{"id":"https://openalex.org/W7124176275","doi":"https://doi.org/10.1109/access.2026.3654095","title":"Federated Learning With Dynamic Pruning for Efficient Model Aggregation in Heterogeneous Environments","display_name":"Federated Learning With Dynamic Pruning for Efficient Model Aggregation in Heterogeneous Environments","publication_year":2026,"publication_date":"2026-01-01","ids":{"openalex":"https://openalex.org/W7124176275","doi":"https://doi.org/10.1109/access.2026.3654095"},"language":null,"primary_location":{"id":"doi:10.1109/access.2026.3654095","is_oa":true,"landing_page_url":"https://doi.org/10.1109/access.2026.3654095","pdf_url":null,"source":{"id":"https://openalex.org/S2485537415","display_name":"IEEE Access","issn_l":"2169-3536","issn":["2169-3536"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Access","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","doaj"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://doi.org/10.1109/access.2026.3654095","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5079755036","display_name":"Lin-Huang Chang","orcid":"https://orcid.org/0000-0002-1826-1992"},"institutions":[{"id":"https://openalex.org/I34574549","display_name":"National Taichung University of Education","ror":"https://ror.org/006tnfe02","country_code":"TW","type":"education","lineage":["https://openalex.org/I34574549"]}],"countries":["TW"],"is_corresponding":true,"raw_author_name":"Lin-Huang Chang","raw_affiliation_strings":["Department of Computer Science, National Taichung University of Education, Taichung, Taiwan"],"affiliations":[{"raw_affiliation_string":"Department of Computer Science, National Taichung University of Education, Taichung, Taiwan","institution_ids":["https://openalex.org/I34574549"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5123049179","display_name":"Jian-Wei Huang","orcid":null},"institutions":[{"id":"https://openalex.org/I34574549","display_name":"National Taichung University of Education","ror":"https://ror.org/006tnfe02","country_code":"TW","type":"education","lineage":["https://openalex.org/I34574549"]}],"countries":["TW"],"is_corresponding":false,"raw_author_name":"Jian-Wei Huang","raw_affiliation_strings":["Department of Computer Science, National Taichung University of Education, Taichung, Taiwan"],"affiliations":[{"raw_affiliation_string":"Department of Computer Science, National Taichung University of Education, Taichung, Taiwan","institution_ids":["https://openalex.org/I34574549"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5101574964","display_name":"Tsung-Han Lee","orcid":"https://orcid.org/0000-0003-3282-0479"},"institutions":[{"id":"https://openalex.org/I34574549","display_name":"National Taichung University of Education","ror":"https://ror.org/006tnfe02","country_code":"TW","type":"education","lineage":["https://openalex.org/I34574549"]}],"countries":["TW"],"is_corresponding":false,"raw_author_name":"Tsung-Han Lee","raw_affiliation_strings":["Department of Computer Science, National Taichung University of Education, Taichung, Taiwan"],"affiliations":[{"raw_affiliation_string":"Department of Computer Science, National Taichung University of Education, Taichung, Taiwan","institution_ids":["https://openalex.org/I34574549"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5079755036"],"corresponding_institution_ids":["https://openalex.org/I34574549"],"apc_list":{"value":1850,"currency":"USD","value_usd":1850},"apc_paid":{"value":1850,"currency":"USD","value_usd":1850},"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.1056229,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"14","issue":null,"first_page":"8972","last_page":"8993"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11598","display_name":"Internet Traffic Analysis and Secure E-voting","score":0.5479999780654907,"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/T11598","display_name":"Internet Traffic Analysis and Secure E-voting","score":0.5479999780654907,"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/T10764","display_name":"Privacy-Preserving Technologies in Data","score":0.06989999860525131,"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/T10714","display_name":"Software-Defined Networks and 5G","score":0.05290000140666962,"subfield":{"id":"https://openalex.org/subfields/1705","display_name":"Computer Networks and Communications"},"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/pruning","display_name":"Pruning","score":0.8528000116348267},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.6628000140190125},{"id":"https://openalex.org/keywords/data-aggregator","display_name":"Data