{"id":"https://openalex.org/W4315605949","doi":"https://doi.org/10.1109/globecom48099.2022.10000892","title":"ChannelFed: Enabling Personalized Federated Learning via Localized Channel Attention","display_name":"ChannelFed: Enabling Personalized Federated Learning via Localized Channel Attention","publication_year":2022,"publication_date":"2022-12-04","ids":{"openalex":"https://openalex.org/W4315605949","doi":"https://doi.org/10.1109/globecom48099.2022.10000892"},"language":"en","primary_location":{"id":"doi:10.1109/globecom48099.2022.10000892","is_oa":false,"landing_page_url":"https://doi.org/10.1109/globecom48099.2022.10000892","pdf_url":null,"source":{"id":"https://openalex.org/S4363607705","display_name":"GLOBECOM 2022 - 2022 IEEE Global Communications Conference","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"GLOBECOM 2022 - 2022 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/A5101914277","display_name":"Kaiyu Zheng","orcid":"https://orcid.org/0000-0002-9002-6292"},"institutions":[{"id":"https://openalex.org/I82880672","display_name":"Beihang University","ror":"https://ror.org/00wk2mp56","country_code":"CN","type":"education","lineage":["https://openalex.org/I82880672"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Kaiyu Zheng","raw_affiliation_strings":["College of Software, Beihang University,China","College of Software, Beihang University, China"],"affiliations":[{"raw_affiliation_string":"College of Software, Beihang University,China","institution_ids":["https://openalex.org/I82880672"]},{"raw_affiliation_string":"College of Software, Beihang University, China","institution_ids":["https://openalex.org/I82880672"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100400532","display_name":"Xuefeng Liu","orcid":"https://orcid.org/0000-0001-9034-0217"},"institutions":[{"id":"https://openalex.org/I82880672","display_name":"Beihang University","ror":"https://ror.org/00wk2mp56","country_code":"CN","type":"education","lineage":["https://openalex.org/I82880672"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xuefeng Liu","raw_affiliation_strings":["School of Computer Science and Engineering, Beihang University,China","School of Computer Science and Engineering, Beihang University, China"],"affiliations":[{"raw_affiliation_string":"School of Computer Science and Engineering, Beihang University,China","institution_ids":["https://openalex.org/I82880672"]},{"raw_affiliation_string":"School of Computer Science and Engineering, Beihang University, China","institution_ids":["https://openalex.org/I82880672"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5057612676","display_name":"Guogang Zhu","orcid":"https://orcid.org/0000-0002-6381-1420"},"institutions":[{"id":"https://openalex.org/I82880672","display_name":"Beihang University","ror":"https://ror.org/00wk2mp56","country_code":"CN","type":"education","lineage":["https://openalex.org/I82880672"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Guogang Zhu","raw_affiliation_strings":["School of Computer Science and Engineering, Beihang University,China","School of Computer Science and Engineering, Beihang University, China"],"affiliations":[{"raw_affiliation_string":"School of Computer Science and Engineering, Beihang University,China","institution_ids":["https://openalex.org/I82880672"]},{"raw_affiliation_string":"School of Computer Science and Engineering, Beihang University, China","institution_ids":["https://openalex.org/I82880672"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5085775609","display_name":"Xinghao Wu","orcid":"https://orcid.org/0000-0002-6987-3972"},"institutions":[{"id":"https://openalex.org/I82880672","display_name":"Beihang University","ror":"https://ror.org/00wk2mp56","country_code":"CN","type":"education","lineage":["https://openalex.org/I82880672"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xinghao Wu","raw_affiliation_strings":["School of Computer Science and Engineering, Beihang University,China","School of Computer Science and Engineering, Beihang University, China"],"affiliations":[{"raw_affiliation_string":"School of Computer Science and Engineering, Beihang University,China","institution_ids":["https://openalex.org/I82880672"]},{"raw_affiliation_string":"School of Computer Science and Engineering, Beihang University, China","institution_ids":["https://openalex.org/I82880672"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5053316728","display_name":"Jianwei Niu","orcid":"https://orcid.org/0000-0003-3946-5107"},"institutions":[{"id":"https://openalex.org/I82880672","display_name":"Beihang University","ror":"https://ror.org/00wk2mp56","country_code":"CN","type":"education","lineage":["https://openalex.org/I82880672"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jianwei Niu","raw_affiliation_strings":["School