{"id":"https://openalex.org/W4415747950","doi":"https://doi.org/10.1109/tmc.2025.3627961","title":"Heterogeneity-Aware Federated Meta Learning for Personalized Edge Devices","display_name":"Heterogeneity-Aware Federated Meta Learning for Personalized Edge Devices","publication_year":2025,"publication_date":"2025-10-31","ids":{"openalex":"https://openalex.org/W4415747950","doi":"https://doi.org/10.1109/tmc.2025.3627961"},"language":null,"primary_location":{"id":"doi:10.1109/tmc.2025.3627961","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tmc.2025.3627961","pdf_url":null,"source":{"id":"https://openalex.org/S69141925","display_name":"IEEE Transactions on Mobile Computing","issn_l":"1536-1233","issn":["1536-1233","1558-0660","2161-9875"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320439","host_organization_name":"IEEE Computer Society","host_organization_lineage":["https://openalex.org/P4310320439","https://openalex.org/P4310319808"],"host_organization_lineage_names":["IEEE Computer Society","Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Mobile Computing","raw_type":"journal-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":null,"display_name":"Ying Zhu","orcid":"https://orcid.org/0009-0000-2534-6604"},"institutions":[{"id":"https://openalex.org/I126520041","display_name":"University of Science and Technology of China","ror":"https://ror.org/04c4dkn09","country_code":"CN","type":"education","lineage":["https://openalex.org/I126520041","https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Ying Zhu","raw_affiliation_strings":["University of Science and Technology of China, Hefei, China","University of Science and Technology of China, Hefei, Anhui, China"],"raw_orcid":"https://orcid.org/0009-0000-2534-6604","affiliations":[{"raw_affiliation_string":"University of Science and Technology of China, Hefei, China","institution_ids":["https://openalex.org/I126520041"]},{"raw_affiliation_string":"University of Science and Technology of China, Hefei, Anhui, China","institution_ids":["https://openalex.org/I126520041"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Yang Xu","orcid":"https://orcid.org/0000-0003-0839-3892"},"institutions":[{"id":"https://openalex.org/I126520041","display_name":"University of Science and Technology of China","ror":"https://ror.org/04c4dkn09","country_code":"CN","type":"education","lineage":["https://openalex.org/I126520041","https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yang Xu","raw_affiliation_strings":["University of Science and Technology of China, Hefei, China","University of Science and Technology of China, Hefei, Anhui, China"],"raw_orcid":"https://orcid.org/0000-0003-0839-3892","affiliations":[{"raw_affiliation_string":"University of Science and Technology of China, Hefei, China","institution_ids":["https://openalex.org/I126520041"]},{"raw_affiliation_string":"University of Science and Technology of China, Hefei, Anhui, China","institution_ids":["https://openalex.org/I126520041"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5110452404","display_name":"Hongli Xu","orcid":"https://orcid.org/0000-0003-3831-4577"},"institutions":[{"id":"https://openalex.org/I126520041","display_name":"University of Science and Technology of China","ror":"https://ror.org/04c4dkn09","country_code":"CN","type":"education","lineage":["https://openalex.org/I126520041","https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Hongli Xu","raw_affiliation_strings":["University of Science and Technology of China, Hefei, China","University of Science and Technology of China, Hefei, Anhui, China"],"raw_orcid":"https://orcid.org/0000-0003-3831-4577","affiliations":[{"raw_affiliation_string":"University of Science and Technology of China, Hefei, China","institution_ids":["https://openalex.org/I126520041"]},{"raw_affiliation_string":"University of Science and Technology of China, Hefei, Anhui, China","institution_ids":["https://openalex.org/I126520041"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5062964635","display_name":"Yunming Liao","orcid":"https://orcid.org/0000-0002-5065-2600"},"institutions":[{"id":"https://openalex.org/I126520041","display_name":"University of Science and Technology of China","ror":"https://ror.org/04c4dkn09","country_code":"CN","type":"education","lineage":["https://openalex.org/I126520041","https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yunming