.org/wiki/Q500094","display_name":"Pruning","level":2,"score":0.7985000014305115},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.5443000197410583},{"id":"https://openalex.org/C2776135515","wikidata":"https://www.wikidata.org/wiki/Q17143721","display_name":"Regularization (linguistics)","level":2,"score":0.526199996471405},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4767000079154968},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.4255000054836273},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.4242999851703644},{"id":"https://openalex.org/C2777735758","wikidata":"https://www.wikidata.org/wiki/Q817765","display_name":"Path (computing)","level":2,"score":0.4221000075340271},{"id":"https://openalex.org/C147764199","wikidata":"https://www.wikidata.org/wiki/Q6865248","display_name":"Minification","level":2,"score":0.41280001401901245},{"id":"https://openalex.org/C117251300","wikidata":"https://www.wikidata.org/wiki/Q1849855","display_name":"Parametric statistics","level":2,"score":0.39899998903274536},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.3813999891281128},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.36970001459121704},{"id":"https://openalex.org/C132964779","wikidata":"https://www.wikidata.org/wiki/Q2110223","display_name":"Raw data","level":2,"score":0.36239999532699585},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.3538999855518341},{"id":"https://openalex.org/C183003079","wikidata":"https://www.wikidata.org/wiki/Q1000371","display_name":"Personalization","level":2,"score":0.31859999895095825},{"id":"https://openalex.org/C93996380","wikidata":"https://www.wikidata.org/wiki/Q44127","display_name":"Server","level":2,"score":0.3172999918460846},{"id":"https://openalex.org/C2984842247","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep neural networks","level":3,"score":0.30709999799728394},{"id":"https://openalex.org/C2992525071","wikidata":"https://www.wikidata.org/wiki/Q50818671","display_name":"Federated learning","level":2,"score":0.29899999499320984},{"id":"https://openalex.org/C162307627","wikidata":"https://www.wikidata.org/wiki/Q204833","display_name":"Enhanced Data Rates for GSM Evolution","level":2,"score":0.28610000014305115},{"id":"https://openalex.org/C67186912","wikidata":"https://www.wikidata.org/wiki/Q367664","display_name":"Data modeling","level":2,"score":0.2833000123500824},{"id":"https://openalex.org/C111335779","wikidata":"https://www.wikidata.org/wiki/Q3454686","display_name":"Reduction (mathematics)","level":2,"score":0.27970001101493835},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.27480000257492065},{"id":"https://openalex.org/C71901391","wikidata":"https://www.wikidata.org/wiki/Q7126699","display_name":"Upload","level":2,"score":0.27320000529289246},{"id":"https://openalex.org/C138236772","wikidata":"https://www.wikidata.org/wiki/Q25098575","display_name":"Edge device","level":3,"score":0.25850000977516174},{"id":"https://openalex.org/C114289077","wikidata":"https://www.wikidata.org/wiki/Q3284399","display_name":"Statistical model","level":2,"score":0.25529998540878296}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.48550/arxiv.2604.06631","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2604.06631","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.2604.06631","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2604.06631","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],"training":[6,65],"while":[7],"preserving":[8],"data":[9,102],"privacy,":[10],"but":[11],"its":[12,164],"practical":[13],"deployment":[14],"is":[15,46],"hampered":[16],"by":[17,147],"system":[18],"and":[19,66,158,169],"statistical":[20],"heterogeneity.":[21],"While":[22],"federated":[23,83],"network":[24],"pruning":[25,40,45,54,106,150],"offers":[26],"a":[27,36,77,109,135],"path":[28],"to":[29,114,123],"mitigate":[30],"these":[31,72],"issues,":[32],"existing":[33],"methods":[34],"face":[35],"critical":[37],"dilemma:":[38],"server-side":[39,81],"lacks":[41],"personalization,":[42],"whereas":[43],"client-side":[44],"computationally":[47],"prohibitive":[48],"for":[49,80,100,166],"resource-constrained":[50,173],"devices.":[51,175],"Furthermore,":[52],"the":[53,105,139,143,148],"process":[55],"itself":[56],"induces":[57],"significant":[58],"parametric":[59,125],"divergence":[60],"among":[61],"heterogeneous":[62],"submodels,":[63],"destabilizing":[64],"hindering":[67],"global":[68,140],"convergence.":[69],"To":[70],"address":[71],"challenges,":[73],"we":[74],"propose":[75],"SubFLOT,":[76],"novel":[78],"framework":[79],"personalized":[82,170],"pruning.":[84],"SubFLOT":[85,156],"introduces":[86],"an":[87],"Optimal":[88],"Transport-enhanced":[89],"Pruning":[90],"(OTP)":[91],"module":[92,132],"that":[93,155],"treats":[94],"historical":[95],"client":[96],"models":[97,171],"as":[98,108],"proxies":[99],"local":[101],"distributions,":[103],"formulating":[104],"task":[107],"Wasserstein":[110],"distance":[111],"minimization":[112],"problem":[113],"generate":[115],"customized":[116],"submodels":[117],"without":[118],"accessing":[119],"raw":[120],"data.":[121],"Concurrently,":[122],"counteract":[124],"divergence,":[126],"our":[127],"Scaling-based":[128],"Adaptive":[129],"Regularization":[130],"(SAR)":[131],"adaptively":[133],"penalizes":[134],"submodel's":[136],"deviation":[137],"from":[138],"model,":[141],"with":[142],"penalty's":[144],"strength":[145],"scaled":[146],"client's":[149],"rate.":[151],"Comprehensive":[152],"experiments":[153],"demonstrate":[154],"consistently":[157],"substantially":[159],"outperforms":[160],"state-of-the-art":[161],"methods,":[162],"underscoring":[163],"potential":[165],"deploying":[167],"efficient":[168],"on":[172],"edge":[174]},"counts_by_year":[],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2026-04-10T00:00:00"}