{"id":"https://openalex.org/W3194748595","doi":null,"title":"Fine-tuning is Fine in Federated Learning","display_name":"Fine-tuning is Fine in Federated Learning","publication_year":2021,"publication_date":"2021-08-16","ids":{"openalex":"https://openalex.org/W3194748595","mag":"3194748595"},"language":"en","primary_location":{"id":"mag:3194748595","doi":null,"is_oa":true,"landing_page_url":"http://export.arxiv.org/pdf/2108.07313","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"arXiv (Cornell University)","raw_type":null},"volume":null,"type":"preprint","is_traditional":true,"indexed_in":[],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"http://export.arxiv.org/pdf/2108.07313","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":null,"display_name":"Gary Cheng","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Gary Cheng","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5063754276","display_name":"Karan N. Chadha","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Karan N. Chadha","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5061331093","display_name":"John C. Duchi","orcid":"https://orcid.org/0000-0003-0045-7185","observed_orcids":["https://orcid.org/0000-0003-0045-7185"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"John C. Duchi","raw_affiliation_strings":[],"raw_orcid":"https://orcid.org/0000-0003-0045-7185","affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":15,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10764","display_name":"Privacy-Preserving Technologies in Data","score":0.9994999766349792,"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":0.9994999766349792,"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":9.999999747378752e-05,"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":9.999999747378752e-05,"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":0.996999979019165},{"id":"https://openalex.org/keywords/fine-tuning","display_name":"fine-tuning","score":0.890999972820282},{"id":"https://openalex.org/keywords/fedavg","display_name":"FedAvg","score":0.871999979019165},{"id":"https://openalex.org/keywords/tikhonov-regularization","display_name":"Tikhonov regularization","score":0.5450000166893005},{"id":"https://openalex.org/keywords/multi-criterion-optimization","display_name":"multi-criterion optimization","score":0.7139999866485596},{"id":"https://openalex.org/keywords/high-dimensional-asymptotics","display_name":"high-dimensional asymptotics","score":0.8339999914169312},{"id":"https://openalex.org/keywords/personalization","display_name":"personalization","score":0.6629999876022339},{"id":"https://openalex.org/keywords/meta-learning","display_name":"meta-learning","score":0.7009999752044678},{"id":"https://openalex.org/keywords/proximal-regularization","display_name":"proximal regularization","score":0.9089999794960022},{"id":"https://openalex.org/keywords/linear-regression","display_name":"linear regression","score":0.5709999799728394},{"id":"https://openalex.org/keywords/local-training","display_name":"local training","score":0.4269999861717224}],"concepts":[{"id":"https://openalex.org/C2992525071","wikidata":"https://www.wikidata.org/wiki/Q50818671","display_name":"Federated learning","level":2,"score":0.8266657590866089},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7413660287857056},{"id":"https://openalex.org/C32277403","wikidata":"https://www.wikidata.org/wiki/Q740445","display_name":"Ridge","level":2,"score":0.6510756611824036},{"id":"https://openalex.org/C183003079","wikidata":"https://www.wikidata.org/wiki/Q1000371","display_name":"Personalization","level":2,"score":0.588829517364502},{"id":"https://openalex.org/C28719098","wikidata":"https://www.wikidata.org/wiki/Q44946","display_name":"Point (geometry)","level":2,"score":0.5692721009254456},{"id":"https://openalex.org/C127576917","wikidata":"https://www.wikidata.org/wiki/Q624630","display_name":"Competitor analysis","level":2,"score":0.519666314125061},{"id":"https://openalex.org/C2986087404","wikidata":"https://www.wikidata.org/wiki/Q15946010","display_name":"Online learning","level":2,"score":0.5078116059303284},{"id":"https://openalex.org/C151201525","wikidata":"https://www.wikidata.org/wiki/Q177239","display_name":"Limit (mathematics)","level":2,"score":0.5077201128005981},{"id":"https://openalex.org/C2779582901","wikidata":"https://www.wikidata.org/wiki/Q21013010","display_name":"Distributed learning","level":2,"score":0.459408164024353},{"id":"https://openalex.org/C9395851","wikidata":"https://www.wikidata.org/wiki/Q177929","display_name":"Stack (abstract data type)","level":2,"score":0.43313223123550415},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.323810338973999},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.15278705954551697},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.07327580451965332},{"id":"https://openalex.org/C19417346","wikidata":"https://www.wikidata.org/wiki/Q7922","display_name":"Pedagogy","level":1,"score":0.0},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"id":"https://openalex.org/C187736073","wikidata":"https://www.wikidata.org/wiki/Q2920921","display_name":"Management","level":1,"score":0.0},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.0},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.0},{"id":"https://openalex.org/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","level":1,"score":0.0},{"id":"https://openalex.org/C151730666","wikidata":"https://www.wikidata.org/wiki/Q7205","display_name":"Paleontology","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"mag:3194748595","doi":null,"is_oa":true,"landing_page_url":"http://export.arxiv.org/pdf/2108.07313","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"arXiv (Cornell University)","raw_type":null}],"best_oa_location":{"id":"mag:3194748595","doi":null,"is_oa":true,"landing_page_url":"http://export.arxiv.org/pdf/2108.07313","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"arXiv (Cornell University)","raw_type":null},"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":12,"referenced_works":["https://openalex.org/W1981573335","https://openalex.org/W2155195660","https://openalex.org/W2165698076","https://openalex.org/W2923764619","https://openalex.org/W2976335444","https://openalex.org/W2982654255","https://openalex.org/W2995022099","https://openalex.org/W3007548213","https://openalex.org/W3008187686","https://openalex.org/W3035668299","https://openalex.org/W3044211235","https://openalex.org/W4401412995"],"related_works":["https://openalex.org/W3208210999","https://openalex.org/W4291165960","https://openalex.org/W3134581569","https://openalex.org/W4388843343","https://openalex.org/W7155175638","https://openalex.org/W4382463479","https://openalex.org/W4283687253","https://openalex.org/W4416359326","https://openalex.org/W4387544171","https://openalex.org/W3176457956"],"abstract_inverted_index":{"We":[0,44,139],"study":[1],"the":[2,19,29,42,58,64,74,106,151],"performance":[3,59],"of":[4,21,41,60,78,150],"federated":[5,22,79,88,148],"learning":[6,23,80],"algorithms":[7,62],"and":[8,81,105,120,130,155],"their":[9],"variants":[10],"in":[11,63],"an":[12],"asymptotic":[13,66,69],"framework.":[14],"Our":[15,90],"starting":[16],"point":[17],"is":[18,31,85],"formulation":[20],"as":[24],"a":[25,46,52],"multi-criterion":[26,70],"objective,":[27],"where":[28],"goal":[30],"to":[32,87,125],"minimize":[33],"each":[34],"client's":[35],"loss":[36],"using":[37],"information":[38],"from":[39],"all":[40],"clients.":[43],"propose":[45],"linear":[47],"regression":[48],"model,":[49],"where,":[50],"for":[51],"given":[53],"client,":[54],"we":[55],"theoretically":[56],"compare":[57],"various":[61],"high-dimensional":[65],"limit.":[67],"This":[68],"approach":[71],"naturally":[72],"models":[73],"high-dimensional,":[75],"many-device":[76],"nature":[77],"suggests":[82,92],"that":[83,93],"personalization":[84],"central":[86],"learning.":[89],"theory":[91],"Fine-tuned":[94],"Federated":[95,99,111],"Averaging":[96,100,112],"(FTFA),":[97],"i.e.,":[98],"followed":[101],"by":[102],"local":[103],"training,":[104],"ridge":[107],"regularized":[108],"variant":[109],"Ridge-tuned":[110],"(RTFA)":[113],"are":[114,132],"competitive":[115],"with":[116,144],"more":[117,134],"sophisticated":[118],"meta-learning":[119],"proximal-regularized":[121],"approaches.":[122],"In":[123],"addition":[124],"being":[126],"conceptually":[127],"simpler,":[128],"FTFA":[129],"RTFA":[131],"computationally":[133],"efficient":[135],"than":[136],"its":[137],"competitors.":[138],"corroborate":[140],"our":[141],"theoretical":[142],"claims":[143],"extensive":[145],"experiments":[146],"on":[147],"versions":[149],"EMNIST,":[152],"CIFAR-100,":[153],"Shakespeare,":[154],"Stack":[156],"Overflow":[157],"datasets.":[158]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":8},{"year":2023,"cited_by_count":3},{"year":2022,"cited_by_count":2},{"year":2021,"cited_by_count":1}],"updated_date":"2026-11-04T10:54:05.112534","created_date":"2021-08-30T00:00:00"}