{"id":"https://openalex.org/W7140134871","doi":"https://doi.org/10.1109/access.2026.3676500","title":"ATC-FL: Adaptive Thompson Sampling for Efficient Clustering in Federated Learning","display_name":"ATC-FL: Adaptive Thompson Sampling for Efficient Clustering in Federated Learning","publication_year":2026,"publication_date":"2026-01-01","ids":{"openalex":"https://openalex.org/W7140134871","doi":"https://doi.org/10.1109/access.2026.3676500"},"language":"en","primary_location":{"id":"doi:10.1109/access.2026.3676500","is_oa":true,"landing_page_url":"https://doi.org/10.1109/access.2026.3676500","pdf_url":null,"source":{"id":"https://openalex.org/S2485537415","display_name":"IEEE Access","issn_l":"2169-3536","issn":["2169-3536"],"is_oa":true,"is_in_doaj":true,"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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Access","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","doaj"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://doi.org/10.1109/access.2026.3676500","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5051639604","display_name":"Shivani Sanjay Kolekar","orcid":"https://orcid.org/0000-0001-8422-6071"},"institutions":[{"id":"https://openalex.org/I111277659","display_name":"Chonnam National University","ror":"https://ror.org/05kzjxq56","country_code":"KR","type":"education","lineage":["https://openalex.org/I111277659"]}],"countries":["KR"],"is_corresponding":true,"raw_author_name":"Shivani Sanjay Kolekar","raw_affiliation_strings":["Department of Artificial Intelligence Convergence, Chonnam National University, Gwangju, South Korea"],"affiliations":[{"raw_affiliation_string":"Department of Artificial Intelligence Convergence, Chonnam National University, Gwangju, South Korea","institution_ids":["https://openalex.org/I111277659"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5130387374","display_name":"Jisoo Shin","orcid":null},"institutions":[{"id":"https://openalex.org/I111277659","display_name":"Chonnam National University","ror":"https://ror.org/05kzjxq56","country_code":"KR","type":"education","lineage":["https://openalex.org/I111277659"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Jisoo Shin","raw_affiliation_strings":["Department of Artificial Intelligence Convergence, Chonnam National University, Gwangju, South Korea"],"affiliations":[{"raw_affiliation_string":"Department of Artificial Intelligence Convergence, Chonnam National University, Gwangju, South Korea","institution_ids":["https://openalex.org/I111277659"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5009794289","display_name":"David J. Richter","orcid":"https://orcid.org/0000-0001-5413-6710"},"institutions":[{"id":"https://openalex.org/I111277659","display_name":"Chonnam National University","ror":"https://ror.org/05kzjxq56","country_code":"KR","type":"education","lineage":["https://openalex.org/I111277659"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"David J. Richter","raw_affiliation_strings":["Department of Artificial Intelligence Convergence, Chonnam National University, Gwangju, South Korea"],"affiliations":[{"raw_affiliation_string":"Department of Artificial Intelligence Convergence, Chonnam National University, Gwangju, South Korea","institution_ids":["https://openalex.org/I111277659"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5015500546","display_name":"Kyungbaek Kim","orcid":"https://orcid.org/0000-0001-9985-3051"},"institutions":[{"id":"https://openalex.org/I111277659","display_name":"Chonnam National University","ror":"https://ror.org/05kzjxq56","country_code":"KR","type":"education","lineage":["https://openalex.org/I111277659"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Kyungbaek Kim","raw_affiliation_strings":["Department of Artificial Intelligence Convergence, Chonnam National University, Gwangju, South Korea"],"affiliations":[{"raw_affiliation_string":"Department