{"id":"https://openalex.org/W7160956306","doi":"https://doi.org/10.1109/ton.2026.3692159","title":"SemiSFL: A Novel Semi-Supervised Split Federated Learning System for Efficient Training With Non-IID Data","display_name":"SemiSFL: A Novel Semi-Supervised Split Federated Learning System for Efficient Training With Non-IID Data","publication_year":2026,"publication_date":"2026-01-01","ids":{"openalex":"https://openalex.org/W7160956306","doi":"https://doi.org/10.1109/ton.2026.3692159"},"language":null,"primary_location":{"id":"doi:10.1109/ton.2026.3692159","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ton.2026.3692159","pdf_url":null,"source":{"id":"https://openalex.org/S5407042750","display_name":"IEEE Transactions on Networking","issn_l":"2998-4157","issn":["2998-4157"],"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":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Networking","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":"https://openalex.org/A5133798291","display_name":"Y Xu","orcid":null},"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":["School of Computer Science and Technology, University of Science and Technology of China, Hefei, Anhui, China"],"raw_orcid":"https://orcid.org/0000-0003-0839-3892","affiliations":[{"raw_affiliation_string":"School of Computer Science and Technology, University of Science and Technology of China, Hefei, Anhui, China","institution_ids":["https://openalex.org/I126520041"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101448183","display_name":"Junhao Cheng","orcid":"https://orcid.org/0009-0009-5009-3253"},"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":"Junhao Cheng","raw_affiliation_strings":["School of Computer Science and Technology, University of Science and Technology of China, Hefei, Anhui, China"],"raw_orcid":"https://orcid.org/0009-0003-4533-5250","affiliations":[{"raw_affiliation_string":"School of Computer Science and Technology, University of Science and Technology of China, Hefei, Anhui, China","institution_ids":["https://openalex.org/I126520041"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5112132392","display_name":"HJ Xu","orcid":null},"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":["School of Computer Science and Technology, University of Science and Technology of China, Hefei, Anhui, China"],"raw_orcid":"https://orcid.org/0000-0003-3831-4577","affiliations":[{"raw_affiliation_string":"School of Computer Science and Technology, 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":["School of Computer Science and Technology, University of Science and Technology of China, Hefei, Anhui, China"],"raw_orcid":"https://orcid.org/0000-0002-5065-2600","affiliations":[{"raw_affiliation_string":"School of Computer Science and Technology, University of Science and Technology of China, Hefei, Anhui, China","institution_ids":["https://openalex.org/I126520041"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5135935935","display_name":"Zhipeng Sun","orcid":null},"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":"Zhipeng Sun","raw_affiliation_strings":["School of Computer Science and Technology, University of Science and Technology of China, Hefei, Anhui, China"],"raw_orcid":"https://orcid.org/0009-0007-4710-5466","affiliations":[{"raw_affiliation_string":"School of Computer Science and Technology, University of Science and Technology of China, Hefei, Anhui, China","institution_ids":["https://openalex.org/I126520041"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"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":0.56789107,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"34","issue":null,"first_page":"5927","last_page":"5941"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10764","display_name":"Privacy-Preserving Technologies in Data","score":0.7261000275611877,"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":0.7261000275611877,"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/T11307","display_name":"Domain Adaptation and Few-Shot Learning","score":0.05510000139474869,"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/T12676","display_name":"Machine Learning and ELM","score":0.025100000202655792,"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/training","display_name":"Training (meteorology)","score":0.588100016117096},{"id":"https://openalex.org/keywords/training-set","display_name":"Training set","score":0.3319999873638153},{"id":"https://openalex.org/keywords/federated-learning","display_name":"Federated learning","score":0.31949999928474426},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.31119999289512634},{"id":"https://openalex.org/keywords/key","display_name":"Key (lock)","score":0.30970001220703125}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.699400007724762},{"id":"https://openalex.org/C2777211547","wikidata":"https://www.wikidata.org/wiki/Q17141490","display_name":"Training (meteorology)","level":2,"score":0.588100016117096},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3635999858379364},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.3319999873638153},{"id":"https://openalex.org/C2992525071","wikidata":"https://www.wikidata.org/wiki/Q50818671","display_name":"Federated learning","level":2,"score":0.31949999928474426},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.31119999289512634},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.30970001220703125},{"id":"https://openalex.org/C77618280","wikidata":"https://www.wikidata.org/wiki/Q1155772","display_name":"Scheme (mathematics)","level":2,"score":0.29429998993873596},{"id":"https://openalex.org/C9652623","wikidata":"https://www.wikidata.org/wiki/Q190109","display_name":"Field (mathematics)","level":2,"score":0.2833999991416931},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.2621999979019165}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/ton.2026.3692159","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ton.2026.3692159","pdf_url":null,"source":{"id":"https://openalex.org/S5407042750","display_name":"IEEE Transactions on Networking","issn_l":"2998-4157","issn":["2998-4157"],"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":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Networking","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G1808207986","display_name":null,"funder_award_id":"WK2150250044","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G3728861621","display_name":null,"funder_award_id":"62502487","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"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":37,"referenced_works":["https://openalex.org/W1861492603","https://openalex.org/W2001610032","https://openalex.org/W2117539524","https://openalex.org/W2618530766","https://openalex.org/W2963209930","https://openalex.org/W2980856918","https://openalex.org/W3018102029","https://openalex.org/W3035524453","https://openalex.org/W3035682985","https://openalex.org/W3045736930","https://openalex.org/W3086809868","https://openalex.org/W3109620645","https://openalex.org/W3182158470","https://openalex.org/W4205151047","https://openalex.org/W4221144447","https://openalex.org/W4221162144","https://openalex.org/W4224311344","https://openalex.org/W4225482284","https://openalex.org/W4285302300","https://openalex.org/W4287322212","https://openalex.org/W4289534065","https://openalex.org/W4289869659","https://openalex.org/W4309080560","https://openalex.org/W4365397981","https://openalex.org/W4385270518","https://openalex.org/W4385286457","https://openalex.org/W4386131770","https://openalex.org/W4386245161","https://openalex.org/W4386245173","https://openalex.org/W4388895109","https://openalex.org/W4396782851","https://openalex.org/W4400909762","https://openalex.org/W4400910543","https://openalex.org/W4404102213","https://openalex.org/W4405014735","https://openalex.org/W4408819658","https://openalex.org/W7133230604"],"related_works":[],"abstract_inverted_index":{"Recently,":[0],"Split":[1],"Federated":[2,7],"Learning":[3,8],"(SFL)":[4],"advances":[5],"typical":[6],"(FL)":[9],"and":[10,26,92,107,124,131,137,142,193,204,238,262],"offers":[11],"a":[12,17,21,27,94,103,108,244],"feasible":[13],"solution":[14],"by":[15,159,171,254],"splitting":[16],"full":[18,125],"model":[19,23,29,66,106,111],"into":[20],"bottom":[22,105,110,161,173,188],"(for":[24,30],"clients)":[25],"top":[28,122],"the":[31,35,72,87,118,121,129,138,155,167,183,198,211,226,251,259,276],"server),":[32],"which":[33,53],"alleviates":[34],"computation":[36],"and/or":[37],"communication":[38,252],"burden":[39],"on":[40,51,202,210,235],"clients.":[41],"However,":[42],"existing":[43],"SFL":[44,91,97],"works":[45],"often":[46],"assume":[47],"sufficient":[48],"labeled":[49,203],"data":[50,59,206],"clients,":[52],"is":[54],"usually":[55],"impractical.":[56],"Besides,":[57],"non-IID":[58,272],"poses":[60],"another":[61],"challenge":[62],"to":[63,114,181,265,275],"ensure":[64],"efficient":[65],"training.":[67,232],"To":[68,215],"our":[69,191],"best":[70],"knowledge,":[71],"above":[73],"two":[74],"data-related":[75],"issues":[76],"have":[77,207],"not":[78],"been":[79],"simultaneously":[80],"addressed":[81],"in":[82,247,268],"SFL.":[83],"Herein,":[84],"we":[85,152,219],"review":[86],"distinct":[88],"properties":[89],"of":[90,127,186,213,228],"develop":[93,220],"novel":[95],"Semi-supervised":[96],"system,":[98],"called":[99],"SemiSFL.":[100,214],"In":[101],"SemiSFL,":[102],"student":[104,156,160,187],"teacher":[109,132,168,172],"are":[112,146],"assigned":[113],"each":[115],"client,":[116],"while":[117,257],"server":[119],"maintains":[120],"parts":[123],"versions":[126],"both":[128],"global":[130],"models.":[133,189],"Cross-entity":[134],"(i.e.,":[135],"clients":[136,165],"server)":[139],"semi-supervised":[140,150,177],"training":[141,145,200,217,248],"server-side":[143,230],"supervised":[144,231],"alternately":[147],"conducted.":[148],"During":[149],"training,":[151,178],"explore":[153],"regularizing":[154],"features":[157,169],"(produced":[158,170],"models)":[162,174],"from":[163],"different":[164,271],"with":[166],"before":[175],"conducting":[176],"so":[179],"as":[180],"improve":[182],"generalization":[184],"ability":[185],"Moreover,":[190],"theoretical":[192],"experimental":[194],"investigations":[195],"reveal":[196],"that":[197,241],"inconsistent":[199],"processes":[201],"unlabeled":[205],"an":[208,221],"influence":[209],"effectiveness":[212],"mitigate":[216],"inconsistency,":[218],"algorithm":[222],"for":[223],"dynamically":[224],"regulating":[225],"frequency":[227],"performing":[229],"Extensive":[233],"experiments":[234],"benchmark":[236],"models":[237],"datasets":[239],"show":[240],"SemiSFL":[242],"provides":[243],"3.8\u00d7":[245],"speed-up":[246],"time,":[249],"reduces":[250],"cost":[253],"about":[255],"70.3%":[256],"reaching":[258],"target":[260],"accuracy,":[261],"achieves":[263],"up":[264],"5.8%":[266],"improvement":[267],"accuracy":[269],"under":[270],"settings":[273],"compared":[274],"state-of-the-art":[277],"baselines.":[278]},"counts_by_year":[],"updated_date":"2026-07-29T09:40:50.615796","created_date":"2026-05-13T00:00:00"}