{"id":"https://openalex.org/W4417282978","doi":"https://doi.org/10.1109/pimrc62392.2025.11274718","title":"FedPLT: Scalable, Resource-Efficient, and Heterogeneity-Aware Federated Learning via Partial Layer Training <sup>\u2217</sup>","display_name":"FedPLT: Scalable, Resource-Efficient, and Heterogeneity-Aware Federated Learning via Partial Layer Training <sup>\u2217</sup>","publication_year":2025,"publication_date":"2025-09-01","ids":{"openalex":"https://openalex.org/W4417282978","doi":"https://doi.org/10.1109/pimrc62392.2025.11274718"},"language":null,"primary_location":{"id":"doi:10.1109/pimrc62392.2025.11274718","is_oa":false,"landing_page_url":"https://doi.org/10.1109/pimrc62392.2025.11274718","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE 36th International Symposium on Personal, Indoor and Mobile Radio Communications (PIMRC)","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/A5110292079","display_name":"Ali Dabaja","orcid":"https://orcid.org/0009-0007-0058-6143"},"institutions":[{"id":"https://openalex.org/I198415970","display_name":"Universit\u00e9 d'Avignon et des Pays de Vaucluse","ror":"https://ror.org/00mfpxb84","country_code":"FR","type":"education","lineage":["https://openalex.org/I198415970"]},{"id":"https://openalex.org/I4210119991","display_name":"Laboratoire Informatique d'Avignon","ror":"https://ror.org/02n399288","country_code":"FR","type":"facility","lineage":["https://openalex.org/I198415970","https://openalex.org/I4210119991"]}],"countries":["FR"],"is_corresponding":true,"raw_author_name":"Ahmad Dabaja","raw_affiliation_strings":["LIA/CERI Avignon University,France"],"affiliations":[{"raw_affiliation_string":"LIA/CERI Avignon University,France","institution_ids":["https://openalex.org/I198415970","https://openalex.org/I4210119991"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5078537181","display_name":"Rachid El-Azouzi","orcid":"https://orcid.org/0000-0002-4756-0887"},"institutions":[{"id":"https://openalex.org/I198415970","display_name":"Universit\u00e9 d'Avignon et des Pays de Vaucluse","ror":"https://ror.org/00mfpxb84","country_code":"FR","type":"education","lineage":["https://openalex.org/I198415970"]},{"id":"https://openalex.org/I4210119991","display_name":"Laboratoire Informatique d'Avignon","ror":"https://ror.org/02n399288","country_code":"FR","type":"facility","lineage":["https://openalex.org/I198415970","https://openalex.org/I4210119991"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"Rachid El-Azouzi","raw_affiliation_strings":["LIA/CERI Avignon University,France"],"affiliations":[{"raw_affiliation_string":"LIA/CERI Avignon University,France","institution_ids":["https://openalex.org/I198415970","https://openalex.org/I4210119991"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5110292079"],"corresponding_institution_ids":["https://openalex.org/I198415970","https://openalex.org/I4210119991"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.22205738,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"6"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10764","display_name":"Privacy-Preserving Technologies in Data","score":0.9387000203132629,"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":0.9387000203132629,"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/T14347","display_name":"Big Data and Digital Economy","score":0.005799999926239252,"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/T10273","display_name":"IoT and Edge/Fog Computing","score":0.004600000102072954,"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":0.6324999928474426},{"id":"https://openalex.org/keywords/variance","display_name":"Variance (accounting)","score":0.5479000210762024},{"id":"https://openalex.org/keywords/training","display_name":"Training (meteorology)","score":0.5202000141143799},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.4844000041484833},{"id":"https://openalex.org/keywords/layer","display_name":"Layer (electronics)","score":0.4796999990940094},{"id":"https://openalex.org/keywords/sampling","display_name":"Sampling (signal processing)","score":0.4715999960899353},{"id":"https://openalex.org/keywords/computation","display_name":"Computation","score":0.42100000381469727},{"id":"https://openalex.org/keywords/training-set","display_name":"Training set","score":0.414000004529953},{"id":"https://openalex.org/keywords/resource","display_name":"Resource (disambiguation)","score":0.37700000405311584}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.821399986743927},{"id":"https://openalex.org/C2992525071","wikidata":"https://www.wikidata.org/wiki/Q50818671","display_name":"Federated learning","level":2,"score":0.6324999928474426},{"id":"https://openalex.org/C196083921","wikidata":"https://www.wikidata.org/wiki/Q7915758","display_name":"Variance (accounting)","level":2,"score":0.5479000210762024},{"id":"https://openalex.org/C2777211547","wikidata":"https://www.wikidata.org/wiki/Q17141490","display_name":"Training (meteorology)","level":2,"score":0.5202000141143799},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.5074999928474426},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.4844000041484833},{"id":"https://openalex.org/C2779227376","wikidata":"https://www.wikidata.org/wiki/Q6505497","display_name":"Layer (electronics)","level":2,"score":0.4796999990940094},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.47600001096725464},{"id":"https://openalex.org/C140779682","wikidata":"https://www.wikidata.org/wiki/Q210868","display_name":"Sampling (signal processing)","level":3,"score":0.4715999960899353},{"id":"https://openalex.org/C120314980","wikidata":"https://www.wikidata.org/wiki/Q180634","display_name":"Distributed computing","level":1,"score":0.44620001316070557},{"id":"https://openalex.org/C45374587","wikidata":"https://www.wikidata.org/wiki/Q12525525","display_name":"Computation","level":2,"score":0.42100000381469727},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.414000004529953},{"id":"https://openalex.org/C206345919","wikidata":"https://www.wikidata.org/wiki/Q20380951","display_name":"Resource (disambiguation)","level":2,"score":0.37700000405311584},{"id":"https://openalex.org/C67186912","wikidata":"https://www.wikidata.org/wiki/Q367664","display_name":"Data modeling","level":2,"score":0.3246000111103058},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.2953999936580658},{"id":"https://openalex.org/C18762648","wikidata":"https://www.wikidata.org/wiki/Q42213","display_name":"Work (physics)","level":2,"score":0.2912999987602234},{"id":"https://openalex.org/C101765175","wikidata":"https://www.wikidata.org/wiki/Q577764","display_name":"Communications system","level":2,"score":0.28439998626708984},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.2816999852657318},{"id":"https://openalex.org/C190793597","wikidata":"https://www.wikidata.org/wiki/Q189768","display_name":"Application layer","level":3,"score":0.2775000035762787},{"id":"https://openalex.org/C77618280","wikidata":"https://www.wikidata.org/wiki/Q1155772","display_name":"Scheme (mathematics)","level":2,"score":0.27160000801086426},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.265500009059906},{"id":"https://openalex.org/C29202148","wikidata":"https://www.wikidata.org/wiki/Q287260","display_name":"Resource allocation","level":2,"score":0.25940001010894775},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.2578999996185303},{"id":"https://openalex.org/C2984842247","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep neural networks","level":3,"score":0.2574999928474426},{"id":"https://openalex.org/C2779582901","wikidata":"https://www.wikidata.org/wiki/Q21013010","display_name":"Distributed learning","level":2,"score":0.25429999828338623},{"id":"https://openalex.org/C557945733","wikidata":"https://www.wikidata.org/wiki/Q389772","display_name":"Data