of Artificial Intelligence Convergence, Chonnam National University, Gwangju, South Korea","institution_ids":["https://openalex.org/I111277659"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5051639604"],"corresponding_institution_ids":["https://openalex.org/I111277659"],"apc_list":{"value":1850,"currency":"USD","value_usd":1850},"apc_paid":{"value":1850,"currency":"USD","value_usd":1850},"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.87529637,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"14","issue":null,"first_page":"44755","last_page":"44774"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10764","display_name":"Privacy-Preserving Technologies in Data","score":0.7383000254631042,"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":0.7383000254631042,"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/T12072","display_name":"Machine Learning and Algorithms","score":0.08089999854564667,"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/T11612","display_name":"Stochastic Gradient Optimization Techniques","score":0.03150000050663948,"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/cluster-analysis","display_name":"Cluster analysis","score":0.6450999975204468},{"id":"https://openalex.org/keywords/federated-learning","display_name":"Federated learning","score":0.6108999848365784},{"id":"https://openalex.org/keywords/sampling","display_name":"Sampling (signal processing)","score":0.44119998812675476},{"id":"https://openalex.org/keywords/distributed-database","display_name":"Distributed database","score":0.35850000381469727},{"id":"https://openalex.org/keywords/adaptive-sampling","display_name":"Adaptive sampling","score":0.3409000039100647}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8639000058174133},{"id":"https://openalex.org/C73555534","wikidata":"https://www.wikidata.org/wiki/Q622825","display_name":"Cluster analysis","level":2,"score":0.6450999975204468},{"id":"https://openalex.org/C2992525071","wikidata":"https://www.wikidata.org/wiki/Q50818671","display_name":"Federated learning","level":2,"score":0.6108999848365784},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.45249998569488525},{"id":"https://openalex.org/C140779682","wikidata":"https://www.wikidata.org/wiki/Q210868","display_name":"Sampling (signal processing)","level":3,"score":0.44119998812675476},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3919999897480011},{"id":"https://openalex.org/C70061542","wikidata":"https://www.wikidata.org/wiki/Q989016","display_name":"Distributed database","level":2,"score":0.35850000381469727},{"id":"https://openalex.org/C2781395549","wikidata":"https://www.wikidata.org/wiki/Q4680762","display_name":"Adaptive sampling","level":3,"score":0.3409000039100647},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3005000054836273},{"id":"https://openalex.org/C2779582901","wikidata":"https://www.wikidata.org/wiki/Q21013010","display_name":"Distributed learning","level":2,"score":0.27950000762939453},{"id":"https://openalex.org/C67186912","wikidata":"https://www.wikidata.org/wiki/Q367664","display_name":"Data modeling","level":2,"score":0.26339998841285706},{"id":"https://openalex.org/C77618280","wikidata":"https://www.wikidata.org/wiki/Q1155772","display_name":"Scheme (mathematics)","level":2,"score":0.25119999051094055}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/access.2026.3676500","is_oa":true,"landing_page_url":"https://doi.org/10.1109/access.2026.3676500","pdf_url":null,"source":{"id":"https://openalex.org/S2485537415","display_name":"IEEE Access","issn_l":"2169-3536","issn":["2169-3536"],"is_oa":true,"is_in_doaj":true,"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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Access","raw_type":"journal-article"},{"id":"pmh:oai:doaj.org/article:cb56b489bf4748c4aa297e73d8e5dc4a","is_oa":true,"landing_page_url":"https://doaj.org/article/cb56b489bf4748c4aa297e73d8e5dc4a","pdf_url":null,"source":{"id":"https://openalex.org/S112646816","display_name":"SHILAP