{"id":"https://openalex.org/W4416250583","doi":"https://doi.org/10.1109/ijcnn64981.2025.11227845","title":"MHFL: A Semi-Asynchronous Personalized Federated Learning Framework Based on Model Migration for Edge Clients with Heterogeneous Data","display_name":"MHFL: A Semi-Asynchronous Personalized Federated Learning Framework Based on Model Migration for Edge Clients with Heterogeneous Data","publication_year":2025,"publication_date":"2025-06-30","ids":{"openalex":"https://openalex.org/W4416250583","doi":"https://doi.org/10.1109/ijcnn64981.2025.11227845"},"language":null,"primary_location":{"id":"doi:10.1109/ijcnn64981.2025.11227845","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ijcnn64981.2025.11227845","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 International Joint Conference on Neural Networks (IJCNN)","raw_type":"proceedings-article"},"type":"conference-paper","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/A5010242765","display_name":"Jia Chen","orcid":"https://orcid.org/0000-0002-9896-1656"},"institutions":[{"id":"https://openalex.org/I2722730","display_name":"Inner Mongolia University","ror":"https://ror.org/0106qb496","country_code":"CN","type":"education","lineage":["https://openalex.org/I2722730"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jia Chen","raw_affiliation_strings":["Inner Mongolia University,Hohhot,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Inner Mongolia University,Hohhot,China","institution_ids":["https://openalex.org/I2722730"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101456383","display_name":"Yongqiang Gao","orcid":"https://orcid.org/0000-0003-3273-3148"},"institutions":[{"id":"https://openalex.org/I2722730","display_name":"Inner Mongolia University","ror":"https://ror.org/0106qb496","country_code":"CN","type":"education","lineage":["https://openalex.org/I2722730"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yongqiang Gao","raw_affiliation_strings":["Inner Mongolia University,Hohhot,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Inner Mongolia University,Hohhot,China","institution_ids":["https://openalex.org/I2722730"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5076405266","display_name":"Rao Fu","orcid":null},"institutions":[{"id":"https://openalex.org/I2722730","display_name":"Inner Mongolia University","ror":"https://ror.org/0106qb496","country_code":"CN","type":"education","lineage":["https://openalex.org/I2722730"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Rao Fu","raw_affiliation_strings":["Inner Mongolia University,Hohhot,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Inner Mongolia University,Hohhot,China","institution_ids":["https://openalex.org/I2722730"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I2722730"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"8"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10764","display_name":"Privacy-Preserving Technologies in Data","score":0.7222999930381775,"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":0.7222999930381775,"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/T10273","display_name":"IoT and Edge/Fog Computing","score":0.05429999902844429,"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"}},{"id":"https://openalex.org/T13918","display_name":"Advanced Data and IoT Technologies","score":0.028999999165534973,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/federated-learning","display_name":"Federated learning","score":0.7559000253677368},{"id":"https://openalex.org/keywords/enhanced-data-rates-for-gsm-evolution","display_name":"Enhanced Data Rates for GSM Evolution","score":0.6740000247955322},{"id":"https://openalex.org/keywords/personalization","display_name":"Personalization","score":0.5705999732017517},{"id":"https://openalex.org/keywords/edge-device","display_name":"Edge device","score":0.5515999794006348},{"id":"https://openalex.org/keywords/edge-computing","display_name":"Edge computing","score":0.5012999773025513},{"id":"https://openalex.org/keywords/server","display_name":"Server","score":0.4487000107765198},{"id":"https://openalex.org/keywords/workload","display_name":"Workload","score":0.44679999351501465},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.43950000405311584}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8482999801635742},{"id":"https://openalex.org/C2992525071","wikidata":"https://www.wikidata.org/wiki/Q50818671","display_name":"Federated learning","level":2,"score":0.7559000253677368},{"id":"https://openalex.org/C162307627","wikidata":"https://www.wikidata.org/wiki/Q204833","display_name":"Enhanced Data Rates for GSM Evolution","level":2,"score":0.6740000247955322},{"id":"https://openalex.org/C120314980","wikidata":"https://www.wikidata.org/wiki/Q180634","display_name":"Distributed computing","level":1,"score":0.6304000020027161},{"id":"https://openalex.org/C183003079","wikidata":"https://www.wikidata.org/wiki/Q1000371","display_name":"Personalization","level":2,"score":0.5705999732017517},{"id":"https://openalex.org/C138236772","wikidata":"https://www.wikidata.org/wiki/Q25098575","display_name":"Edge device","level":3,"score":0.5515999794006348},{"id":"https://openalex.org/C31258907","wikidata":"https://www.wikidata.org/wiki/Q1301371","display_name":"Computer network","level":1,"score":0.5019999742507935},{"id":"https://openalex.org/C2778456923","wikidata":"https://www.wikidata.org/wiki/Q5337692","display_name":"Edge