{"id":"https://openalex.org/W4408324716","doi":"https://doi.org/10.1109/globecom52923.2024.10901645","title":"FedNHN: Generated Data-driven Personalized Federated Learning with Heterogeneous Data","display_name":"FedNHN: Generated Data-driven Personalized Federated Learning with Heterogeneous Data","publication_year":2024,"publication_date":"2024-12-08","ids":{"openalex":"https://openalex.org/W4408324716","doi":"https://doi.org/10.1109/globecom52923.2024.10901645"},"language":"en","primary_location":{"id":"doi:10.1109/globecom52923.2024.10901645","is_oa":false,"landing_page_url":"https://doi.org/10.1109/globecom52923.2024.10901645","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"GLOBECOM 2024 - 2024 IEEE Global Communications Conference","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/A5111537539","display_name":"Jialong Sun","orcid":null},"institutions":[{"id":"https://openalex.org/I55022517","display_name":"Heilongjiang University","ror":"https://ror.org/04zyhq975","country_code":"CN","type":"education","lineage":["https://openalex.org/I55022517"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Jialong Sun","raw_affiliation_strings":["Heilongjiang University,School of Mathematical Science,Harbin,China,150080"],"affiliations":[{"raw_affiliation_string":"Heilongjiang University,School of Mathematical Science,Harbin,China,150080","institution_ids":["https://openalex.org/I55022517"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5109535448","display_name":"Jing Dong","orcid":null},"institutions":[{"id":"https://openalex.org/I55022517","display_name":"Heilongjiang University","ror":"https://ror.org/04zyhq975","country_code":"CN","type":"education","lineage":["https://openalex.org/I55022517"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jing Dong","raw_affiliation_strings":["Heilongjiang University,School of Data Science and Technology,Harbin,China,150080"],"affiliations":[{"raw_affiliation_string":"Heilongjiang University,School of Data Science and Technology,Harbin,China,150080","institution_ids":["https://openalex.org/I55022517"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5018234471","display_name":"Zu-En Su","orcid":"https://orcid.org/0009-0005-4026-7169"},"institutions":[{"id":"https://openalex.org/I55022517","display_name":"Heilongjiang University","ror":"https://ror.org/04zyhq975","country_code":"CN","type":"education","lineage":["https://openalex.org/I55022517"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhanye Su","raw_affiliation_strings":["Heilongjiang University,School of Mathematical Science,Harbin,China,150080"],"affiliations":[{"raw_affiliation_string":"Heilongjiang University,School of Mathematical Science,Harbin,China,150080","institution_ids":["https://openalex.org/I55022517"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100450629","display_name":"Wenchao Zhang","orcid":"https://orcid.org/0000-0003-0619-3109"},"institutions":[{"id":"https://openalex.org/I206777745","display_name":"Nanjing Audit University","ror":"https://ror.org/04zj2bd87","country_code":"CN","type":"education","lineage":["https://openalex.org/I206777745"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Wenchao Zhang","raw_affiliation_strings":["Nanjing Audit University,School of Mathematics,Nanjing,China,211815"],"affiliations":[{"raw_affiliation_string":"Nanjing Audit University,School of Mathematics,Nanjing,China,211815","institution_ids":["https://openalex.org/I206777745"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100614380","display_name":"Kejia Zhang","orcid":"https://orcid.org/0000-0001-9715-6076"},"institutions":[{"id":"https://openalex.org/I55022517","display_name":"Heilongjiang University","ror":"https://ror.org/04zyhq975","country_code":"CN","type":"education","lineage":["https://openalex.org/I55022517"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Kejia Zhang","raw_affiliation_strings":["Heilongjiang University,School of Mathematical Science,Harbin,China,150080"],"affiliations":[{"raw_affiliation_string":"Heilongjiang University,School of Mathematical Science,Harbin,China,150080","institution_ids":["https://openalex.org/I55022517"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5111537539"],"corresponding_institution_ids":["https://openalex.org/I55022517"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.2597818,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"373","last_page":"378"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10764","display_name":"Privacy-Preserving Technologies in Data","score":0.9965999722480774,"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":0.9965999722480774,"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/T10203","display_name":"Recommender Systems and Techniques","score":0.9387000203132629,"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/computer-science","display_name":"Computer