Revista de lepidopterolog\u00eda","issn_l":"0300-5267","issn":["0300-5267","2340-4078"],"is_oa":true,"is_in_doaj":true,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"IEEE Access, Vol 14, Pp 44755-44774 (2026)","raw_type":"article"}],"best_oa_location":{"id":"doi:10.1109/access.2026.3676500","is_oa":true,"landing_page_url":"https://doi.org/10.1109/access.2026.3676500","pdf_url":null,"source":{"id":"https://openalex.org/S2485537415","display_name":"IEEE Access","issn_l":"2169-3536","issn":["2169-3536"],"is_oa":true,"is_in_doaj":true,"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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Access","raw_type":"journal-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Federated":[0,58],"Learning":[1],"(FL)":[2],"enables":[3],"collaborative":[4],"model":[5,74],"training":[6],"across":[7],"decentralized":[8],"clients":[9,26],"without":[10],"sharing":[11],"raw":[12],"data.":[13],"To":[14],"improve":[15,210],"scalability":[16],"and":[17,65,73,101,135,145,151,169,197,206],"address":[18],"client":[19,67,97,121],"heterogeneity,":[20],"clustering-based":[21],"FL":[22],"methods":[23],"group":[24],"similar":[25],"to":[27,45,47,69,90,120,158,172,185],"train":[28],"specialized":[29],"models.":[30],"However,":[31],"under":[32,147],"realistic":[33,217],"network":[34,142],"constraints,":[35],"existing":[36],"approaches":[37],"often":[38],"incur":[39],"high":[40],"communication":[41,71,170],"overhead":[42],"or":[43],"fail":[44],"adapt":[46],"dynamic":[48],"conditions.":[49],"We":[50,128,162],"propose":[51],"ATC-FL":[52,76,130,190],"(Adaptive":[53],"Thompson-sampling":[54],"based":[55],"Clustering":[56],"for":[57],"Learning),":[59],"a":[60,82,112,154,174],"framework":[61],"that":[62,203],"adaptively":[63],"selects":[64],"maintains":[66],"clusters":[68],"balance":[70],"cost":[72,171],"performance.":[75],"formulates":[77],"cluster":[78],"count":[79],"selection":[80],"as":[81,111],"multi-armed":[83],"bandit":[84],"problem,":[85],"using":[86],"fixed-budget":[87],"Thompson":[88],"sampling":[89],"explore":[91],"candidate":[92],"configurations.":[93],"At":[94],"each":[95],"round,":[96],"updates":[98],"are":[99],"embedded":[100],"clustered":[102],"via":[103],"K-means,":[104],"with":[105,178],"the":[106,179],"Davies-Bouldin":[107],"Index":[108],"(DBI)":[109],"serving":[110],"low-overhead":[113],"reward":[114],"signal.":[115],"A":[116],"re-clustering":[117],"scheduler":[118],"adapts":[119],"participation":[122],"dynamics":[123],"while":[124,212],"bounding":[125],"server":[126],"computation.":[127],"evaluate":[129],"on":[131,153],"Human":[132],"Activity":[133],"Recognition":[134],"CIFAR-10":[136],"tasks":[137],"over":[138],"two":[139],"emulated":[140],"backbone-style":[141],"topologies":[143],"(NSFNET":[144],"fat-tree)":[146],"non-IID":[148],"data":[149,182],"distributions,":[150],"additionally":[152],"MIMIC-III":[155],"medical":[156],"benchmark":[157],"assess":[159],"cross-domain":[160],"generalization.":[161],"further":[163],"analyze":[164],"how":[165],"ATC-FL\u2019s":[166],"convergence":[167],"behavior":[168],"reach":[173],"target":[175],"accuracy":[176],"vary":[177],"severity":[180],"of":[181],"heterogeneity.":[183],"Compared":[184],"resource-aware":[186],"federated":[187,218],"clustering":[188,205],"methods,":[189],"achieves":[191],"faster":[192],"convergence,":[193],"lower":[194],"bandwidth":[195],"usage,":[196],"reduced":[198],"delay.":[199],"These":[200],"results":[201],"suggest":[202],"adaptive":[204],"network-aware":[207],"control":[208],"can":[209],"efficiency":[211],"maintaining":[213],"stable":[214],"performance":[215],"in":[216],"deployments.":[219]},"counts_by_year":[],"updated_date":"2026-03-30T08:08:38.191290","created_date":"2026-03-24T00:00:00"}