{"id":"https://openalex.org/W4414856475","doi":"https://doi.org/10.1109/tnnls.2025.3611832","title":"FedMPS: Federated Learning in a Synergy of Multi-Level Prototype-Based Contrastive Learning and Soft Label Generation","display_name":"FedMPS: Federated Learning in a Synergy of Multi-Level Prototype-Based Contrastive Learning and Soft Label Generation","publication_year":2025,"publication_date":"2025-10-06","ids":{"openalex":"https://openalex.org/W4414856475","doi":"https://doi.org/10.1109/tnnls.2025.3611832","pmid":"https://pubmed.ncbi.nlm.nih.gov/41052182"},"language":"en","primary_location":{"id":"doi:10.1109/tnnls.2025.3611832","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tnnls.2025.3611832","pdf_url":null,"source":{"id":"https://openalex.org/S4210175523","display_name":"IEEE Transactions on Neural Networks and Learning Systems","issn_l":"2162-237X","issn":["2162-237X","2162-2388"],"is_oa":false,"is_in_doaj":false,"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":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Neural Networks and Learning Systems","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","pubmed"],"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/A5101244868","display_name":"Wenxin Yang","orcid":"https://orcid.org/0009-0006-2035-1854"},"institutions":[{"id":"https://openalex.org/I170215575","display_name":"National University of Defense Technology","ror":"https://ror.org/05d2yfz11","country_code":"CN","type":"education","lineage":["https://openalex.org/I170215575"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Wenxin Yang","raw_affiliation_strings":["Laboratory for Big Data and Decision, National University of Defense Technology, Changsha, China"],"affiliations":[{"raw_affiliation_string":"Laboratory for Big Data and Decision, National University of Defense Technology, Changsha, China","institution_ids":["https://openalex.org/I170215575"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5063734773","display_name":"Xingchen Hu","orcid":"https://orcid.org/0000-0001-6879-5266"},"institutions":[{"id":"https://openalex.org/I170215575","display_name":"National University of Defense Technology","ror":"https://ror.org/05d2yfz11","country_code":"CN","type":"education","lineage":["https://openalex.org/I170215575"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xingchen Hu","raw_affiliation_strings":["Laboratory for Big Data and Decision and the School of Computer, National University of Defense Technology, Changsha, China"],"affiliations":[{"raw_affiliation_string":"Laboratory for Big Data and Decision and the School of Computer, National University of Defense Technology, Changsha, China","institution_ids":["https://openalex.org/I170215575"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5079140689","display_name":"Xiubin Zhu","orcid":"https://orcid.org/0000-0002-7947-8749"},"institutions":[{"id":"https://openalex.org/I149594827","display_name":"Xidian University","ror":"https://ror.org/05s92vm98","country_code":"CN","type":"education","lineage":["https://openalex.org/I149594827"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xiubin Zhu","raw_affiliation_strings":["School of Electro-Mechanical Engineering, Xidian University, Xi’an, China"],"affiliations":[{"raw_affiliation_string":"School of Electro-Mechanical Engineering, Xidian University, Xi’an, China","institution_ids":["https://openalex.org/I149594827"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5037320795","display_name":"Rouwan Wu","orcid":null},"institutions":[{"id":"https://openalex.org/I170215575","display_name":"National University of Defense Technology","ror":"https://ror.org/05d2yfz11","country_code":"CN","type":"education","lineage":["https://openalex.org/I170215575"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Rouwan Wu","raw_affiliation_strings":["School of Systems Engineering, National University of Defense Technology, Changsha, China"],"affiliations":[{"raw_affiliation_string":"School of Systems Engineering, National University of Defense Technology, Changsha, China","institution_ids":["https://openalex.org/I170215575"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5003799782","display_name":"Witold Pedrycz","orcid":"https://orcid.org/0000-0002-9335-9930"},"institutions":[{"id":"https://openalex.org/I154425047","display_name":"University of Alberta","ror":"https://ror.org/0160cpw27","country_code":"CA","type":"education","lineage":["https://openalex.org/I154425047"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"Witold Pedrycz","raw_affiliation_strings":["Department of Electrical and Computer Engineering, University of Alberta, Edmonton, AB, Canada"],"affiliations":[{"raw_affiliation_string":"Department of Electrical and Computer Engineering, University of Alberta, Edmonton, AB, Canada","institution_ids":["https://openalex.org/I154425047"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101727888","display_name":"Xinwang Liu","orcid":"https://orcid.org/0000-0001-9066-1475"},"institutions":[{"id":"https://openalex.org/I170215575","display_name":"National University of Defense Technology","ror":"https://ror.org/05d2yfz11","country_code":"CN","type":"education","lineage":["https://openalex.org/I170215575"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xinwang Liu","raw_affiliation_strings":["School of Computer, National University of Defense