{"id":"https://openalex.org/W4406458779","doi":"https://doi.org/10.1109/bigdata62323.2024.10825786","title":"Personalized Federated Learning by Domain-Aware Network Pruning and Re-growth","display_name":"Personalized Federated Learning by Domain-Aware Network Pruning and Re-growth","publication_year":2024,"publication_date":"2024-12-15","ids":{"openalex":"https://openalex.org/W4406458779","doi":"https://doi.org/10.1109/bigdata62323.2024.10825786"},"language":"en","primary_location":{"id":"doi:10.1109/bigdata62323.2024.10825786","is_oa":false,"landing_page_url":"https://doi.org/10.1109/bigdata62323.2024.10825786","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 IEEE International Conference on Big Data (BigData)","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/A5072412284","display_name":"Yuto Suzuki","orcid":"https://orcid.org/0000-0001-5018-7596"},"institutions":[{"id":"https://openalex.org/I921990950","display_name":"University of Colorado Denver","ror":"https://ror.org/02hh7en24","country_code":"US","type":"education","lineage":["https://openalex.org/I921990950"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Yuto Suzuki","raw_affiliation_strings":["University of Colorado Denver,Department of Computer Science and Engineering,Denver,Colorado,USA"],"affiliations":[{"raw_affiliation_string":"University of Colorado Denver,Department of Computer Science and Engineering,Denver,Colorado,USA","institution_ids":["https://openalex.org/I921990950"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5007232242","display_name":"Farnoush Banaei\u2010Kashani","orcid":"https://orcid.org/0000-0003-4102-9873"},"institutions":[{"id":"https://openalex.org/I921990950","display_name":"University of Colorado Denver","ror":"https://ror.org/02hh7en24","country_code":"US","type":"education","lineage":["https://openalex.org/I921990950"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Farnoush Banaei-Kashani","raw_affiliation_strings":["University of Colorado Denver,Department of Computer Science and Engineering,Denver,Colorado,USA"],"affiliations":[{"raw_affiliation_string":"University of Colorado Denver,Department of Computer Science and Engineering,Denver,Colorado,USA","institution_ids":["https://openalex.org/I921990950"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5072412284"],"corresponding_institution_ids":["https://openalex.org/I921990950"],"apc_list":null,"apc_paid":null,"fwci":0.3637,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.70835132,"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":"1464","last_page":"1469"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10764","display_name":"Privacy-Preserving Technologies in Data","score":1.0,"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":1.0,"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/T11612","display_name":"Stochastic Gradient Optimization Techniques","score":0.996999979019165,"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/T10237","display_name":"Cryptography and Data Security","score":0.9929999709129333,"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":0.7987542748451233},{"id":"https://openalex.org/keywords/pruning","display_name":"Pruning","score":0.7665256261825562},{"id":"https://openalex.org/keywords/domain","display_name":"Domain (mathematical analysis)","score":0.5852102041244507},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.47323641180992126},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.3740542232990265}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7987542748451233},{"id":"https://openalex.org/C108010975","wikidata":"https://www.wikidata.org/wiki/Q500094","display_name":"Pruning","level":2,"score":0.7665256261825562},{"id":"https://openalex.org/C36503486","wikidata":"https://www.wikidata.org/wiki/Q11235244","display_name":"Domain (mathematical