{"id":"https://openalex.org/W4414539549","doi":"https://doi.org/10.1109/icc52391.2025.11162027","title":"GFLLM: Federated Learning in Large Language Models With Optimized Group Aggregation","display_name":"GFLLM: Federated Learning in Large Language Models With Optimized Group Aggregation","publication_year":2025,"publication_date":"2025-06-08","ids":{"openalex":"https://openalex.org/W4414539549","doi":"https://doi.org/10.1109/icc52391.2025.11162027"},"language":"en","primary_location":{"id":"doi:10.1109/icc52391.2025.11162027","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icc52391.2025.11162027","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICC 2025 - IEEE International Conference on Communications","raw_type":"proceedings-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/A5107936571","display_name":"Hui Chen","orcid":"https://orcid.org/0009-0009-5028-9424"},"institutions":[{"id":"https://openalex.org/I41725924","display_name":"Muroran Institute of Technology","ror":"https://ror.org/04rymkk69","country_code":"JP","type":"education","lineage":["https://openalex.org/I41725924"]}],"countries":["JP"],"is_corresponding":true,"raw_author_name":"Hui Chen","raw_affiliation_strings":["Muroran Institute of Technology,Department of Sciences and Informatics,Muroran,Hokkaido,Japan"],"affiliations":[{"raw_affiliation_string":"Muroran Institute of Technology,Department of Sciences and Informatics,Muroran,Hokkaido,Japan","institution_ids":["https://openalex.org/I41725924"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5106707877","display_name":"Kaoru Ota","orcid":"https://orcid.org/0000-0002-3382-1652"},"institutions":[{"id":"https://openalex.org/I41725924","display_name":"Muroran Institute of Technology","ror":"https://ror.org/04rymkk69","country_code":"JP","type":"education","lineage":["https://openalex.org/I41725924"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Kaoru Ota","raw_affiliation_strings":["Muroran Institute of Technology,Department of Sciences and Informatics,Muroran,Hokkaido,Japan"],"affiliations":[{"raw_affiliation_string":"Muroran Institute of Technology,Department of Sciences and Informatics,Muroran,Hokkaido,Japan","institution_ids":["https://openalex.org/I41725924"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5061453937","display_name":"Mianxiong Dong","orcid":"https://orcid.org/0000-0002-2788-3451"},"institutions":[{"id":"https://openalex.org/I41725924","display_name":"Muroran Institute of Technology","ror":"https://ror.org/04rymkk69","country_code":"JP","type":"education","lineage":["https://openalex.org/I41725924"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Mianxiong Dong","raw_affiliation_strings":["Muroran Institute of Technology,Department of Sciences and Informatics,Muroran,Hokkaido,Japan"],"affiliations":[{"raw_affiliation_string":"Muroran Institute of Technology,Department of Sciences and Informatics,Muroran,Hokkaido,Japan","institution_ids":["https://openalex.org/I41725924"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5107936571"],"corresponding_institution_ids":["https://openalex.org/I41725924"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.14472747,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"2791","last_page":"2796"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10764","display_name":"Privacy-Preserving Technologies in Data","score":0.9958999752998352,"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":0.9958999752998352,"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/federated-learning","display_name":"Federated learning","score":0.75},{"id":"https://openalex.org/keywords/upload","display_name":"Upload","score":0.6890000104904175},{"id":"https://openalex.org/keywords/language-model","display_name":"Language model","score":0.4171999990940094},{"id":"https://openalex.org/keywords/cloud-computing","display_name":"Cloud computing","score":0.41530001163482666},{"id":"https://openalex.org/keywords/aggregate","display_name":"Aggregate (composite)","score":0.3783999979496002},{"id":"https://openalex.org/keywords/server","display_name":"Server","score":0.35120001435279846},{"id":"https://openalex.org/keywords/data-modeling","display_name":"Data modeling","score":0.33889999985694885}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8173999786376953},{"id":"https://openalex.org/C2992525071","wikidata":"https://www.wikidata.org/wiki/Q50818671","display_name":"Federated learning","level":2,"score":0.75},{"id":"https://openalex.org/C71901391","wikidata":"https://www.wikidata.org/wiki/Q7126699","display_name":"Upload","level":2,"score":0.6890000104904175},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.4171999990940094},{"id":"https://openalex.org/C79974875","wikidata":"https://www.wikidata.org/wiki/Q483639","display_name":"Cloud