{"id":"https://openalex.org/W7130589880","doi":"https://doi.org/10.1109/fllm67465.2025.11390924","title":"Optimizing Federated Learning in the Era of LLMs: Message Quantization and Streaming","display_name":"Optimizing Federated Learning in the Era of LLMs: Message Quantization and Streaming","publication_year":2025,"publication_date":"2025-11-25","ids":{"openalex":"https://openalex.org/W7130589880","doi":"https://doi.org/10.1109/fllm67465.2025.11390924"},"language":null,"primary_location":{"id":"doi:10.1109/fllm67465.2025.11390924","is_oa":false,"landing_page_url":"https://doi.org/10.1109/fllm67465.2025.11390924","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 3rd International Conference on Foundation and Large Language Models (FLLM)","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/A5123691308","display_name":"Ziyue Xu","orcid":null},"institutions":[{"id":"https://openalex.org/I4210127875","display_name":"Nvidia (United States)","ror":"https://ror.org/03jdj4y14","country_code":"US","type":"company","lineage":["https://openalex.org/I4210127875"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Ziyue Xu","raw_affiliation_strings":["Nvidia Corp.,USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Nvidia Corp.,USA","institution_ids":["https://openalex.org/I4210127875"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5016899045","display_name":"Zhihong Zhang","orcid":"https://orcid.org/0009-0002-3261-1175"},"institutions":[{"id":"https://openalex.org/I4210127875","display_name":"Nvidia (United States)","ror":"https://ror.org/03jdj4y14","country_code":"US","type":"company","lineage":["https://openalex.org/I4210127875"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Zhihong Zhang","raw_affiliation_strings":["Nvidia Corp.,USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Nvidia Corp.,USA","institution_ids":["https://openalex.org/I4210127875"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5067968321","display_name":"H Roth","orcid":null},"institutions":[{"id":"https://openalex.org/I4210127875","display_name":"Nvidia (United States)","ror":"https://ror.org/03jdj4y14","country_code":"US","type":"company","lineage":["https://openalex.org/I4210127875"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Holger R. Roth","raw_affiliation_strings":["Nvidia Corp.,USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Nvidia Corp.,USA","institution_ids":["https://openalex.org/I4210127875"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5006909076","display_name":"Chester Chen","orcid":"https://orcid.org/0009-0000-5835-6104"},"institutions":[{"id":"https://openalex.org/I4210127875","display_name":"Nvidia (United States)","ror":"https://ror.org/03jdj4y14","country_code":"US","type":"company","lineage":["https://openalex.org/I4210127875"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Chester Chen","raw_affiliation_strings":["Nvidia Corp.,USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Nvidia Corp.,USA","institution_ids":["https://openalex.org/I4210127875"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5023881583","display_name":"Yan Cheng","orcid":"https://orcid.org/0009-0009-9609-8762"},"institutions":[{"id":"https://openalex.org/I4210127875","display_name":"Nvidia (United States)","ror":"https://ror.org/03jdj4y14","country_code":"US","type":"company","lineage":["https://openalex.org/I4210127875"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Yan Cheng","raw_affiliation_strings":["Nvidia Corp.,USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Nvidia Corp.,USA","institution_ids":["https://openalex.org/I4210127875"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5066604966","display_name":"Andrew Feng","orcid":"https://orcid.org/0000-0002-1675-745X"},"institutions":[{"id":"https://openalex.org/I4210127875","display_name":"Nvidia (United States)","ror":"https://ror.org/03jdj4y14","country_code":"US","type":"company","lineage":["https://openalex.org/I4210127875"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Andrew Feng","raw_affiliation_strings":["Nvidia Corp.,USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Nvidia Corp.,USA","institution_ids":["https://openalex.org/I4210127875"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I4210127875"],"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":"876","last_page":"880"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10764","display_name":"Privacy-Preserving Technologies in Data","score":0.7527999877929688,"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":0.7527999877929688,"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/T14347","display_name":"Big Data and Digital Economy","score":0.06560000032186508,"subfield":{"id":"https://openalex.org/subfields/1710","display_name":"Information Systems"},"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/T10237","display_name":"Cryptography and Data Security","score":0.024900000542402267,"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":0.8379999995231628},{"id":"https://openalex.org/keywords/scalability","display_name":"Scalability","score":0.6748999953269958},{"id":"https://openalex.org/keywords/workflow","display_name":"Workflow","score":0.6545000076293945},{"id":"https://openalex.org/keywords/robustness","display_name":"Robustness (evolution)","score":0.5692999958992004},{"id":"https://openalex.org/keywords/quantization","display_name":"Quantization (signal processing)","score":0.5077000260353088},{"id":"https://openalex.org/keywords/data-transmission","display_name":"Data transmission","score":0.38280001282691956},{"id":"https://openalex.org/keywords/models-of-communication","display_name":"Models of communication","score":0.3677000105381012},{"id":"https://openalex.org/keywords/boosting","display_name":"Boosting (machine learning)","score":0.3646000027656555}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8623999953269958},{"id":"https://openalex.org/C2992525071","wikidata":"https://www.wikidata.org/wiki/Q50818671","display_name":"Federated learning","level":2,"score":0.8379999995231628},{"id":"https://openalex.org/C48044578","wikidata":"https://www.wikidata.org/wiki/Q727490","display_name":"Scalability","level":2,"score":0.6748999953269958},{"id":"https://openalex.org/C177212765","wikidata":"https://www.wikidata.org/wiki/Q627335","display_name":"Workflow","level":2,"score":0.6545000076293945},{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.5692999958992004},{"id":"https://openalex.org/C120314980","wikidata":"https://www.wikidata.org/wiki/Q180634","display_name":"Distributed computing","level":1,"score":0.5160999894142151},{"id":"https://openalex.org/C28855332","wikidata":"https://www.wikidata.org/wiki/Q198099","display_name":"Quantization (signal processing)","level":2,"score":0.5077000260353088},{"id":"https://openalex.org/C557945733","wikidata":"https://www.wikidata.org/wiki/Q389772","display_name":"Data transmission","level":2,"score":0.38280001282691956},{"id":"https://openalex.org/C158156997","wikidata":"https://www.wikidata.org/wiki/Q1416645","display_name":"Models of communication","level":2,"score":0.3677000105381012},{"id":"https://openalex.org/C46686674","wikidata":"https://www.wikidata.org/wiki/Q466303","display_name":"Boosting (machine learning)","level":2,"score":0.3646000027656555},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.35929998755455017},{"id":"https://openalex.org/C2779960059","wikidata":"https://www.wikidata.org/wiki/Q7113681","display_name":"Overhead (engineering)","level":2,"score":0.35420000553131104},{"id":"https://openalex.org/C130795937","wikidata":"https://www.wikidata.org/wiki/Q2561570","display_name":"Remote direct memory access","level":2,"score":0.3398999869823456},{"id":"https://openalex.org/C854659","wikidata":"https://www.wikidata.org/wiki/Q1859284","display_name":"Message passing","level":2,"score":0.3181999921798706},{"id":"https://openalex.org/C206729178","wikidata":"https://www.wikidata.org/wiki/Q2271896","display_name":"Scheduling (production processes)","level":2,"score":0.3158999979496002},{"id":"https://openalex.org/C2779582901","wikidata":"https://www.wikidata.org/wiki/Q21013010","display_name":"Distributed learning","level":2,"score":0.314300000667572},{"id":"https://openalex.org/C12186640","wikidata":"https://www.wikidata.org/wiki/Q6815743","display_name":"Memory model","level":3,"score":0.31200000643730164},{"id":"https://openalex.org/C93996380","wikidata":"https://www.wikidata.org/wiki/Q44127","display_name":"Server","level":2,"score":0.2881999909877777},{"id":"https://openalex.org/C67186912","wikidata":"https://www.wikidata.org/wiki/Q367664","display_name":"Data modeling","level":2,"score":0.2838999927043915},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.274399995803833},{"id":"https://openalex.org/C199833920","wikidata":"https://www.wikidata.org/wiki/Q612536","display_name":"Vector quantization","level":2,"score":0.25780001282691956},{"id":"https://openalex.org/C47487241","wikidata":"https://www.wikidata.org/wiki/Q5227230","display_name":"Data access","level":2,"score":0.2554999887943268}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/fllm67465.2025.11390924","is_oa":false,"landing_page_url":"https://doi.org/10.1109/fllm67465.2025.11390924","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 3rd International Conference on Foundation and Large Language Models (FLLM)","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":3,"referenced_works":["https://openalex.org/W3184606595","https://openalex.org/W4307323645","https://openalex.org/W4409790147"],"related_works":[],"abstract_inverted_index":{"Federated":[0],"Learning":[1],"(FL)":[2],"offers":[3],"a":[4],"promising":[5],"solution":[6],"for":[7,64,72,87,95],"training":[8],"machine":[9],"learning":[10,141],"models":[11,51],"across":[12],"distributed":[13],"data":[14,18],"sources":[15],"while":[16,110],"preserving":[17],"privacy.":[19],"However,":[20],"FL":[21,93,132],"faces":[22],"critical":[23],"challenges":[24,77],"related":[25],"to":[26],"communication":[27,56,81],"overhead":[28],"and":[29,55,61,103,118,129],"local":[30],"resource":[31],"constraints,":[32,57],"especially":[33],"in":[34,138],"the":[35,127],"era":[36],"of":[37,44,49,131],"Large":[38],"Language":[39],"Models":[40],"(LLMs)":[41],"with":[42,120,133],"billions":[43],"parameters.":[45],"The":[46],"sheer":[47],"size":[48],"these":[50,76],"exacerbates":[52],"both":[53],"memory":[54,114],"making":[58],"efficient":[59,113],"transmission":[60],"processing":[62],"essential":[63],"practical":[65],"deployment.":[66],"NVIDIA":[67],"FLARE,":[68],"an":[69],"open-source":[70],"SDK":[71],"federated":[73,140],"learning,":[74],"addresses":[75],"by":[78],"introducing":[79],"advanced":[80],"capabilities.":[82],"Building":[83],"upon":[84],"existing":[85,121],"solutions":[86],"large":[88],"object":[89],"streaming,":[90],"we":[91],"enhance":[92,126],"workflows":[94],"LLMs":[96],"through":[97],"two":[98],"key":[99],"techniques:":[100],"message":[101,108],"quantization":[102],"container/file":[104],"streaming.":[105],"Quantization":[106],"reduces":[107],"size,":[109],"streaming":[111],"enables":[112],"management,":[115],"improving":[116],"scalability":[117],"integration":[119],"workflows.":[122],"These":[123],"advancements":[124],"significantly":[125],"robustness":[128],"efficiency":[130],"LLMs,":[134],"ensuring":[135],"better":[136],"performance":[137],"real-world":[139],"scenarios.":[142]},"counts_by_year":[],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2026-02-20T00:00:00"}