aggregator","score":0.4336000084877014},{"id":"https://openalex.org/keywords/trimming","display_name":"Trimming","score":0.4156000018119812},{"id":"https://openalex.org/keywords/convolutional-neural-network","display_name":"Convolutional neural network","score":0.4097000062465668},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.3887999951839447},{"id":"https://openalex.org/keywords/aggregate","display_name":"Aggregate (composite)","score":0.3700999915599823},{"id":"https://openalex.org/keywords/generalizability-theory","display_name":"Generalizability theory","score":0.36899998784065247}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8862000107765198},{"id":"https://openalex.org/C108010975","wikidata":"https://www.wikidata.org/wiki/Q500094","display_name":"Pruning","level":2,"score":0.8528000116348267},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.6628000140190125},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4756999909877777},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.4717000126838684},{"id":"https://openalex.org/C82578977","wikidata":"https://www.wikidata.org/wiki/Q16773055","display_name":"Data aggregator","level":3,"score":0.4336000084877014},{"id":"https://openalex.org/C56951928","wikidata":"https://www.wikidata.org/wiki/Q3539213","display_name":"Trimming","level":2,"score":0.4156000018119812},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.4153999984264374},{"id":"https://openalex.org/C81363708","wikidata":"https://www.wikidata.org/wiki/Q17084460","display_name":"Convolutional neural network","level":2,"score":0.4097000062465668},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.3887999951839447},{"id":"https://openalex.org/C4679612","wikidata":"https://www.wikidata.org/wiki/Q866298","display_name":"Aggregate (composite)","level":2,"score":0.3700999915599823},{"id":"https://openalex.org/C27158222","wikidata":"https://www.wikidata.org/wiki/Q5532422","display_name":"Generalizability theory","level":2,"score":0.36899998784065247},{"id":"https://openalex.org/C179799912","wikidata":"https://www.wikidata.org/wiki/Q205084","display_name":"Computational complexity theory","level":2,"score":0.3628000020980835},{"id":"https://openalex.org/C2777303404","wikidata":"https://www.wikidata.org/wiki/Q759757","display_name":"Convergence (economics)","level":2,"score":0.3546999990940094},{"id":"https://openalex.org/C120314980","wikidata":"https://www.wikidata.org/wiki/Q180634","display_name":"Distributed computing","level":1,"score":0.3531000018119812},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.34950000047683716},{"id":"https://openalex.org/C157764524","wikidata":"https://www.wikidata.org/wiki/Q1383412","display_name":"Throughput","level":3,"score":0.3269999921321869},{"id":"https://openalex.org/C158207573","wikidata":"https://www.wikidata.org/wiki/Q5747224","display_name":"Heterogeneous network","level":4,"score":0.31540000438690186},{"id":"https://openalex.org/C2777210771","wikidata":"https://www.wikidata.org/wiki/Q4927124","display_name":"Block (permutation group theory)","level":2,"score":0.3138999938964844},{"id":"https://openalex.org/C67186912","wikidata":"https://www.wikidata.org/wiki/Q367664","display_name":"Data modeling","level":2,"score":0.2906000018119812},{"id":"https://openalex.org/C206345919","wikidata":"https://www.wikidata.org/wiki/Q20380951","display_name":"Resource (disambiguation)","level":2,"score":0.27379998564720154},{"id":"https://openalex.org/C165435473","wikidata":"https://www.wikidata.org/wiki/Q1509884","display_name":"Padding","level":2,"score":0.2635999917984009},{"id":"https://openalex.org/C172430144","wikidata":"https://www.wikidata.org/wiki/Q17111997","display_name":"Symmetric multiprocessor system","level":2,"score":0.2563000023365021},{"id":"https://openalex.org/C141513077","wikidata":"https://www.wikidata.org/wiki/Q378542","display_name":"Independent and identically distributed random variables","level":3,"score":0.25060001015663147}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/access.2026.3654095","is_oa":true,"landing_page_url":"https://doi.org/10.1109/access.2026.3654095","pdf_url":null,"source":{"id":"https://openalex.org/S2485537415","display_name":"IEEE Access","issn_l":"2169-3536","issn":["2169-3536"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Access","raw_type":"journal-article"}],"best_oa_location":{"id":"doi:10.1109/access.2026.3654095","is_oa":true,"landing_page_url":"https://doi.org/10.1109/access.2026.3654095","pdf_url":null,"source":{"id":"https://openalex.org/S2485537415","display_name":"IEEE Access","issn_l":"2169-3536","issn":["2169-3536"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Access","raw_type":"journal-article"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/8","display_name":"Decent work