{"id":"https://openalex.org/W4401857637","doi":"https://doi.org/10.1145/3637528.3671582","title":"OpenFedLLM: Training Large Language Models on Decentralized Private Data via Federated Learning","display_name":"OpenFedLLM: Training Large Language Models on Decentralized Private Data via Federated Learning","publication_year":2024,"publication_date":"2024-08-24","ids":{"openalex":"https://openalex.org/W4401857637","doi":"https://doi.org/10.1145/3637528.3671582"},"language":"en","primary_location":{"id":"doi:10.1145/3637528.3671582","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3637528.3671582","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 30th ACM SIGKDD Conference on Knowledge Discovery and Data Mining","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/A5100728766","display_name":"Rui Ye","orcid":"https://orcid.org/0009-0007-5998-8200"},"institutions":[{"id":"https://openalex.org/I183067930","display_name":"Shanghai Jiao Tong University","ror":"https://ror.org/0220qvk04","country_code":"CN","type":"education","lineage":["https://openalex.org/I183067930"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Rui Ye","raw_affiliation_strings":["Shanghai Jiao Tong University, Shanghai, China"],"affiliations":[{"raw_affiliation_string":"Shanghai Jiao Tong University, Shanghai, China","institution_ids":["https://openalex.org/I183067930"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5109768862","display_name":"Wenhao Wang","orcid":"https://orcid.org/0009-0009-9160-1584"},"institutions":[{"id":"https://openalex.org/I76130692","display_name":"Zhejiang University","ror":"https://ror.org/00a2xv884","country_code":"CN","type":"education","lineage":["https://openalex.org/I76130692"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Wenhao Wang","raw_affiliation_strings":["Zhejiang University, Zhejiang, China"],"affiliations":[{"raw_affiliation_string":"Zhejiang University, Zhejiang, China","institution_ids":["https://openalex.org/I76130692"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5064810450","display_name":"Jingyi Chai","orcid":"https://orcid.org/0009-0000-2959-3274"},"institutions":[{"id":"https://openalex.org/I183067930","display_name":"Shanghai Jiao Tong University","ror":"https://ror.org/0220qvk04","country_code":"CN","type":"education","lineage":["https://openalex.org/I183067930"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jingyi Chai","raw_affiliation_strings":["Shanghai Jiao Tong University, Shanghai, China"],"affiliations":[{"raw_affiliation_string":"Shanghai Jiao Tong University, Shanghai, China","institution_ids":["https://openalex.org/I183067930"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5080866991","display_name":"Dihan Li","orcid":null},"institutions":[{"id":"https://openalex.org/I1174212","display_name":"University of Southern California","ror":"https://ror.org/03taz7m60","country_code":"US","type":"education","lineage":["https://openalex.org/I1174212"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Dihan Li","raw_affiliation_strings":["University of Southern California, Los Angeles, USA"],"affiliations":[{"raw_affiliation_string":"University of Southern California, Los Angeles, USA","institution_ids":["https://openalex.org/I1174212"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5031648019","display_name":"Zexi Li","orcid":null},"institutions":[{"id":"https://openalex.org/I76130692","display_name":"Zhejiang University","ror":"https://ror.org/00a2xv884","country_code":"CN","type":"education","lineage":["https://openalex.org/I76130692"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zexi Li","raw_affiliation_strings":["Zhejiang University, Zhejiang, China"],"affiliations":[{"raw_affiliation_string":"Zhejiang University, Zhejiang, China","institution_ids":["https://openalex.org/I76130692"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102346536","display_name":"Yinda Xu","orcid":"https://orcid.org/0000-0003-3910-685X"},"institutions":[{"id":"https://openalex.org/I183067930","display_name":"Shanghai Jiao Tong University","ror":"https://ror.org/0220qvk04","country_code":"CN","type":"education","lineage":["https://openalex.org/I183067930"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yinda Xu","raw_affiliation_strings":["Shanghai Jiao Tong University, Shanghai, China"],"affiliations":[{"raw_affiliation_string":"Shanghai Jiao Tong University, Shanghai, China","institution_ids":["https://openalex.org/I183067930"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5078544994","display_name":"Yaxin