{"id":"https://openalex.org/W4408345743","doi":"https://doi.org/10.1109/icassp49660.2025.10889557","title":"Collaborative Personalized Federated Learning via Exponential Moving Average Optimization","display_name":"Collaborative Personalized Federated Learning via Exponential Moving Average Optimization","publication_year":2025,"publication_date":"2025-03-12","ids":{"openalex":"https://openalex.org/W4408345743","doi":"https://doi.org/10.1109/icassp49660.2025.10889557"},"language":"en","primary_location":{"id":"doi:10.1109/icassp49660.2025.10889557","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49660.2025.10889557","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2025 - 2025 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","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/A5100379932","display_name":"Yuqing Li","orcid":"https://orcid.org/0000-0002-1691-4689"},"institutions":[{"id":"https://openalex.org/I139759216","display_name":"Beijing University of Posts and Telecommunications","ror":"https://ror.org/04w9fbh59","country_code":"CN","type":"education","lineage":["https://openalex.org/I139759216"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Yuqing Li","raw_affiliation_strings":["Beijing University of Posts and Telecommunications,Beijing,China"],"affiliations":[{"raw_affiliation_string":"Beijing University of Posts and Telecommunications,Beijing,China","institution_ids":["https://openalex.org/I139759216"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102998611","display_name":"Jintao Liang","orcid":"https://orcid.org/0009-0001-4127-7749"},"institutions":[{"id":"https://openalex.org/I139759216","display_name":"Beijing University of Posts and Telecommunications","ror":"https://ror.org/04w9fbh59","country_code":"CN","type":"education","lineage":["https://openalex.org/I139759216"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jintao Liang","raw_affiliation_strings":["Beijing University of Posts and Telecommunications,Beijing,China"],"affiliations":[{"raw_affiliation_string":"Beijing University of Posts and Telecommunications,Beijing,China","institution_ids":["https://openalex.org/I139759216"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101903306","display_name":"Peng Tang","orcid":"https://orcid.org/0000-0002-4377-3666"},"institutions":[{"id":"https://openalex.org/I4210136793","display_name":"Peng Cheng Laboratory","ror":"https://ror.org/03qdqbt06","country_code":"CN","type":"facility","lineage":["https://openalex.org/I4210136793"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Peng Tang","raw_affiliation_strings":["Quan Cheng Laboratory,Jinan,China"],"affiliations":[{"raw_affiliation_string":"Quan Cheng Laboratory,Jinan,China","institution_ids":["https://openalex.org/I4210136793"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5036865453","display_name":"Sen Su","orcid":"https://orcid.org/0000-0003-4266-7527"},"institutions":[{"id":"https://openalex.org/I139759216","display_name":"Beijing University of Posts and Telecommunications","ror":"https://ror.org/04w9fbh59","country_code":"CN","type":"education","lineage":["https://openalex.org/I139759216"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Sen Su","raw_affiliation_strings":["Beijing University of Posts and Telecommunications,Beijing,China"],"affiliations":[{"raw_affiliation_string":"Beijing University of Posts and Telecommunications,Beijing,China","institution_ids":["https://openalex.org/I139759216"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5100379932"],"corresponding_institution_ids":["https://openalex.org/I139759216"],"apc_list":null,"apc_paid":null,"fwci":2.5953,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.88935936,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":91,"max":95},"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"5"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10764","display_name":"Privacy-Preserving Technologies in Data","score":0.9872999787330627,"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":0.9872999787330627,"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":0.9623000025749207,"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":0.722987949848175},{"id":"https://openalex.org/keywords/exponential-function","display_name":"Exponential function","score":0.46260201930999756},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.369019478559494},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.10501351952552795}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.722987949848175},{"id":"https://openalex.org/C151376022","wikidata":"https://www.wikidata.org/wiki/Q168698","display_name":"Exponential function","level":2,"score":0.46260201930999756},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.369019478559494},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.10501351952552795},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp49660.2025.10889557","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49660.2025.10889557","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2025 - 2025 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":19,"referenced_works":["https://openalex.org/W2060277733","https://openalex.org/W2112796928","https://openalex.org/W2618530766","https://openalex.org/W2912213068","https://openalex.org/W2962966271","https://openalex.org/W3021654819","https://openalex.org/W3080934299","https://openalex.org/W3089578458","https://openalex.org/W3112044954","https://openalex.org/W3196371845","https://openalex.org/W4287332481","https://openalex.org/W4389723455","https://openalex.org/W6728757088","https://openalex.org/W6743688258","https://openalex.org/W6784336702","https://openalex.org/W6791102956","https://openalex.org/W6791444617","https://openalex.org/W6854708048","https://openalex.org/W7075999875"],"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":{"Data":[0],"heterogeneity":[1],"poses":[2],"a":[3,57],"critical":[4],"challenge":[5],"in":[6,41],"federated":[7],"learning,":[8],"driving":[9],"the":[10,39,46,49,84,97,122,135,140],"development":[11],"of":[12,48,72,93,139],"personalized":[13,59,116],"client":[14],"models.":[15,51],"However,":[16],"when":[17],"each":[18],"client\u2019s":[19],"local":[20,81],"data":[21,42,73,112],"is":[22],"limited":[23],"and":[24,26,87,137,155],"nonindependent":[25],"identically":[27],"distributed":[28],"(non-IID),":[29],"previous":[30],"efforts":[31],"fail":[32],"to":[33,69,79,103,133,158],"implement":[34],"collaborative":[35,67],"strategies":[36,68],"based":[37,95],"on":[38,96,145],"variability":[40],"heterogeneity,":[43],"thereby":[44],"constraining":[45],"generalizability":[47],"trained":[50],"In":[52],"this":[53],"paper,":[54],"we":[55],"introduce":[56],"novel":[58],"Federated":[60],"Learning":[61],"method":[62,151],"named":[63],"FedCEMA,":[64],"which":[65],"tailors":[66],"different":[70],"scenarios":[71],"heterogeneity.":[74],"FedCEMA":[75,120],"extracts":[76],"prototype":[77],"feature":[78],"align":[80],"objectives":[82],"with":[83,110],"global":[85],"optimum,":[86],"then":[88],"calculates":[89],"client-specific":[90],"linear":[91],"combinations":[92],"classifiers":[94],"similarity":[98],"between":[99],"clients.This":[100],"allows":[101],"clients":[102],"collaborate":[104],"effectively":[105],"by":[106],"learning":[107],"from":[108],"those":[109],"similar":[111],"distributions,":[113],"while":[114],"maintaining":[115],"model":[117],"benefits.":[118],"Additionally,":[119],"employs":[121],"Classifier":[123],"Exponential":[124],"Moving":[125],"Average":[126],"(CEMA)":[127],"method,":[128],"incorporating":[129],"previously":[130],"acquired":[131],"knowledge":[132],"enhance":[134],"stability":[136,156],"efficiency":[138],"model.":[141],"Extensive":[142],"experimental":[143],"results":[144],"benchmark":[146],"datasets":[147],"demonstrate":[148],"that":[149],"our":[150],"improves":[152],"both":[153],"accuracy":[154],"compared":[157],"baselines.":[159]},"counts_by_year":[{"year":2025,"cited_by_count":1}],"updated_date":"2026-03-22T08:09:32.410652","created_date":"2025-10-10T00:00:00"}