computing","level":3,"score":0.5012999773025513},{"id":"https://openalex.org/C93996380","wikidata":"https://www.wikidata.org/wiki/Q44127","display_name":"Server","level":2,"score":0.4487000107765198},{"id":"https://openalex.org/C2778476105","wikidata":"https://www.wikidata.org/wiki/Q628539","display_name":"Workload","level":2,"score":0.44679999351501465},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.43950000405311584},{"id":"https://openalex.org/C2779582901","wikidata":"https://www.wikidata.org/wiki/Q21013010","display_name":"Distributed learning","level":2,"score":0.4311999976634979},{"id":"https://openalex.org/C177148314","wikidata":"https://www.wikidata.org/wiki/Q170084","display_name":"Generalization","level":2,"score":0.3783999979496002},{"id":"https://openalex.org/C141513077","wikidata":"https://www.wikidata.org/wiki/Q378542","display_name":"Independent and identically distributed random variables","level":3,"score":0.3531999886035919},{"id":"https://openalex.org/C67186912","wikidata":"https://www.wikidata.org/wiki/Q367664","display_name":"Data modeling","level":2,"score":0.337799996137619},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.31850001215934753},{"id":"https://openalex.org/C158156997","wikidata":"https://www.wikidata.org/wiki/Q1416645","display_name":"Models of communication","level":2,"score":0.31470000743865967},{"id":"https://openalex.org/C70061542","wikidata":"https://www.wikidata.org/wiki/Q989016","display_name":"Distributed database","level":2,"score":0.31189998984336853},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.2939999997615814},{"id":"https://openalex.org/C138959212","wikidata":"https://www.wikidata.org/wiki/Q1806783","display_name":"Load balancing (electrical power)","level":3,"score":0.2818000018596649},{"id":"https://openalex.org/C151319957","wikidata":"https://www.wikidata.org/wiki/Q752739","display_name":"Asynchronous communication","level":2,"score":0.27379998564720154},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.2700999975204468},{"id":"https://openalex.org/C192126672","wikidata":"https://www.wikidata.org/wiki/Q1068715","display_name":"Telecommunications network","level":2,"score":0.2676999866962433},{"id":"https://openalex.org/C2777735758","wikidata":"https://www.wikidata.org/wiki/Q817765","display_name":"Path (computing)","level":2,"score":0.26649999618530273}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/ijcnn64981.2025.11227845","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ijcnn64981.2025.11227845","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 International Joint Conference on Neural Networks (IJCNN)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"},{"id":"https://openalex.org/F4320335577","display_name":"Major Research Plan","ror":null}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":17,"referenced_works":["https://openalex.org/W2954124071","https://openalex.org/W2962804345","https://openalex.org/W2963318081","https://openalex.org/W3033664100","https://openalex.org/W3042621011","https://openalex.org/W3129932124","https://openalex.org/W3156717451","https://openalex.org/W3187356235","https://openalex.org/W4308360268","https://openalex.org/W4313643873","https://openalex.org/W4320067864","https://openalex.org/W4360995590","https://openalex.org/W4376478371","https://openalex.org/W4390872376","https://openalex.org/W4392877260","https://openalex.org/W4395069486","https://openalex.org/W4405022072"],"related_works":[],"abstract_inverted_index":{"Federated":[0],"learning":[1,44,52],"(FL)":[2],"in":[3,28,146],"edge":[4,33,100],"computing":[5],"scenarios":[6],"faces":[7],"critical":[8],"challenges":[9],"such":[10],"as":[11],"data":[12,64],"heterogeneity":[13],"and":[14,66,81,87,123,125,152],"limited":[15,24,78],"communication":[16,79,131,154],"resources.":[17],"The":[18,133],"traditional":[19],"FL":[20,59],"global":[21],"model":[22],"has":[23],"generalization":[25],"capabilities,":[26],"resulting":[27],"poor":[29],"performance":[30],"on":[31],"individual":[32],"nodes.":[34],"To":[35],"address":[36],"this,":[37],"we":[38],"propose":[39],"a":[40,95],"semi-asynchronous":[41,96],"personalized":[42,75],"federated":[43],"framework,":[45],"named":[46],"MHFL.":[47],"MHFL":[48,93,142],"utilizes":[49],"deep":[50],"reinforcement":[51],"(DRL)":[53],"to":[54,57,73,102,106,112,139,150,158],"dynamically":[55],"adapt":[56],"the":[58,83,107,110],"environment":[60],"(e.g.,":[61],"network":[62],"conditions,":[63],"distribution,":[65],"workload":[67],"distribution),":[68],"generating":[69],"optimized":[70],"migration":[71],"strategies":[72],"enhance":[74],"performance,":[76],"alleviate":[77],"resources,":[80],"mitigate":[82],"impact":[84],"of":[85,148],"non-independent":[86],"identically":[88],"distributed":[89],"(Non-IID)":[90],"data.":[91],"Furthermore,":[92],"adopts":[94],"aggregation":[97],"strategy,":[98],"allowing":[99],"nodes":[101],"transmit":[103],"their":[104],"models":[105],"server":[108],"without":[109],"need":[111],"synchronize":[113],"all":[114],"devices,":[115],"thereby":[116],"avoiding":[117],"straggler":[118],"issues,":[119],"balancing":[120],"training":[121],"loss":[122],"latency,":[124],"further":[126],"optimizing":[127],"personalization":[128],"while":[129],"reducing":[130],"costs.":[132],"experimental":[134],"results":[135],"demonstrate":[136],"that,":[137],"compared":[138],"existing":[140],"methods,":[141],"achieves":[143],"an":[144],"improvement":[145],"accuracy":[147],"up":[149,157],"15.8%":[151],"reduces":[153],"costs":[155],"by":[156],"40.3%.":[159]},"counts_by_year":[],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-11-14T00:00:00"}