of Computer Science and Engineering, Beihang University,China","School of Computer Science and Engineering, Beihang University, China"],"affiliations":[{"raw_affiliation_string":"School of Computer Science and Engineering, Beihang University,China","institution_ids":["https://openalex.org/I82880672"]},{"raw_affiliation_string":"School of Computer Science and Engineering, Beihang University, China","institution_ids":["https://openalex.org/I82880672"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5101914277"],"corresponding_institution_ids":["https://openalex.org/I82880672"],"apc_list":null,"apc_paid":null,"fwci":0.8377,"has_fulltext":false,"cited_by_count":9,"citation_normalized_percentile":{"value":0.75253087,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"2987","last_page":"2992"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10764","display_name":"Privacy-Preserving Technologies in Data","score":0.9998000264167786,"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":0.9998000264167786,"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":0.9638000130653381,"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"}},{"id":"https://openalex.org/T11273","display_name":"Advanced Graph Neural Networks","score":0.9348999857902527,"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/computer-science","display_name":"Computer science","score":0.8586524724960327},{"id":"https://openalex.org/keywords/normalization","display_name":"Normalization (sociology)","score":0.8354595899581909},{"id":"https://openalex.org/keywords/mnist-database","display_name":"MNIST database","score":0.7961564660072327},{"id":"https://openalex.org/keywords/federated-learning","display_name":"Federated learning","score":0.769870400428772},{"id":"https://openalex.org/keywords/exploit","display_name":"Exploit","score":0.7026398181915283},{"id":"https://openalex.org/keywords/channel","display_name":"Channel (broadcasting)","score":0.6134921312332153},{"id":"https://openalex.org/keywords/key","display_name":"Key (lock)","score":0.5029992461204529},{"id":"https://openalex.org/keywords/data-modeling","display_name":"Data modeling","score":0.42984068393707275},{"id":"https://openalex.org/keywords/statistical-model","display_name":"Statistical model","score":0.4251420497894287},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.3838485777378082},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.38326165080070496},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.3353434205055237},{"id":"https://openalex.org/keywords/deep-learning","display_name":"Deep learning","score":0.2602434754371643},{"id":"https://openalex.org/keywords/database","display_name":"Database","score":0.20270246267318726},{"id":"https://openalex.org/keywords/computer-network","display_name":"Computer network","score":0.1947043240070343},{"id":"https://openalex.org/keywords/computer-security","display_name":"Computer security","score":0.08663183450698853}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8586524724960327},{"id":"https://openalex.org/C136886441","wikidata":"https://www.wikidata.org/wiki/Q926129","display_name":"Normalization (sociology)","level":2,"score":0.8354595899581909},{"id":"https://openalex.org/C190502265","wikidata":"https://www.wikidata.org/wiki/Q17069496","display_name":"MNIST database","level":3,"score":0.7961564660072327},{"id":"https://openalex.org/C2992525071","wikidata":"https://www.wikidata.org/wiki/Q50818671","display_name":"Federated learning","level":2,"score":0.769870400428772},{"id":"https://openalex.org/C165696696","wikidata":"https://www.wikidata.org/wiki/Q11287","display_name":"Exploit","level":2,"score":0.7026398181915283},{"id":"https://openalex.org/C127162648","wikidata":"https://www.wikidata.org/wiki/Q16858953","display_name":"Channel (broadcasting)","level":2,"score":0.6134921312332153},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.5029992461204529},{"id":"https://openalex.org/C67186912","wikidata":"https://www.wikidata.org/wiki/Q367664","display_name":"Data modeling","level":2,"score":0.42984068393707275},{"id":"https://openalex.org/C114289077","wikidata":"https://www.wikidata.org/wiki/Q3284399","display_name":"Statistical model","level":2,"score":0.4251420497894287},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3838485777378082},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.38326165080070496},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.3353434205055237},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.2602434754371643},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.20270246267318726},{"id":"https://openalex.org/C31258907","wikidata":"https://www.wikidata.org/wiki/Q1301371","display_name":"Computer