Liao","raw_affiliation_strings":["University of Science and Technology of China, Hefei, China","University of Science and Technology of China, Hefei, Anhui, China"],"raw_orcid":"https://orcid.org/0000-0002-5065-2600","affiliations":[{"raw_affiliation_string":"University of Science and Technology of China, Hefei, China","institution_ids":["https://openalex.org/I126520041"]},{"raw_affiliation_string":"University of Science and Technology of China, Hefei, Anhui, China","institution_ids":["https://openalex.org/I126520041"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5032224075","display_name":"Zhiwei Yao","orcid":"https://orcid.org/0009-0007-2284-3323"},"institutions":[{"id":"https://openalex.org/I126520041","display_name":"University of Science and Technology of China","ror":"https://ror.org/04c4dkn09","country_code":"CN","type":"education","lineage":["https://openalex.org/I126520041","https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhiwei Yao","raw_affiliation_strings":["University of Science and Technology of China, Hefei, China","University of Science and Technology of China, Hefei, Anhui, China"],"raw_orcid":"https://orcid.org/0009-0007-2284-3323","affiliations":[{"raw_affiliation_string":"University of Science and Technology of China, Hefei, China","institution_ids":["https://openalex.org/I126520041"]},{"raw_affiliation_string":"University of Science and Technology of China, Hefei, Anhui, China","institution_ids":["https://openalex.org/I126520041"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5019604942","display_name":"Liusheng Huang","orcid":"https://orcid.org/0000-0001-8417-3256"},"institutions":[{"id":"https://openalex.org/I126520041","display_name":"University of Science and Technology of China","ror":"https://ror.org/04c4dkn09","country_code":"CN","type":"education","lineage":["https://openalex.org/I126520041","https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Liusheng Huang","raw_affiliation_strings":["University of Science and Technology of China, Hefei, China","University of Science and Technology of China, Hefei, Anhui, China"],"raw_orcid":"https://orcid.org/0000-0001-8417-3256","affiliations":[{"raw_affiliation_string":"University of Science and Technology of China, Hefei, China","institution_ids":["https://openalex.org/I126520041"]},{"raw_affiliation_string":"University of Science and Technology of China, Hefei, Anhui, China","institution_ids":["https://openalex.org/I126520041"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":6,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I126520041"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.16172984,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"25","issue":"4","first_page":"5302","last_page":"5318"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10764","display_name":"Privacy-Preserving Technologies in Data","score":0.225600004196167,"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":0.225600004196167,"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":0.07370000332593918,"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":0.06509999930858612,"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/usable","display_name":"USable","score":0.6875},{"id":"https://openalex.org/keywords/stochastic-gradient-descent","display_name":"Stochastic gradient descent","score":0.647599995136261},{"id":"https://openalex.org/keywords/enhanced-data-rates-for-gsm-evolution","display_name":"Enhanced Data Rates for GSM Evolution","score":0.6399999856948853},{"id":"https://openalex.org/keywords/federated-learning","display_name":"Federated learning","score":0.6187000274658203},{"id":"https://openalex.org/keywords/personalization","display_name":"Personalization","score":0.5928000211715698},{"id":"https://openalex.org/keywords/metric","display_name":"Metric (unit)","score":0.5672000050544739},{"id":"https://openalex.org/keywords/edge-device","display_name":"Edge device","score":0.5128999948501587},{"id":"https://openalex.org/keywords/key","display_name":"Key (lock)","score":0.5005999803543091}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.9110999703407288},{"id":"https://openalex.org/C2780615836","wikidata":"https://www.wikidata.org/wiki/Q2471869","display_name":"USable","level":2,"score":0.6875},{"id":"https://openalex.org/C206688291","wikidata":"https://www.wikidata.org/wiki/Q7617819","display_name":"Stochastic