analysis)","level":2,"score":0.5852102041244507},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.47323641180992126},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3740542232990265},{"id":"https://openalex.org/C6557445","wikidata":"https://www.wikidata.org/wiki/Q173113","display_name":"Agronomy","level":1,"score":0.0},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0},{"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/bigdata62323.2024.10825786","is_oa":false,"landing_page_url":"https://doi.org/10.1109/bigdata62323.2024.10825786","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 IEEE International Conference on Big Data (BigData)","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":32,"referenced_works":["https://openalex.org/W2805003733","https://openalex.org/W2807006176","https://openalex.org/W2963819344","https://openalex.org/W2972570881","https://openalex.org/W2980910578","https://openalex.org/W3048121440","https://openalex.org/W3118608800","https://openalex.org/W3133814152","https://openalex.org/W3203587904","https://openalex.org/W4221138565","https://openalex.org/W4225796852","https://openalex.org/W4255788608","https://openalex.org/W4281778696","https://openalex.org/W4287906413","https://openalex.org/W4297799876","https://openalex.org/W4300427714","https://openalex.org/W4320167271","https://openalex.org/W6668990524","https://openalex.org/W6728757088","https://openalex.org/W6736057607","https://openalex.org/W6738383168","https://openalex.org/W6751979845","https://openalex.org/W6752029299","https://openalex.org/W6767676916","https://openalex.org/W6769871928","https://openalex.org/W6770699648","https://openalex.org/W6772318479","https://openalex.org/W6781891088","https://openalex.org/W6809980434","https://openalex.org/W6839016350","https://openalex.org/W6842749662","https://openalex.org/W6849918048"],"related_works":["https://openalex.org/W2961085424","https://openalex.org/W4306674287","https://openalex.org/W4387369504","https://openalex.org/W3046775127","https://openalex.org/W4394896187","https://openalex.org/W3170094116","https://openalex.org/W4386462264","https://openalex.org/W3107602296","https://openalex.org/W4364306694","https://openalex.org/W4312192474"],"abstract_inverted_index":{"Federated":[0],"learning":[1,6,15,60],"(FL)":[2],"is":[3,29,70,84,131],"a":[4,56,89],"machine":[5,14],"paradigm":[7],"where":[8],"multiple":[9],"clients":[10,119],"train":[11],"their":[12],"local":[13],"models":[16],"collaboratively":[17],"(without":[18],"sharing":[19,105,123],"private":[20],"data).":[21],"One":[22],"of":[23,32,94,117,143],"the":[24,33,134,140,144,149,171],"main":[25],"challenges":[26],"in":[27,96,100,139,158],"FL":[28,39],"statistical":[30,42],"heterogeneity":[31,43,93],"data":[34],"distributions":[35],"across":[36,48],"clients.":[37,50,126],"Personalized":[38],"(PFL)":[40],"mitigates":[41],"by":[44,61,86],"collaborative":[45],"model":[46,129,159],"training":[47],"homogeneous":[49],"In":[51],"this":[52],"paper,":[53],"we":[54,165],"propose":[55],"novel":[57],"personalized":[58],"federated":[59],"domain-aware":[62],"network":[63,98,104,112,122],"pruning":[64,99],"and":[65,109,156],"re-growth,":[66],"called":[67],"FedDNPR,":[68,128],"that":[69,167],"more":[71],"accurate":[72],"as":[73,148],"compared":[74],"to":[75,102,120,152],"existing":[76],"PFL":[77,173],"methods":[78],"while":[79,175],"maintaining":[80,176],"high":[81],"efficiency.":[82,178],"This":[83],"achieved":[85],"1)":[87],"introducing":[88],"regularization":[90],"term":[91],"capturing":[92],"weights":[95,116],"iterative":[97,111],"order":[101],"reduce":[103],"among":[106,124],"unrelated":[107],"clients,":[108],"2)":[110],"re-growing":[113],"only":[114],"from":[115],"related":[118,125],"increase":[121],"With":[127,161],"clustering":[130],"performed":[132],"considering":[133],"similarity":[135,150],"between":[136],"gradient":[137],"updates":[138],"last":[141],"layers":[142],"networks,":[145],"with":[146],"cosine":[147],"measure":[151],"achieve":[153],"both":[154],"accuracy":[155],"efficiency":[157],"personalization.":[160],"extensive":[162],"experimental":[163],"evaluation,":[164],"show":[166],"FedDNPR":[168],"significantly":[169],"outperforms":[170],"state-of-the-art":[172],"approaches,":[174],"comparable":[177]},"counts_by_year":[{"year":2025,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}