and economic growth","score":0.5128862857818604}],"awards":[{"id":"https://openalex.org/G4979360580","display_name":null,"funder_award_id":"MOST 111-2221-E-142-002-MY2","funder_id":"https://openalex.org/F4320331164","funder_display_name":"National Science and Technology Council"},{"id":"https://openalex.org/G5097494901","display_name":null,"funder_award_id":"NSTC 113-2221-E-142-005-MY2","funder_id":"https://openalex.org/F4320331164","funder_display_name":"National Science and Technology Council"},{"id":"https://openalex.org/G5748155443","display_name":null,"funder_award_id":"MOST 111-2221-E-142 -002 -MY2","funder_id":"https://openalex.org/F4320331164","funder_display_name":"National Science and Technology Council"}],"funders":[{"id":"https://openalex.org/F4320331164","display_name":"National Science and Technology Council","ror":"https://ror.org/00wnb9798"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":18,"referenced_works":["https://openalex.org/W2096118443","https://openalex.org/W2112169033","https://openalex.org/W2928560789","https://openalex.org/W3045474099","https://openalex.org/W3159845898","https://openalex.org/W3165464242","https://openalex.org/W3204468048","https://openalex.org/W3204874618","https://openalex.org/W4200034442","https://openalex.org/W4213016094","https://openalex.org/W4226319939","https://openalex.org/W4312424218","https://openalex.org/W4312869277","https://openalex.org/W4390190717","https://openalex.org/W4391896150","https://openalex.org/W4396520561","https://openalex.org/W4404101286","https://openalex.org/W4410056266"],"related_works":[],"abstract_inverted_index":{"With":[0],"the":[1,53,58,142,167,177,203,220],"widespread":[2],"adoption":[3],"of":[4,144,171,205],"5G":[5],"networks,":[6],"Federated":[7],"Learning":[8],"(FL)":[9],"has":[10],"gradually":[11],"become":[12],"an":[13],"important":[14],"paradigm":[15],"for":[16,98],"distributed":[17],"artificial":[18],"intelligence.":[19],"However,":[20],"clients":[21,129],"in":[22,29,71,87,166],"FL":[23,100,179,209],"environments":[24],"often":[25],"exhibit":[26],"significant":[27],"heterogeneity":[28,44],"computational":[30,59],"resources":[31,139],"and":[32,35,38,76,149,183,211,234],"data":[33],"distributions,":[34],"under":[36,160],"Non-Independent":[37],"Identically":[39],"Distributed":[40],"(Non-IID)":[41],"scenarios,":[42],"such":[43],"not":[45],"only":[46],"slows":[47],"model":[48,88,232],"convergence":[49],"but":[50],"also":[51],"affects":[52],"final":[54],"accuracy.":[55],"To":[56,105],"reduce":[57],"burden":[60],"on":[61,136,154],"clients,":[62],"this":[63,107],"study":[64],"adopts":[65],"structured":[66],"pruning":[67,79,93,121,133,195],"by":[68,181,187],"trimming":[69],"filters":[70],"convolutional":[72],"neural":[73],"networks":[74],"(CNNs)":[75],"dynamically":[77],"adjusting":[78],"ratios":[80,94,134],"according":[81],"to":[82,102,130,197],"client":[83],"resources.":[84],"Nevertheless,":[85],"variations":[86],"structures":[89],"resulting":[90],"from":[91],"different":[92],"make":[95],"it":[96],"difficult":[97],"traditional":[99],"aggregation":[101,125,145],"maintain":[103],"consistency.":[104],"address":[106],"issue,":[108],"we":[109,201],"propose":[110],"FedCHAP":[111,127,175,206,224],"(Federated":[112],"Customized":[113],"Heterogeneous":[114],"Aggregation":[115],"with":[116,122,190],"Pruning),":[117],"which":[118],"integrates":[119],"dynamic":[120],"a":[123,155,192],"heterogeneous":[124],"mechanism.":[126],"enables":[128],"flexibly":[131],"adjust":[132],"based":[135],"their":[137],"available":[138],"while":[140,230],"ensuring":[141],"feasibility":[143],"through":[146],"padding":[147],"weight":[148],"structural":[150],"alignment.":[151],"Experiments":[152],"conducted":[153],"network":[156],"traffic":[157],"classification":[158],"dataset":[159],"multiple":[161],"Non-IID":[162],"scenarios":[163],"demonstrate":[164,212],"that,":[165],"most":[168],"extreme":[169],"case":[170],"quantity-based":[172],"label":[173],"imbalance,":[174],"reduced":[176],"overall":[178],"runtime":[180],"8.1%":[182],"improved":[184],"global":[185],"accuracy":[186],"4%":[188],"compared":[189],"applying":[191],"fixed":[193],"30%":[194],"ratio":[196],"all":[198],"clients.":[199],"Furthermore,":[200],"benchmark":[202],"performance":[204,233],"against":[207],"state-of-the-art":[208],"methods":[210],"its":[213],"generalizability":[214],"across":[215],"various":[216],"application":[217],"domains.":[218],"Overall,":[219],"findings":[221],"validate":[222],"that":[223],"can":[225],"effectively":[226],"lower":[227],"resource":[228],"consumption":[229],"preserving":[231],"stability.":[235]},"counts_by_year":[],"updated_date":"2026-04-09T08:11:56.329763","created_date":"2026-01-15T00:00:00"}