{"id":"https://openalex.org/W7129087232","doi":"https://doi.org/10.1109/access.2026.3665401","title":"FedPA: A Performance-Based Approach for Resource-Optimized and Imbalance-Resilient Federated Learning","display_name":"FedPA: A Performance-Based Approach for Resource-Optimized and Imbalance-Resilient Federated Learning","publication_year":2026,"publication_date":"2026-01-01","ids":{"openalex":"https://openalex.org/W7129087232","doi":"https://doi.org/10.1109/access.2026.3665401"},"language":"en","primary_location":{"id":"doi:10.1109/access.2026.3665401","is_oa":true,"landing_page_url":"https://doi.org/10.1109/access.2026.3665401","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.2026.3665401","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5000205588","display_name":"Atif Mahmood","orcid":"https://orcid.org/0000-0002-0069-6955"},"institutions":[{"id":"https://openalex.org/I12649496","display_name":"INTI International University","ror":"https://ror.org/03fj82m46","country_code":"MY","type":"education","lineage":["https://openalex.org/I12649496"]}],"countries":["MY"],"is_corresponding":false,"raw_author_name":"Atif Mahmood","raw_affiliation_strings":["Faculty of Data Science and Information and Technology, INTI International University, Putra Nilai, Malaysia"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Faculty of Data Science and Information and Technology, INTI International University, Putra Nilai, Malaysia","institution_ids":["https://openalex.org/I12649496"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5026797013","display_name":"Adnan N. Qureshi","orcid":"https://orcid.org/0000-0003-4505-630X"},"institutions":[{"id":"https://openalex.org/I210300861","display_name":"Newman University","ror":"https://ror.org/009tnsj43","country_code":"GB","type":"education","lineage":["https://openalex.org/I210300861"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Adnan N. Qureshi","raw_affiliation_strings":["Faculty of Arts, Society, and Professional Studies, Birmingham Newman University, Birmingham, U.K"],"raw_orcid":"https://orcid.org/0000-0003-4505-630X","affiliations":[{"raw_affiliation_string":"Faculty of Arts, Society, and Professional Studies, Birmingham Newman University, Birmingham, U.K","institution_ids":["https://openalex.org/I210300861"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5018058989","display_name":"Muhammad Umair Munir","orcid":"https://orcid.org/0000-0001-5651-7795"},"institutions":[{"id":"https://openalex.org/I33849332","display_name":"University of Malaya","ror":"https://ror.org/00rzspn62","country_code":"MY","type":"education","lineage":["https://openalex.org/I33849332"]}],"countries":["MY"],"is_corresponding":false,"raw_author_name":"Muhammad Umair Munir","raw_affiliation_strings":["Department of Computer System and Technology, Faculty of Computer Science and Information Technology, Universiti Malaya, Kuala Lumpur, Malaysia"],"raw_orcid":"https://orcid.org/0000-0001-5651-7795","affiliations":[{"raw_affiliation_string":"Department of Computer System and Technology, Faculty of Computer Science and Information Technology, Universiti Malaya, Kuala Lumpur, Malaysia","institution_ids":["https://openalex.org/I33849332"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Roziana Ramli","orcid":"https://orcid.org/0000-0002-3763-3149"},"institutions":[{"id":"https://openalex.org/I32394136","display_name":"Northumbria University","ror":"https://ror.org/049e6bc10","country_code":"GB","type":"education","lineage":["https://openalex.org/I32394136"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Roziana Ramli","raw_affiliation_strings":["Department of Computer and Information Sciences, Northumbria University, Newcastle, U.K"],"raw_orcid":"https://orcid.org/0000-0002-3763-3149","affiliations":[{"raw_affiliation_string":"Department of Computer and Information Sciences, Northumbria University, Newcastle, U.K","institution_ids":["https://openalex.org/I32394136"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5126145638","display_name":"Saaidal Razalli Azzuhri","orcid":null},"institutions":[{"id":"https://openalex.org/I33849332","display_name":"University of Malaya","ror":"https://ror.org/00rzspn62","country_code":"MY","type":"education","lineage":["https://openalex.org/I33849332"]}],"countries":["MY"],"is_corresponding":false,"raw_author_name":"Saaidal Razalli Azzuhri","raw_affiliation_strings":["Department of Computer System and Technology, Faculty of Computer Science and Information Technology, Universiti Malaya, Kuala Lumpur, Malaysia"],"raw_orcid":"https://orcid.org/0000-0001-8603-8840","affiliations":[{"raw_affiliation_string":"Department of Computer System and Technology, Faculty of Computer Science and Information Technology, Universiti Malaya, Kuala