Du","orcid":null},"institutions":[{"id":"https://openalex.org/I183067930","display_name":"Shanghai Jiao Tong University","ror":"https://ror.org/0220qvk04","country_code":"CN","type":"education","lineage":["https://openalex.org/I183067930"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yaxin Du","raw_affiliation_strings":["Shanghai Jiao Tong University, Shanghai, China"],"affiliations":[{"raw_affiliation_string":"Shanghai Jiao Tong University, Shanghai, China","institution_ids":["https://openalex.org/I183067930"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5064101065","display_name":"Yanfeng Wang","orcid":null},"institutions":[{"id":"https://openalex.org/I183067930","display_name":"Shanghai Jiao Tong University","ror":"https://ror.org/0220qvk04","country_code":"CN","type":"education","lineage":["https://openalex.org/I183067930"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yanfeng Wang","raw_affiliation_strings":["Shanghai Jiao Tong University & Shanghai AI Laboratory, Shanghai, China"],"affiliations":[{"raw_affiliation_string":"Shanghai Jiao Tong University & Shanghai AI Laboratory, Shanghai, China","institution_ids":["https://openalex.org/I183067930"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5070837391","display_name":"Siheng Chen","orcid":"https://orcid.org/0000-0001-6199-529X"},"institutions":[{"id":"https://openalex.org/I183067930","display_name":"Shanghai Jiao Tong University","ror":"https://ror.org/0220qvk04","country_code":"CN","type":"education","lineage":["https://openalex.org/I183067930"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Siheng Chen","raw_affiliation_strings":["Shanghai Jiao Tong University & Shanghai AI Laboratory, Shanghai, China"],"affiliations":[{"raw_affiliation_string":"Shanghai Jiao Tong University & Shanghai AI Laboratory, Shanghai, China","institution_ids":["https://openalex.org/I183067930"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":9,"corresponding_author_ids":["https://openalex.org/A5100728766"],"corresponding_institution_ids":["https://openalex.org/I183067930"],"apc_list":null,"apc_paid":null,"fwci":27.1063,"has_fulltext":false,"cited_by_count":78,"citation_normalized_percentile":{"value":0.99730355,"is_in_top_1_percent":true,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":99,"max":100},"biblio":{"volume":null,"issue":null,"first_page":"6137","last_page":"6147"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10764","display_name":"Privacy-Preserving Technologies in Data","score":0.9997000098228455,"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":0.9997000098228455,"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/T10028","display_name":"Topic Modeling","score":0.9865999817848206,"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/T11598","display_name":"Internet Traffic Analysis and Secure E-voting","score":0.9764000177383423,"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/computer-science","display_name":"Computer science","score":0.7848522663116455},{"id":"https://openalex.org/keywords/training","display_name":"Training (meteorology)","score":0.7532045841217041},{"id":"https://openalex.org/keywords/federated-learning","display_name":"Federated learning","score":0.5938834547996521},{"id":"https://openalex.org/keywords/training-set","display_name":"Training set","score":0.5653128027915955},{"id":"https://openalex.org/keywords/data-modeling","display_name":"Data modeling","score":0.4126163721084595},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.39124375581741333},{"id":"https://openalex.org/keywords/database","display_name":"Database","score":0.17877084016799927}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7848522663116455},{"id":"https://openalex.org/C2777211547","wikidata":"https://www.wikidata.org/wiki/Q17141490","display_name":"Training (meteorology)","level":2,"score":0.7532045841217041},{"id":"https://openalex.org/C2992525071","wikidata":"https://www.wikidata.org/wiki/Q50818671","display_name":"Federated learning","level":2,"score":0.5938834547996521},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.5653128027915955},{"id":"https://openalex.org/C67186912","wikidata":"https://www.wikidata.org/wiki/Q367664","display_name":"Data