transmission","level":2,"score":0.25200000405311584}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/pimrc62392.2025.11274718","is_oa":false,"landing_page_url":"https://doi.org/10.1109/pimrc62392.2025.11274718","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE 36th International Symposium on Personal, Indoor and Mobile Radio Communications (PIMRC)","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":3,"referenced_works":["https://openalex.org/W3202260564","https://openalex.org/W4387105517","https://openalex.org/W4401753426"],"related_works":[],"abstract_inverted_index":{"Federated":[0],"Learning":[1,92],"(FL)":[2],"has":[3,26,54],"gained":[4],"significant":[5],"attention":[6],"in":[7,215,250],"distributed":[8],"machine":[9],"learning":[10,170],"by":[11,172,222,242],"enabling":[12],"collaborative":[13],"model":[14,139],"training":[15,60,102,199],"across":[16,74,141],"decentralized":[17],"devices":[18],"while":[19,202,253],"preserving":[20],"data":[21,29],"privacy.":[22],"Although":[23],"extensive":[24,182],"research":[25],"addressed":[27,55],"statistical":[28],"heterogeneity,":[30,47],"FL":[31],"still":[32],"faces":[33],"several":[34],"challenges,":[35],"including":[36],"high":[37],"communication":[38,120,179,251],"and":[39,44,61,80,83,99,112,121,136,163,229],"computation":[40],"overheads,":[41],"energy":[42],"inefficiency,":[43],"severe":[45],"device":[46],"which":[48],"require":[49],"further":[50],"investigation.":[51],"Prior":[52],"work":[53],"these":[56],"issues":[57],"through":[58],"sub-model":[59],"partial":[62,101],"parameter":[63,72,132],"updates.":[64],"However,":[65],"such":[66],"methods":[67,214],"often":[68],"suffer":[69],"from":[70],"inconsistent":[71],"distributions":[73],"clients,":[75],"inaccurate":[76],"global":[77],"loss":[78],"estimation,":[79],"increased":[81],"bias":[82],"variance.":[84],"In":[85,149],"this":[86,166],"paper,":[87],"we":[88,151,184],"propose":[89],"FedPLT":[90,144,156,187,236],"(Federated":[91],"with":[93,159],"Partial":[94],"Layer":[95],"Training),":[96],"a":[97,125],"novel":[98],"structured":[100],"approach":[103],"that":[104,165,186,196],"divides":[105],"neural":[106],"network":[107],"layers":[108],"into":[109],"equal-sized":[110],"sub-layers":[111],"assigns":[113],"them":[114],"to":[115,225,244,247],"clients":[116],"based":[117],"on":[118],"their":[119],"computational":[122],"capacities":[123],"using":[124],"fixed":[126],"assignment":[127],"strategy.":[128],"This":[129],"ensures":[130],"balanced":[131],"distribution,":[133],"reduces":[134],"variance,":[135],"supports":[137],"varying":[138],"sizes":[140],"devices,":[142],"making":[143],"well-suited":[145],"for":[146],"resource-constrained":[147],"environments.":[148],"addition,":[150],"examine":[152],"the":[153,177,216,231,239,255],"performance":[154,171,189,259],"of":[155,197,233,258],"when":[157],"combined":[158],"optimal":[160],"client":[161],"sampling":[162,174],"show":[164,185],"integration":[167],"enhances":[168],"federated":[169],"reducing":[173,230],"variance":[175],"under":[176,218],"same":[178,256],"constraints.":[180],"Through":[181],"experiments,":[183],"achieves":[188],"comparable":[190],"to,":[191,195],"or":[192],"even":[193],"superior":[194],"full-model":[198,261],"(i.e.,":[200],"FedAvg),":[201],"requiring":[203],"significantly":[204],"fewer":[205],"trainable":[206],"parameters":[207,241],"per":[208],"client.":[209],"It":[210],"also":[211],"outperforms":[212],"existing":[213],"literature":[217],"highly":[219],"heterogeneous":[220],"systems":[221],"efficiently":[223],"adapting":[224],"clients\u2019":[226],"resource":[227],"constraints":[228],"number":[232],"stragglers.":[234],"Moreover,":[235],"can":[237],"reduce":[238],"trained":[240],"up":[243],"65\u201385%,":[245],"leading":[246],"substantial":[248],"savings":[249],"costs,":[252],"maintaining":[254],"level":[257],"as":[260],"training.":[262]},"counts_by_year":[],"updated_date":"2026-03-07T16:01:11.037858","created_date":"2025-12-12T00:00:00"}