Lumpur, Malaysia","institution_ids":["https://openalex.org/I33849332"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":5,"corresponding_author_ids":[],"corresponding_institution_ids":[],"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":0.20804701,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"14","issue":null,"first_page":"42105","last_page":"42118"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10764","display_name":"Privacy-Preserving Technologies in Data","score":0.8658999800682068,"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":0.8658999800682068,"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/T13918","display_name":"Advanced Data and IoT Technologies","score":0.013799999840557575,"subfield":{"id":"https://openalex.org/subfields/2208","display_name":"Electrical and Electronic Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T10273","display_name":"IoT and Edge/Fog Computing","score":0.013500000350177288,"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/federated-learning","display_name":"Federated learning","score":0.8562999963760376},{"id":"https://openalex.org/keywords/scalability","display_name":"Scalability","score":0.6991999745368958},{"id":"https://openalex.org/keywords/mnist-database","display_name":"MNIST database","score":0.6916000247001648},{"id":"https://openalex.org/keywords/robustness","display_name":"Robustness (evolution)","score":0.6844000220298767},{"id":"https://openalex.org/keywords/software-deployment","display_name":"Software deployment","score":0.5687999725341797},{"id":"https://openalex.org/keywords/stochastic-gradient-descent","display_name":"Stochastic gradient descent","score":0.41600000858306885},{"id":"https://openalex.org/keywords/wireless","display_name":"Wireless","score":0.4124999940395355},{"id":"https://openalex.org/keywords/data-aggregator","display_name":"Data aggregator","score":0.40299999713897705}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8849999904632568},{"id":"https://openalex.org/C2992525071","wikidata":"https://www.wikidata.org/wiki/Q50818671","display_name":"Federated learning","level":2,"score":0.8562999963760376},{"id":"https://openalex.org/C48044578","wikidata":"https://www.wikidata.org/wiki/Q727490","display_name":"Scalability","level":2,"score":0.6991999745368958},{"id":"https://openalex.org/C190502265","wikidata":"https://www.wikidata.org/wiki/Q17069496","display_name":"MNIST database","level":3,"score":0.6916000247001648},{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.6844000220298767},{"id":"https://openalex.org/C120314980","wikidata":"https://www.wikidata.org/wiki/Q180634","display_name":"Distributed computing","level":1,"score":0.579800009727478},{"id":"https://openalex.org/C105339364","wikidata":"https://www.wikidata.org/wiki/Q2297740","display_name":"Software deployment","level":2,"score":0.5687999725341797},{"id":"https://openalex.org/C206688291","wikidata":"https://www.wikidata.org/wiki/Q7617819","display_name":"Stochastic gradient descent","level":3,"score":0.41600000858306885},{"id":"https://openalex.org/C555944384","wikidata":"https://www.wikidata.org/wiki/Q249","display_name":"Wireless","level":2,"score":0.4124999940395355},{"id":"https://openalex.org/C82578977","wikidata":"https://www.wikidata.org/wiki/Q16773055","display_name":"Data aggregator","level":3,"score":0.40299999713897705},{"id":"https://openalex.org/C2777303404","wikidata":"https://www.wikidata.org/wiki/Q759757","display_name":"Convergence (economics)","level":2,"score":0.3968999981880188},{"id":"https://openalex.org/C67186912","wikidata":"https://www.wikidata.org/wiki/Q367664","display_name":"Data modeling","level":2,"score":0.3359000086784363},{"id":"https://openalex.org/C153258448","wikidata":"https://www.wikidata.org/wiki/Q1199743","display_name":"Gradient descent","level":3,"score":0.3357999920845032},{"id":"https://openalex.org/C2779582901","wikidata":"https://www.wikidata.org/wiki/Q21013010","display_name":"Distributed learning","level":2,"score":0.320499986410141},{"id":"https://openalex.org/C2777212361","wikidata":"https://www.wikidata.org/wiki/Q5127848","display_name":"Class (philosophy)","level":2,"score":0.31949999928474426},{"id":"https://openalex.org/C29202148","wikidata":"https://www.wikidata.org/wiki/Q287260","display_name":"Resource allocation","level":2,"score":0.3156999945640564},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3118000030517578},{"id":"https://openalex.org/C123201435","wikidata":"https://www.wikidata.org/wiki/Q456632","display_name":"Information privacy","level":2,"score":0.3109999895095825},{"id":"https://openalex.org/C206345919","wikidata":"https://www.wikidata.org/wiki/Q20380951","display_name":"Resource (disambiguation)","level":2,"score":0.30820000171661377},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.2906000018119812},{"id":"https://openalex.org/C137822555","wikidata":"https://www.wikidata.org/wiki/Q2587068","display_name":"Information