network","level":1,"score":0.1947043240070343},{"id":"https://openalex.org/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","level":1,"score":0.08663183450698853},{"id":"https://openalex.org/C144024400","wikidata":"https://www.wikidata.org/wiki/Q21201","display_name":"Sociology","level":0,"score":0.0},{"id":"https://openalex.org/C19165224","wikidata":"https://www.wikidata.org/wiki/Q23404","display_name":"Anthropology","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/globecom48099.2022.10000892","is_oa":false,"landing_page_url":"https://doi.org/10.1109/globecom48099.2022.10000892","pdf_url":null,"source":{"id":"https://openalex.org/S4363607705","display_name":"GLOBECOM 2022 - 2022 IEEE Global Communications Conference","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"GLOBECOM 2022 - 2022 IEEE Global Communications Conference","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G1234070867","display_name":null,"funder_award_id":"61976012","funder_id":"https://openalex.org/F4320320997","funder_display_name":"Funda\u00e7\u00e3o de Amparo \u00e0 Pesquisa do Estado de S\u00e3o Paulo"}],"funders":[{"id":"https://openalex.org/F4320320997","display_name":"Funda\u00e7\u00e3o de Amparo \u00e0 Pesquisa do Estado de S\u00e3o Paulo","ror":"https://ror.org/02ddkpn78"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":27,"referenced_works":["https://openalex.org/W1514535095","https://openalex.org/W1836465849","https://openalex.org/W2194775991","https://openalex.org/W2752782242","https://openalex.org/W2884585870","https://openalex.org/W2912213068","https://openalex.org/W2939059980","https://openalex.org/W2995022099","https://openalex.org/W3007548213","https://openalex.org/W3012968339","https://openalex.org/W3091267000","https://openalex.org/W3112044954","https://openalex.org/W3125494587","https://openalex.org/W3129603732","https://openalex.org/W3133814152","https://openalex.org/W3199576415","https://openalex.org/W3214265786","https://openalex.org/W4214666412","https://openalex.org/W4289752563","https://openalex.org/W4318619660","https://openalex.org/W6638667902","https://openalex.org/W6728757088","https://openalex.org/W6774195376","https://openalex.org/W6774978782","https://openalex.org/W6786597537","https://openalex.org/W6789305514","https://openalex.org/W6803975504"],"related_works":["https://openalex.org/W4386603768","https://openalex.org/W2950475743","https://openalex.org/W2886711096","https://openalex.org/W2750384547","https://openalex.org/W3196405711","https://openalex.org/W4392303055","https://openalex.org/W3187232590","https://openalex.org/W4388282301","https://openalex.org/W2073891040","https://openalex.org/W1510133244"],"abstract_inverted_index":{"One":[0,26],"vital":[1],"challenge":[2],"in":[3,13,52,73,151],"federated":[4,36],"learning":[5,37],"(FL)":[6],"is":[7,39,55,75,99],"the":[8,19,22,60,78,94,103,133,152],"statistical":[9,160,178],"heterogeneity":[10,161,179],"of":[11,21,59,116,125],"data":[12,127],"different":[14,109,114,129],"clients,":[15],"which":[16,57,92,118],"negatively":[17],"affects":[18],"performance":[20],"finally":[23],"obtained":[24],"model.":[25],"common":[27],"approach":[28],"to":[29,40,76,111,122,141,156],"address":[30],"this":[31,83],"problem,":[32],"called":[33],"as":[34],"personalized":[35,43,64],"(PFL),":[38],"train":[41],"a":[42,88],"model":[44,61],"for":[45,65,113,159],"each":[46,66],"client.":[47,67],"A":[48],"key":[49],"design":[50],"issue":[51],"PFL-based":[53,90],"methods":[54,176],"determining":[56],"parts":[58],"should":[62],"be":[63,120],"For":[68],"example,":[69],"one":[70],"popular":[71],"method":[72,91],"PFL":[74,175],"personalize":[77],"batch":[79],"normalization":[80,148],"layers.":[81],"In":[82],"paper,":[84],"we":[85],"propose":[86],"ChannelFed,":[87],"new":[89],"personalizes":[93],"channel":[95,134,153],"attention":[96,107,135,154],"module.":[97],"ChannelFed":[98,138,146,172],"designed":[100],"based":[101],"on":[102,143,164],"following":[104],"observation:":[105],"Channel":[106],"assigns":[108],"weights":[110],"channels":[112],"classes":[115],"data,":[117],"can":[119],"utilized":[121],"exploit":[123],"knowledge":[124],"heterogeneous":[126],"from":[128],"clients.":[130],"By":[131],"keeping":[132],"module":[136,155],"localized,":[137],"enables":[139],"clients":[140],"concentrate":[142],"client-specific":[144],"channels.":[145],"implements":[147],"across":[149],"samples":[150],"better":[157],"fit":[158],"scenarios.":[162,180],"Experiments":[163],"CIFAR-10,":[165],"Fashion-MNIST,":[166],"and":[167],"CIFAR-100":[168],"datasets":[169],"demonstrate":[170],"that":[171],"outperforms":[173],"other":[174],"under":[177]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":5},{"year":2023,"cited_by_count":2},{"year":2021,"cited_by_count":1}],"updated_date":"2026-03-20T23:20:44.827607","created_date":"2025-10-10T00:00:00"}