science","score":0.7899566888809204},{"id":"https://openalex.org/keywords/data-modeling","display_name":"Data modeling","score":0.443812757730484},{"id":"https://openalex.org/keywords/data-science","display_name":"Data science","score":0.41953322291374207},{"id":"https://openalex.org/keywords/world-wide-web","display_name":"World Wide Web","score":0.3262125551700592},{"id":"https://openalex.org/keywords/database","display_name":"Database","score":0.21085518598556519}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7899566888809204},{"id":"https://openalex.org/C67186912","wikidata":"https://www.wikidata.org/wiki/Q367664","display_name":"Data modeling","level":2,"score":0.443812757730484},{"id":"https://openalex.org/C2522767166","wikidata":"https://www.wikidata.org/wiki/Q2374463","display_name":"Data science","level":1,"score":0.41953322291374207},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.3262125551700592},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.21085518598556519}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/globecom52923.2024.10901645","is_oa":false,"landing_page_url":"https://doi.org/10.1109/globecom52923.2024.10901645","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"GLOBECOM 2024 - 2024 IEEE Global Communications Conference","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":22,"referenced_works":["https://openalex.org/W2803782214","https://openalex.org/W2978422189","https://openalex.org/W3010852232","https://openalex.org/W3129195893","https://openalex.org/W3182158470","https://openalex.org/W4296079221","https://openalex.org/W4319865686","https://openalex.org/W4382463479","https://openalex.org/W4387319219","https://openalex.org/W4389161176","https://openalex.org/W4392175354","https://openalex.org/W4392902785","https://openalex.org/W4399418344","https://openalex.org/W6640425456","https://openalex.org/W6728757088","https://openalex.org/W6759238902","https://openalex.org/W6767676916","https://openalex.org/W6768746289","https://openalex.org/W6773817997","https://openalex.org/W6802039821","https://openalex.org/W6810638590","https://openalex.org/W6853070551"],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2899084033","https://openalex.org/W2748952813","https://openalex.org/W2390279801","https://openalex.org/W4391913857","https://openalex.org/W2358668433","https://openalex.org/W4396701345","https://openalex.org/W2376932109","https://openalex.org/W2001405890","https://openalex.org/W4396696052"],"abstract_inverted_index":{"The":[0],"emergence":[1],"of":[2,89,128,170,189],"heterogeneous":[3,15,175],"data":[4,16,131],"brings":[5],"new":[6],"challenges":[7],"to":[8,37,79,120,152],"Federated":[9,59],"Learning":[10,60],"(FL).":[11],"Unlike":[12],"homogeneous":[13],"datasets,":[14],"are":[17],"inherently":[18],"characterized":[19],"by":[20,69,96,132],"sample":[21],"domain":[22],"center":[23],"offsets,":[24],"which":[25],"makes":[26],"traditional":[27],"federated":[28,172],"learning":[29],"often":[30],"suffer":[31],"from":[32],"poor":[33],"model":[34,108,135,173],"results":[35],"due":[36],"catastrophic":[38],"forgetting":[39],"and":[40,76,93,109,136,141,177,187],"increased":[41],"communication":[42],"costs":[43],"when":[44],"dealing":[45],"with":[46,104],"such":[47],"data.":[48,111],"To":[49],"address":[50],"this":[51],"problem,":[52],"we":[53],"introduce":[54],"FedNHN,":[55],"a":[56],"novel":[57],"Personalized":[58],"(PFL)":[61],"algorithm.":[62],"FedNHN":[63,113],"regularizes":[64],"the":[65,71,74,98,106,115,122,125,129,133,137,143,154,168,171,185],"local":[66,75,110,138,155],"training":[67,156],"loss":[68,157],"quantifying":[70],"disparity":[72],"between":[73,124],"global":[77,107,134],"models":[78],"generate":[80],"pseudo-data":[81],"feature":[82,126],"representations.":[83],"Specifically,":[84],"it":[85],"generates":[86],"two":[87],"types":[88],"pseudo-data:":[90],"Highly":[91],"Pseudo":[92],"Perturbed":[94],"Data,":[95],"employing":[97],"Fast":[99],"Gradient":[100],"Sign":[101],"Method":[102],"(FGSM)":[103],"both":[105],"Furthermore,":[112],"leverages":[114],"Hilbert-Schmidt":[116],"Independence":[117],"Criterion":[118],"(DN-HSIC)":[119],"assess":[121],"distances":[123],"representations":[127],"generated":[130],"model,":[139],"respectively,":[140],"utilizes":[142],"Centered":[144],"Kernel":[145],"Alignment":[146],"(CKA)":[147],"similarity":[148],"based":[149],"on":[150,180],"DN-HSIC":[151],"regulate":[153],"effectively.":[158],"Our":[159],"mathematical":[160],"analyses":[161],"show":[162],"that":[163],"our":[164,190],"design":[165],"can":[166],"maintain":[167],"utility":[169],"under":[174],"data,":[176],"extensive":[178],"evaluations":[179],"three":[181],"classical":[182],"datasets":[183],"illustrate":[184],"effectiveness":[186],"performance":[188],"proposed":[191],"implementation.":[192]},"counts_by_year":[],"updated_date":"2025-12-28T23:10:05.387466","created_date":"2025-10-10T00:00:00"}