computing","level":2,"score":0.41530001163482666},{"id":"https://openalex.org/C4679612","wikidata":"https://www.wikidata.org/wiki/Q866298","display_name":"Aggregate (composite)","level":2,"score":0.3783999979496002},{"id":"https://openalex.org/C93996380","wikidata":"https://www.wikidata.org/wiki/Q44127","display_name":"Server","level":2,"score":0.35120001435279846},{"id":"https://openalex.org/C67186912","wikidata":"https://www.wikidata.org/wiki/Q367664","display_name":"Data modeling","level":2,"score":0.33889999985694885},{"id":"https://openalex.org/C82578977","wikidata":"https://www.wikidata.org/wiki/Q16773055","display_name":"Data aggregator","level":3,"score":0.32659998536109924},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.325300008058548},{"id":"https://openalex.org/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","level":1,"score":0.3156000077724457},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.30559998750686646},{"id":"https://openalex.org/C2776257435","wikidata":"https://www.wikidata.org/wiki/Q1576430","display_name":"Bandwidth (computing)","level":2,"score":0.289000004529953},{"id":"https://openalex.org/C2987335383","wikidata":"https://www.wikidata.org/wiki/Q878048","display_name":"Cloud server","level":3,"score":0.289000004529953},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.28049999475479126},{"id":"https://openalex.org/C31258907","wikidata":"https://www.wikidata.org/wiki/Q1301371","display_name":"Computer network","level":1,"score":0.2800000011920929},{"id":"https://openalex.org/C44871818","wikidata":"https://www.wikidata.org/wiki/Q5154139","display_name":"Communication in small groups","level":2,"score":0.26440000534057617},{"id":"https://openalex.org/C2781311116","wikidata":"https://www.wikidata.org/wiki/Q83306","display_name":"Group (periodic table)","level":2,"score":0.262800008058548},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.2515000104904175}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icc52391.2025.11162027","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icc52391.2025.11162027","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICC 2025 - IEEE International Conference on Communications","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":14,"referenced_works":["https://openalex.org/W1556784394","https://openalex.org/W2131681506","https://openalex.org/W3155963862","https://openalex.org/W4285267501","https://openalex.org/W4286375442","https://openalex.org/W4323519480","https://openalex.org/W4384561707","https://openalex.org/W4385338519","https://openalex.org/W4387007274","https://openalex.org/W4390499608","https://openalex.org/W4391743005","https://openalex.org/W4400728225","https://openalex.org/W4401509187","https://openalex.org/W4401857637"],"related_works":[],"abstract_inverted_index":{"Large":[0,95],"language":[1],"model":[2,109],"(LLM)":[3],"have":[4,26],"shown":[5],"their":[6],"potential":[7],"to":[8,30,39,43,65],"improve":[9,44],"the":[10,18,41,69,73,102,112,116,122,126,142],"efficiency":[11],"and":[12,51,72,75,106,114],"effectiveness":[13],"of":[14,79,130,141],"medical":[15,32,45],"works.":[16],"On":[17],"other":[19],"hand,":[20],"developments":[21],"in":[22,35,57,60,94],"federated":[23],"learning":[24],"(FL)":[25],"made":[27],"it":[28],"possible":[29],"utilize":[31],"textual":[33],"datasets":[34],"different":[36],"data":[37],"silos":[38],"fulfilling":[40],"need":[42],"insight":[46],"while":[47],"addressing":[48],"stringent":[49],"privacy":[50],"security":[52],"concerns.":[53],"However,":[54],"fine-tuning":[55],"LLMs":[56,151],"FL":[58,70,148],"results":[59,129],"high":[61],"communication":[62],"costs":[63],"due":[64],"frequent":[66],"transmissions":[67],"between":[68],"server":[71,124],"client":[74],"a":[76],"large":[77],"number":[78],"trainable":[80],"parameters.":[81,155],"To":[82],"solve":[83],"this":[84],"problem,":[85],"we":[86],"propose":[87],"GFLLM:":[88],"Group":[89],"Aggregation":[90],"for":[91],"Federated":[92],"Learning":[93],"Language":[96],"Models.":[97],"Our":[98],"method":[99,137],"first":[100],"assigns":[101],"clients":[103,117],"into":[104],"groups":[105],"performs":[107],"partial":[108],"aggregation":[110],"within":[111],"group,":[113],"then":[115],"with":[118,121,152],"larger":[119],"bandwidth":[120],"cloud":[123],"upload":[125],"weights.":[127],"The":[128],"simulation":[131],"experiments":[132],"demonstrate":[133],"that":[134],"our":[135],"proposed":[136],"saves":[138],"27.5":[139],"%":[140],"time":[143],"on":[144],"average":[145],"over":[146],"traditional":[147],"when":[149],"facing":[150],"7":[153],"billion":[154]},"counts_by_year":[],"updated_date":"2026-03-07T16:01:11.037858","created_date":"2025-10-10T00:00:00"}