Technology, Changsha, China"],"affiliations":[{"raw_affiliation_string":"School of Computer, National University of Defense Technology, Changsha, China","institution_ids":["https://openalex.org/I170215575"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5115467769","display_name":"Jincai Huang","orcid":null},"institutions":[{"id":"https://openalex.org/I170215575","display_name":"National University of Defense Technology","ror":"https://ror.org/05d2yfz11","country_code":"CN","type":"education","lineage":["https://openalex.org/I170215575"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jincai Huang","raw_affiliation_strings":["Laboratory for Big Data and Decision, National University of Defense Technology, Changsha, China"],"affiliations":[{"raw_affiliation_string":"Laboratory for Big Data and Decision, National University of Defense Technology, Changsha, China","institution_ids":["https://openalex.org/I170215575"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":7,"corresponding_author_ids":["https://openalex.org/A5101244868"],"corresponding_institution_ids":["https://openalex.org/I170215575"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.15133909,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"37","issue":"2","first_page":"781","last_page":"794"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12262","display_name":"Hate Speech and Cyberbullying Detection","score":0.8052999973297119,"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/T12262","display_name":"Hate Speech and Cyberbullying Detection","score":0.8052999973297119,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/consistency","display_name":"Consistency (knowledge bases)","score":0.6338000297546387},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.4781999886035919},{"id":"https://openalex.org/keywords/raw-data","display_name":"Raw data","score":0.46070000529289246},{"id":"https://openalex.org/keywords/code","display_name":"Code (set theory)","score":0.4284999966621399},{"id":"https://openalex.org/keywords/feature-extraction","display_name":"Feature extraction","score":0.39309999346733093},{"id":"https://openalex.org/keywords/convergence","display_name":"Convergence (economics)","score":0.38100001215934753},{"id":"https://openalex.org/keywords/key","display_name":"Key (lock)","score":0.34860000014305115},{"id":"https://openalex.org/keywords/federated-learning","display_name":"Federated learning","score":0.3334999978542328}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8309000134468079},{"id":"https://openalex.org/C2776436953","wikidata":"https://www.wikidata.org/wiki/Q5163215","display_name":"Consistency (knowledge bases)","level":2,"score":0.6338000297546387},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5218999981880188},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.4781999886035919},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.4666999876499176},{"id":"https://openalex.org/C132964779","wikidata":"https://www.wikidata.org/wiki/Q2110223","display_name":"Raw data","level":2,"score":0.46070000529289246},{"id":"https://openalex.org/C2776760102","wikidata":"https://www.wikidata.org/wiki/Q5139990","display_name":"Code (set theory)","level":3,"score":0.4284999966621399},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.39309999346733093},{"id":"https://openalex.org/C2777303404","wikidata":"https://www.wikidata.org/wiki/Q759757","display_name":"Convergence (economics)","level":2,"score":0.38100001215934753},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.34860000014305115},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.3449000120162964},{"id":"https://openalex.org/C2992525071","wikidata":"https://www.wikidata.org/wiki/Q50818671","display_name":"Federated learning","level":2,"score":0.3334999978542328},{"id":"https://openalex.org/C67186912","wikidata":"https://www.wikidata.org/wiki/Q367664","display_name":"Data modeling","level":2,"score":0.3287000060081482},{"id":"https://openalex.org/C59404180","wikidata":"https://www.wikidata.org/wiki/Q17013334","display_name":"Feature learning","level":2,"score":0.3253999948501587},{"id":"https://openalex.org/C2779304628","wikidata":"https://www.wikidata.org/wiki/Q3503480","display_name":"Face (sociological concept)","level":2,"score":0.3208000063896179},{"id":"https://openalex.org/C66746571","wikidata":"https://www.wikidata.org/wiki/Q1134833","display_name":"ENCODE","level":3,"score":0.3000999987125397},{"id":"https://openalex.org/C2780440489","wikidata":"https://www.wikidata.org/wiki/Q5227278","display_name":"Data-driven","level":2,"score":0.29980000853538513},{"id":"https://openalex.org/C123201435","wikidata":"https://www.wikidata.org/wiki/Q456632","display_name":"Information privacy","level":2,"score":0.2897999882698059},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.2827000021934509},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.27900001406669617},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.27799999713897705},{"id":"https://openalex.org/C77618280","wikidata":"https://www.wikidata.org/wiki/Q1155772","display_name":"Scheme (mathematics)","level":2,"score":0.2678999900817871},{"id":"https://openalex.org/C22367795","wikidata":"https://www.wikidata.org/wiki/Q7625208","display_name":"Structured