gradient descent","level":3,"score":0.647599995136261},{"id":"https://openalex.org/C162307627","wikidata":"https://www.wikidata.org/wiki/Q204833","display_name":"Enhanced Data Rates for GSM Evolution","level":2,"score":0.6399999856948853},{"id":"https://openalex.org/C2992525071","wikidata":"https://www.wikidata.org/wiki/Q50818671","display_name":"Federated learning","level":2,"score":0.6187000274658203},{"id":"https://openalex.org/C183003079","wikidata":"https://www.wikidata.org/wiki/Q1000371","display_name":"Personalization","level":2,"score":0.5928000211715698},{"id":"https://openalex.org/C176217482","wikidata":"https://www.wikidata.org/wiki/Q860554","display_name":"Metric (unit)","level":2,"score":0.5672000050544739},{"id":"https://openalex.org/C138236772","wikidata":"https://www.wikidata.org/wiki/Q25098575","display_name":"Edge device","level":3,"score":0.5128999948501587},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.5005999803543091},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.4397999942302704},{"id":"https://openalex.org/C2780898871","wikidata":"https://www.wikidata.org/wiki/Q860554","display_name":"Performance metric","level":2,"score":0.4377000033855438},{"id":"https://openalex.org/C2777303404","wikidata":"https://www.wikidata.org/wiki/Q759757","display_name":"Convergence (economics)","level":2,"score":0.4235000014305115},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.41589999198913574},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.40119999647140503},{"id":"https://openalex.org/C114289077","wikidata":"https://www.wikidata.org/wiki/Q3284399","display_name":"Statistical model","level":2,"score":0.3880000114440918},{"id":"https://openalex.org/C2781002164","wikidata":"https://www.wikidata.org/wiki/Q6822311","display_name":"Meta learning (computer science)","level":3,"score":0.38510000705718994},{"id":"https://openalex.org/C153258448","wikidata":"https://www.wikidata.org/wiki/Q1199743","display_name":"Gradient descent","level":3,"score":0.36820000410079956},{"id":"https://openalex.org/C120314980","wikidata":"https://www.wikidata.org/wiki/Q180634","display_name":"Distributed computing","level":1,"score":0.3440000116825104},{"id":"https://openalex.org/C67186912","wikidata":"https://www.wikidata.org/wiki/Q367664","display_name":"Data modeling","level":2,"score":0.3237000107765198},{"id":"https://openalex.org/C2778456923","wikidata":"https://www.wikidata.org/wiki/Q5337692","display_name":"Edge computing","level":3,"score":0.32330000400543213},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.3091000020503998},{"id":"https://openalex.org/C170130773","wikidata":"https://www.wikidata.org/wiki/Q216378","display_name":"Usability","level":2,"score":0.2782999873161316},{"id":"https://openalex.org/C168167062","wikidata":"https://www.wikidata.org/wiki/Q1117970","display_name":"Component (thermodynamics)","level":2,"score":0.27570000290870667}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/tmc.2025.3627961","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tmc.2025.3627961","pdf_url":null,"source":{"id":"https://openalex.org/S69141925","display_name":"IEEE Transactions on Mobile Computing","issn_l":"1536-1233","issn":["1536-1233","1558-0660","2161-9875"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320439","host_organization_name":"IEEE Computer Society","host_organization_lineage":["https://openalex.org/P4310320439","https://openalex.org/P4310319808"],"host_organization_lineage_names":["IEEE Computer Society","Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Mobile