{"id":"https://openalex.org/W7105705207","doi":"https://doi.org/10.1109/ijcnn64981.2025.11229069","title":"Towards Accurate Federated Learning under Heterogeneous Local Models via Global Model Decoupling","display_name":"Towards Accurate Federated Learning under Heterogeneous Local Models via Global Model Decoupling","publication_year":2025,"publication_date":"2025-06-30","ids":{"openalex":"https://openalex.org/W7105705207","doi":"https://doi.org/10.1109/ijcnn64981.2025.11229069"},"language":null,"primary_location":{"id":"doi:10.1109/ijcnn64981.2025.11229069","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ijcnn64981.2025.11229069","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 International Joint Conference on Neural Networks (IJCNN)","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":null,"display_name":"Shijie He","orcid":null},"institutions":[{"id":"https://openalex.org/I4210131342","display_name":"Yibin University","ror":"https://ror.org/03w8m2977","country_code":"CN","type":"education","lineage":["https://openalex.org/I4210131342"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Shijie He","raw_affiliation_strings":["Sichuan University of Science and Engineering,School of Management,Yibin,China"],"affiliations":[{"raw_affiliation_string":"Sichuan University of Science and Engineering,School of Management,Yibin,China","institution_ids":["https://openalex.org/I4210131342"]}]},{"author_position":"last","author":{"id":null,"display_name":"Jinshan Lai","orcid":null},"institutions":[{"id":"https://openalex.org/I150229711","display_name":"University of Electronic Science and Technology of China","ror":"https://ror.org/04qr3zq92","country_code":"CN","type":"education","lineage":["https://openalex.org/I150229711"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jinshan Lai","raw_affiliation_strings":["University of Electronic Science and Technology of China,School of Information and Software Engineering,Chengdu,China"],"affiliations":[{"raw_affiliation_string":"University of Electronic Science and Technology of China,School of Information and Software Engineering,Chengdu,China","institution_ids":["https://openalex.org/I150229711"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I4210131342"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.79531542,"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":"8"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10764","display_name":"Privacy-Preserving Technologies in Data","score":0.8752999901771545,"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":0.8752999901771545,"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/T11273","display_name":"Advanced Graph Neural Networks","score":0.0215000007301569,"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":0.01940000057220459,"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/classifier","display_name":"Classifier (UML)","score":0.5185999870300293},{"id":"https://openalex.org/keywords/federated-learning","display_name":"Federated learning","score":0.504800021648407},{"id":"https://openalex.org/keywords/global-optimization","display_name":"Global optimization","score":0.4993000030517578},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.45559999346733093},{"id":"https://openalex.org/keywords/extractor","display_name":"Extractor","score":0.36399999260902405},{"id":"https://openalex.org/keywords/focus","display_name":"Focus (optics)","score":0.3490999937057495},{"id":"https://openalex.org/keywords/decoupling","display_name":"Decoupling (probability)","score":0.3467999994754791}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7892000079154968},{"id":"https://openalex.org/C95623464","wikidata":"https://www.wikidata.org/wiki/Q1096149","display_name":"Classifier (UML)","level":2,"score":0.5185999870300293},{"id":"https://openalex.org/C2992525071","wikidata":"https://www.wikidata.org/wiki/Q50818671","display_name":"Federated learning","level":2,"score":0.504800021648407},{"id":"https://openalex.org/C164752517","wikidata":"https://www.wikidata.org/wiki/Q5570875","display_name":"Global optimization","level":2,"score":0.4993000030517578},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4848000109195709},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.45559999346733093},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.42320001125335693},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3874000012874603},{"id":"https://openalex.org/C117978034","wikidata":"https://www.wikidata.org/wiki/Q5422192","display_name":"Extractor","level":2,"score":0.36399999260902405},{"id":"https://openalex.org/C192209626","wikidata":"https://www.wikidata.org/wiki/Q190909","display_name":"Focus (optics)","level":2,"score":0.3490999937057495},{"id":"https://openalex.org/C205606062","wikidata":"https://www.wikidata.org/wiki/Q5249645","display_name":"Decoupling (probability)","level":2,"score":0.3467999994754791},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.32269999384880066},{"id":"https://openalex.org/C67186912","wikidata":"https://www.wikidata.org/wiki/Q367664","display_name":"Data modeling","level":2,"score":0.314300000667572},{"id":"https://openalex.org/C101814296","wikidata":"https://www.wikidata.org/wiki/Q5439685","display_name":"Feature model","level":3,"score":0.28439998626708984},{"id":"https://openalex.org/C2779188883","wikidata":"https://www.wikidata.org/wiki/Q82446","display_name":"Global Map","level":3,"score":0.26499998569488525},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.2533000111579895},{"id":"https://openalex.org/C120314980","wikidata":"https://www.wikidata.org/wiki/Q180634","display_name":"Distributed computing","level":1,"score":0.25209999084472656},{"id":"https://openalex.org/C164866538","wikidata":"https://www.wikidata.org/wiki/Q367351","display_name":"Cluster (spacecraft)","level":2,"score":0.25}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/ijcnn64981.2025.11229069","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ijcnn64981.2025.11229069","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 International Joint Conference on Neural Networks (IJCNN)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.41868463158607483,"id":"https://metadata.un.org/sdg/9","display_name":"Industry, innovation and infrastructure"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":27,"referenced_works":["https://openalex.org/W2964162474","https://openalex.org/W3018102029","https://openalex.org/W3047069132","https://openalex.org/W3102626224","https://openalex.org/W3187356235","https://openalex.org/W3206985409","https://openalex.org/W3215194618","https://openalex.org/W4214758645","https://openalex.org/W4220867361","https://openalex.org/W4283204848","https://openalex.org/W4283796083","https://openalex.org/W4285601829","https://openalex.org/W4312231739","https://openalex.org/W4312600254","https://openalex.org/W4313643873","https://openalex.org/W4317926941","https://openalex.org/W4378697396","https://openalex.org/W4382317683","https://openalex.org/W4385567528","https://openalex.org/W4386083155","https://openalex.org/W4386243236","https://openalex.org/W4386245189","https://openalex.org/W4387969057","https://openalex.org/W4390873050","https://openalex.org/W4392125018","https://openalex.org/W4393156671","https://openalex.org/W4393159708"],"related_works":[],"abstract_inverted_index":{"Clients":[0],"in":[1,13,190],"federated":[2],"learning":[3],"(FL)":[4],"may":[5],"use":[6],"different":[7],"model":[8,33,39,59,65,78,83,94],"architectures":[9],"due":[10],"to":[11,74,121,129,142,147,165,175],"variations":[12],"computing":[14],"capabilities":[15],"and":[16,71,116,135,169,194],"memory":[17],"space.":[18],"While":[19],"existing":[20],"studies":[21],"on":[22,30],"FL":[23,50],"with":[24,56,91],"heterogeneous":[25,53],"local":[26,32,54,104],"models":[27,55],"primarily":[28],"focus":[29],"improving":[31],"accuracy,":[34],"achieving":[35],"a":[36,48,82,101,154,161],"high-accuracy":[37],"global":[38,58,64,77,132,136,140,149,155,167,179],"remains":[40],"underexplored.":[41],"In":[42],"this":[43],"work,":[44],"we":[45,99,152],"propose":[46,100,153],"Fed-DGMT,":[47],"novel":[49],"framework":[51],"for":[52],"decoupled":[57],"training,":[60],"which":[61,126,159],"decouples":[62],"the":[63,92,109,131,139,148,166,177],"training":[66,70,73,105],"into":[67],"feature":[68,133],"extractor":[69,134],"classifier":[72,168],"achieves":[75],"high":[76],"accuracy.":[79],"We":[80],"introduce":[81],"architecture-aware":[84],"client":[85],"grouping":[86],"method":[87,106,113],"that":[88,107,185],"clusters":[89],"clients":[90],"same":[93],"architecture.":[95],"For":[96,138],"each":[97],"cluster,":[98],"data":[102],"heterogeneity-aware":[103],"incorporates":[108],"scaled":[110],"alternating":[111],"direction":[112],"of":[114,192],"multipliers":[115],"sharpness-aware":[117],"minimization-based":[118],"gradient":[119],"correction":[120],"train":[122],"accurate":[123],"cluster":[124],"models,":[125],"are":[127],"concatenated":[128,178],"form":[130],"classifier.":[137,180],"classifier,":[141],"ensure":[143],"it":[144],"adapts":[145],"well":[146],"label":[150],"distribution,":[151],"knowledge-guided":[156],"fine-tuning":[157],"method,":[158],"adds":[160],"fixed-weight":[162],"linear":[163],"layer":[164],"uses":[170],"its":[171],"output":[172],"as":[173],"guidance":[174],"fine-tune":[176],"Extensive":[181],"experimental":[182],"results":[183],"demonstrate":[184],"Fed-DGMT":[186],"outperforms":[187],"state-of-the-art":[188],"methods":[189],"terms":[191],"accuracy":[193],"computational":[195],"overhead.":[196]},"counts_by_year":[],"updated_date":"2025-11-15T23:13:30.683059","created_date":"2025-11-14T00:00:00"}