prediction","level":2,"score":0.2578999996185303},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.2549000084400177},{"id":"https://openalex.org/C2780598303","wikidata":"https://www.wikidata.org/wiki/Q65921492","display_name":"Flexibility (engineering)","level":2,"score":0.2533999979496002}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/tnnls.2025.3611832","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tnnls.2025.3611832","pdf_url":null,"source":{"id":"https://openalex.org/S4210175523","display_name":"IEEE Transactions on Neural Networks and Learning Systems","issn_l":"2162-237X","issn":["2162-237X","2162-2388"],"is_oa":false,"is_in_doaj":false,"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":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Neural Networks and Learning Systems","raw_type":"journal-article"},{"id":"pmid:41052182","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/41052182","pdf_url":null,"source":{"id":"https://openalex.org/S4306525036","display_name":"PubMed","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1299303238","host_organization_name":"National Institutes of Health","host_organization_lineage":["https://openalex.org/I1299303238"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE transactions on neural networks and learning systems","raw_type":null}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":38,"referenced_works":["https://openalex.org/W1821462560","https://openalex.org/W2138621090","https://openalex.org/W2141545068","https://openalex.org/W2991236681","https://openalex.org/W3084432478","https://openalex.org/W3155499466","https://openalex.org/W3155790529","https://openalex.org/W3176065502","https://openalex.org/W3176482836","https://openalex.org/W3182158470","https://openalex.org/W3193881593","https://openalex.org/W3197947753","https://openalex.org/W3204874618","https://openalex.org/W3215194618","https://openalex.org/W4214718285","https://openalex.org/W4224227775","https://openalex.org/W4224860128","https://openalex.org/W4225644355","https://openalex.org/W4226101686","https://openalex.org/W4282933047","https://openalex.org/W4283796083","https://openalex.org/W4286542654","https://openalex.org/W4296477225","https://openalex.org/W4306688887","https://openalex.org/W4307232117","https://openalex.org/W4312592506","https://openalex.org/W4312869277","https://openalex.org/W4317498947","https://openalex.org/W4321488467","https://openalex.org/W4376225158","https://openalex.org/W4378213626","https://openalex.org/W4382461569","https://openalex.org/W4386598485","https://openalex.org/W4386767075","https://openalex.org/W4387146104","https://openalex.org/W4390788106","https://openalex.org/W4392939845","https://openalex.org/W4396216552"],"related_works":[],"abstract_inverted_index":{"Federated":[0],"learning":[1,84],"(FL)":[2],"facilitates":[3],"collaborative":[4,28],"training":[5],"among":[6,23],"multiple":[7],"clients":[8],"while":[9],"preserving":[10],"data":[11,16,21],"privacy":[12],"by":[13],"eliminating":[14],"raw":[15],"transmission.":[17],"However,":[18],"the":[19,32,103,133,152,184,187,193],"inherent":[20],"heterogeneity":[22],"participants":[24],"induces":[25],"bias":[26],"during":[27],"learning,":[29],"significantly":[30],"degrading":[31],"performance":[33],"of":[34,80,102,156,186],"local":[35],"models.":[36],"Existing":[37],"FL":[38,75,196],"solutions":[39],"face":[40],"critical":[41],"challenges":[42],"in":[43,61,77,109,115,132,151],"achieving":[44],"efficient":[45],"knowledge":[46,170],"transmission,":[47],"particularly":[48],"with":[49],"respect":[50],"to":[51,105,125,146,192],"insufficient":[52],"information":[53,108,114],"extraction":[54],"or":[55],"excessive":[56],"communication":[57,173],"costs,":[58],"which":[59],"result":[60],"slow":[62],"convergence":[63],"and":[64,86,112,129,164,172],"inferior":[65],"performance.":[66],"To":[67],"address":[68],"these":[69],"limitations,":[70],"we":[71],"propose":[72],"a":[73,78,138],"novel":[74],"framework":[76],"synergy":[79],"multi-level":[81,97],"prototype-based":[82],"contrastive":[83],"(CL)":[85],"soft":[87,140,165],"label":[88,141],"generation,":[89],"named":[90],"FedMPS.":[91],"The":[92,198],"proposed":[93,188],"method":[94,189],"first":[95],"constructs":[96],"prototypes":[98,119,163],"from":[99],"different":[100],"layers":[101],"model":[104,147,158],"capture":[106],"semantic":[107],"high-level":[110],"features":[111],"detailed":[113],"low-level":[116],"features.":[117],"These":[118],"are":[120],"then":[121],"utilized":[122],"through":[123],"CL":[124],"enhance":[126],"intra-class":[127,130],"discriminability":[128],"consistency":[131],"feature":[134],"space.":[135,154],"In":[136],"addition,":[137],"prototype-guided":[139],"generation":[142],"module":[143],"is":[144,200],"introduced":[145],"latent":[148],"interclass":[149],"relationships":[150],"output":[153],"Instead":[155],"exchanging":[157],"parameters,":[159],"FedMPS":[160],"transmits":[161],"only":[162],"labels,":[166],"effectively":[167],"reducing":[168],"global":[169],"shift":[171],"costs.":[174],"Extensive":[175],"experimental":[176],"studies":[177],"on":[178],"six":[179],"publicly":[180],"available":[181,201],"datasets":[182],"validate":[183],"effectiveness":[185],"when":[190],"compared":[191],"current":[194],"state-of-the-art":[195],"approaches.":[197],"code":[199],"at":[202],"github.com/wenxinyang1026/FedMPS.":[203]},"counts_by_year":[],"updated_date":"2026-03-07T16:01:11.037858","created_date":"2025-10-10T00:00:00"}