Computing","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G5563275549","display_name":null,"funder_award_id":"624B2136","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G645416012","display_name":null,"funder_award_id":"62132019","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G7992979919","display_name":null,"funder_award_id":"62472401","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":35,"referenced_works":["https://openalex.org/W1825216778","https://openalex.org/W1995875735","https://openalex.org/W2149772057","https://openalex.org/W2273387967","https://openalex.org/W2293634267","https://openalex.org/W2618530766","https://openalex.org/W2624989916","https://openalex.org/W2990000708","https://openalex.org/W3042621011","https://openalex.org/W3080934299","https://openalex.org/W3089578458","https://openalex.org/W3104631511","https://openalex.org/W3130806609","https://openalex.org/W3133814152","https://openalex.org/W3163842339","https://openalex.org/W3183910508","https://openalex.org/W3194020564","https://openalex.org/W4210712880","https://openalex.org/W4285234583","https://openalex.org/W4285302300","https://openalex.org/W4292737460","https://openalex.org/W4293155325","https://openalex.org/W4306178637","https://openalex.org/W4312557211","https://openalex.org/W4312634912","https://openalex.org/W4315485876","https://openalex.org/W4377107432","https://openalex.org/W4385478307","https://openalex.org/W4385567577","https://openalex.org/W4385567904","https://openalex.org/W4386131770","https://openalex.org/W4401110031","https://openalex.org/W4402716118","https://openalex.org/W4413805483","https://openalex.org/W7133216270"],"related_works":[],"abstract_inverted_index":{"Recently,":[0],"aided":[1],"by":[2,21,262,270],"edge":[3,19,90],"computing":[4,141],"(EC),":[5],"federated":[6,25],"meta-learning":[7,23],"(FML)":[8],"has":[9],"been":[10],"proposed":[11],"to":[12,39,54,64,95,116,173,194,229,238,245,264,276],"adequately":[13],"utilize":[14],"personalized":[15],"data":[16,97],"on":[17,212,219],"different":[18,87,236],"devices":[20],"incorporating":[22],"with":[24,105,119,131,145],"learning":[26],"(FL).":[27],"Unlike":[28],"conventional":[29],"FL":[30],"which":[31,99,158,243],"conducts":[32],"several":[33],"stochastic":[34],"gradient":[35],"descent":[36],"(SGD)":[37],"steps":[38,209],"directly":[40],"update":[41,65],"the":[42,66,70,73,124,138,161,175,201,204,220,232,240,277],"local":[43,67,134],"model":[44,58,68,213,247,268],"in":[45,103,109,126,140,169,192],"each":[46,170],"training":[47,171,248,261],"round,":[48],"FML":[49,79,113,154],"first":[50],"performs":[51,61],"some":[52],"SGDsteps":[53],"obtain":[55],"a":[56,62,152,189],"reference":[57,74],"and":[59,84,92,136,167,178,198,210,215,249,266],"then":[60],"meta-step":[63,168],"along":[69],"direction":[71],"towards":[72],"model.":[75],"In":[76],"this":[77],"way,":[78],"can":[80,258],"identify":[81],"common":[82],"patterns":[83],"structures":[85],"across":[86],"clients":[88,130,144,237],"(i.e.,":[89],"devices)":[91],"quickly":[93],"adapt":[94],"new":[96,190],"distributions,":[98],"exhibits":[100],"its":[101],"advantage":[102],"dealing":[104],"statistical":[106,177],"heterogeneity":[107,180,241],"inherent":[108],"FL.":[110],"However,":[111],"existing":[112],"approaches":[114],"struggle":[115],"effectively":[117],"cope":[118],"two":[120],"key":[121],"challenges:":[122],"i)":[123],"disparity":[125,139],"dataset":[127,196],"informativeness":[128],"among":[129,143],"statistically":[132],"heterogeneous":[133,146,280],"data;":[135],"ii)":[137],"capacities":[142],"hardware":[147],"configurations.":[148],"Herein,":[149],"we":[150,223],"propose":[151],"heterogeneity-aware":[153],"framework,":[155],"termed":[156],"HFML,":[157],"explores":[159],"adjusting":[160],"execution":[162,205,233],"frequencies":[163,206,234],"of":[164,203,207,273],"SGD":[165,208],"step":[166],"round":[172],"address":[174],"above":[176],"system":[179],"challenges":[181],"simultaneously.":[182],"We":[183],"introduce":[184],"usable":[185],"information":[186],"(UI)":[187],"as":[188],"metric":[191],"HFML":[193,257],"quantify":[195],"informativeness,":[197],"theoretically":[199],"analyze":[200],"influence":[202],"meta-steps":[211],"performance":[214],"convergence":[216],"speed.":[217],"Based":[218],"theoretical":[221],"analysis,":[222],"develop":[224],"an":[225,271],"efficient":[226],"optimization":[227],"algorithm":[228],"jointly":[230],"adjust":[231],"for":[235],"handle":[239],"issues,":[242],"contributes":[244],"accelerating":[246],"enhancing":[250],"personalization":[251],"performance.":[252],"Experimental":[253],"results":[254],"demonstrate":[255],"that":[256],"speed":[259],"up":[260,263],"4.02\u00d7":[265],"improve":[267],"accuracy":[269],"average":[272],"11.5%":[274],"compared":[275],"baselines":[278],"under":[279],"settings.":[281]},"counts_by_year":[],"updated_date":"2026-03-09T07:00:12.390032","created_date":"2025-10-31T00:00:00"}