sensitivity","level":2,"score":0.2727999985218048},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.2653999924659729}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/access.2026.3665401","is_oa":true,"landing_page_url":"https://doi.org/10.1109/access.2026.3665401","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"},{"id":"pmh:oai:doaj.org/article:62d23ea2054347c2aa46161ed87709e4","is_oa":true,"landing_page_url":"https://doaj.org/article/62d23ea2054347c2aa46161ed87709e4","pdf_url":null,"source":{"id":"https://openalex.org/S4306401280","display_name":"DOAJ (DOAJ: Directory of Open Access Journals)","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":"repository"},"license":"cc-by-sa","license_id":"https://openalex.org/licenses/cc-by-sa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"IEEE Access, Vol 14, Pp 42105-42118 (2026)","raw_type":"article"}],"best_oa_location":{"id":"doi:10.1109/access.2026.3665401","is_oa":true,"landing_page_url":"https://doi.org/10.1109/access.2026.3665401","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":[{"score":0.5923454761505127,"id":"https://metadata.un.org/sdg/9","display_name":"Industry, innovation and infrastructure"}],"awards":[],"funders":[{"id":"https://openalex.org/F4320322604","display_name":"Universiti Malaya","ror":"https://ror.org/00rzspn62"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Federated":[0,32,36,90],"Learning":[1],"(FL)":[2],"has":[3],"emerged":[4],"as":[5,18],"a":[6,94,157],"pivotal":[7],"framework":[8],"for":[9,131,213,250],"privacy-preserving":[10],"collaborative":[11],"model":[12,68,129],"training,":[13],"especially":[14],"in":[15,48,194,221,226],"domains":[16],"such":[17],"healthcare,":[19],"telecommunication,":[20],"finance":[21],"where":[22,230],"data":[23,50,79,190],"sensitivity":[24],"is":[25],"paramount.":[26],"While":[27],"traditional":[28],"FL":[29,219,254],"techniques":[30],"like":[31,208],"Averaging":[33,92],"(FedAvg)":[34],"and":[35,43,73,80,109,145,170,189,198,215,234,252],"Stochastic":[37],"Gradient":[38],"Descent":[39],"(FedSGD)":[40],"offer":[41],"simplicity":[42],"efficiency,":[44],"they":[45],"often":[46],"struggle":[47],"heterogeneous":[49],"environments":[51],"due":[52],"to":[53,65,126,179,185],"equal":[54],"treatment":[55],"of":[56,61,140,218],"all":[57],"client":[58,81],"contributions,":[59,142],"regardless":[60],"quality.":[62],"This":[63,134],"leads":[64],"degraded":[66],"global":[67,119,128],"performance,":[69],"high":[70],"communication":[71,147,176,199,235],"overhead,":[72],"slow":[74],"convergence,":[75,144],"particularly":[76],"under":[77,156],"non-IID":[78,159],"variability.":[82],"To":[83],"address":[84],"these":[85],"limitations,":[86],"we":[87],"propose":[88],"Performance-Based":[89],"Partial":[91],"(FedPA),":[93],"novel":[95],"aggregation":[96,206,243],"method":[97],"that":[98,165,204],"selectively":[99],"incorporates":[100],"updates":[101,117,130],"from":[102,118],"high-performing":[103],"clients":[104,125],"based":[105],"on":[106],"local":[107],"accuracy":[108,169],"F1-score":[110],"thresholds.":[111],"Unlike":[112],"FedAvg,":[113],"FedPA":[114,151,166,182,209,239],"excludes":[115],"low-performing":[116],"aggregation,":[120],"while":[121],"still":[122],"allowing":[123],"underperforming":[124],"receive":[127],"progressive":[132],"learning.":[133],"approach":[135],"mitigates":[136],"the":[137,153,248],"adverse":[138],"effects":[139],"noisy":[141],"accelerates":[143],"reduces":[146],"overhead.":[148],"We":[149],"validate":[150],"using":[152],"MNIST":[154],"dataset":[155],"simulated":[158],"federated":[160],"setting.":[161],"Experimental":[162],"results":[163],"show":[164],"achieves":[167],"competitive":[168],"F1":[171],"scores":[172],"with":[173,244],"significantly":[174],"fewer":[175],"rounds":[177],"compared":[178],"FedAvg.":[180],"Additionally,":[181],"demonstrates":[183],"robustness":[184],"client-side":[186],"class":[187],"imbalance":[188],"heterogeneity,":[191],"outperforming":[192],"baselines":[193],"fairness,":[195],"convergence":[196],"stability,":[197],"efficiency.":[200],"Our":[201],"findings":[202],"suggest":[203],"performance-aware":[205],"strategies":[207],"hold":[210],"strong":[211],"potential":[212],"scalable":[214],"equitable":[216],"deployment":[217,255],"systems":[220],"real-world,":[222],"data-sensitive":[223],"applications.":[224],"Especially":[225],"5G":[227],"wireless":[228],"networks,":[229],"optimized":[231],"resource":[232,245],"allocation":[233],"efficiency":[236],"are":[237],"essential,":[238],"effectively":[240],"aligns":[241],"performance-driven":[242],"constraints,":[246],"paving":[247],"way":[249],"intelligent":[251],"adaptive":[253],"across":[256],"edge-cloud":[257],"infrastructures.":[258]},"counts_by_year":[],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2026-02-17T00:00:00"}