modeling","level":2,"score":0.4126163721084595},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.39124375581741333},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.17877084016799927},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C153294291","wikidata":"https://www.wikidata.org/wiki/Q25261","display_name":"Meteorology","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3637528.3671582","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3637528.3671582","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 30th ACM SIGKDD Conference on Knowledge Discovery and Data Mining","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":20,"referenced_works":["https://openalex.org/W1546425147","https://openalex.org/W2798658104","https://openalex.org/W2979826702","https://openalex.org/W3038022836","https://openalex.org/W3174770825","https://openalex.org/W3212544464","https://openalex.org/W4206637810","https://openalex.org/W4221143046","https://openalex.org/W4226278401","https://openalex.org/W4280534475","https://openalex.org/W4281557260","https://openalex.org/W4285247752","https://openalex.org/W4286421857","https://openalex.org/W4292779060","https://openalex.org/W4382998416","https://openalex.org/W4385430086","https://openalex.org/W4385572162","https://openalex.org/W6759238902","https://openalex.org/W6778883912","https://openalex.org/W6838865847"],"related_works":["https://openalex.org/W4298221930","https://openalex.org/W230091440","https://openalex.org/W2777914285","https://openalex.org/W2233261550","https://openalex.org/W2810751659","https://openalex.org/W4394050964","https://openalex.org/W2551249631","https://openalex.org/W4388282301","https://openalex.org/W4285322112","https://openalex.org/W4292794239"],"abstract_inverted_index":{"Trained":[0],"on":[1,56,118,149],"massive":[2],"publicly":[3],"available":[4,201,211],"data,":[5],"large":[6],"language":[7],"models":[8],"(LLMs)":[9],"have":[10],"demonstrated":[11],"tremendous":[12],"success":[13],"across":[14,157],"various":[15],"fields.":[16],"While":[17],"more":[18],"data":[19,31,61,68],"contributes":[20],"to":[21,194],"better":[22],"performance,":[23],"a":[24,36,44,72,84,153,158,164,178],"disconcerting":[25],"reality":[26],"is":[27,200,210],"that":[28,142],"high-quality":[29],"public":[30],"will":[32],"be":[33],"exhausted":[34],"in":[35,163,196],"few":[37],"years.":[38],"In":[39],"this":[40],"paper,":[41],"we":[42,82,122,132,140],"offer":[43],"potential":[45],"next":[46],"step":[47],"for":[48,97,104,192],"contemporary":[49],"LLMs:":[50],"collaborative":[51],"and":[52,87,109,127],"privacy-preserving":[53],"LLM":[54],"training":[55,117,125,148,150,187],"the":[57,182],"underutilized":[58],"distributed":[59],"private":[60],"via":[62],"federated":[63,94,101],"learning":[64],"(FL),":[65],"where":[66,121,131],"multiple":[67],"owners":[69],"collaboratively":[70],"train":[71],"shared":[73],"model":[74,183],"without":[75],"transmitting":[76],"raw":[77],"data.":[78],"To":[79],"achieve":[80],"this,":[81],"build":[83],"concise,":[85],"integrated,":[86],"research-friendly":[88],"framework/codebase,":[89],"named":[90],"OpenFedLLM.":[91],"It":[92],"covers":[93],"instruction":[95],"tuning":[96],"enhancing":[98],"instruction-following":[99],"capability,":[100],"value":[102],"alignment":[103],"aligning":[105],"with":[106],"human":[107],"values,":[108],"7":[110],"representative":[111],"FL":[112,144,172],"algorithms.":[113],"Besides,":[114],"OpenFedLLM":[115],"supports":[116],"diverse":[119],"domains,":[120],"cover":[123,133],"8":[124],"datasets;":[126],"provides":[128],"comprehensive":[129],"evaluations,":[130],"30+":[134],"evaluation":[135],"metrics.":[136],"Through":[137],"extensive":[138],"experiments,":[139],"observe":[141],"all":[143],"algorithms":[145],"outperform":[146,175],"local":[147],"LLMs,":[151],"demonstrating":[152,189],"clear":[154],"performance":[155],"improvement":[156],"variety":[159],"of":[160,207],"settings.":[161],"Notably,":[162],"financial":[165],"benchmark,":[166],"Llama2-7B":[167],"fine-tuned":[168],"by":[169,177],"applying":[170],"any":[171],"algorithm":[173],"can":[174],"GPT-4":[176],"significant":[179],"margin,":[180],"while":[181],"obtained":[184],"through":[185],"individual":[186],"cannot,":[188],"strong":[190],"motivation":[191],"clients":[193],"participate":[195],"FL.":[197],"The":[198,204],"code":[199],"at":[202,212],"https://github.com/rui-ye/OpenFedLLM.":[203],"full":[205],"version":[206],"our":[208],"paper":[209],"https://arxiv.org/pdf/2402.06954.":[213]},"counts_by_year":[{"year":2026,"cited_by_count":7},{"year":2025,"cited_by_count":63},{"year":2024,"cited_by_count":8}],"updated_date":"2026-03-27T05:58:40.876381","created_date":"2025-10-10T00:00:00"}