{"id":"https://openalex.org/W4415158317","doi":"https://doi.org/10.48550/arxiv.2504.09850","title":"Accelerating Differentially Private Federated Learning via Adaptive Extrapolation","display_name":"Accelerating Differentially Private Federated Learning via Adaptive Extrapolation","publication_year":2025,"publication_date":"2025-04-14","ids":{"openalex":"https://openalex.org/W4415158317","doi":"https://doi.org/10.48550/arxiv.2504.09850"},"language":"en","primary_location":{"id":"pmh:oai:arXiv.org:2504.09850","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2504.09850","pdf_url":"https://arxiv.org/pdf/2504.09850","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":null,"raw_type":"text"},"volume":null,"type":"preprint","indexed_in":["arxiv","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2504.09850","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5119989939","display_name":"Shokichi Takakura","orcid":"https://orcid.org/0000-0002-4672-9855","observed_orcids":["https://orcid.org/0000-0002-4672-9855"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Takakura, Shokichi","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5048228893","display_name":"Seng Pei Liew","orcid":"https://orcid.org/0000-0003-2419-2505","observed_orcids":["https://orcid.org/0000-0003-2419-2505"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Liew, Seng Pei","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":null,"display_name":"Hasegawa, Satoshi","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Hasegawa, Satoshi","raw_affiliation_strings":[],"raw_orcid":null,"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":true,"cited_by_count":0,"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":1.0,"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":1.0,"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":0.0,"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/T12535","display_name":"Machine Learning and Data Classification","score":0.0,"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/differential-privacy","display_name":"differential privacy","score":0.7400000095367432},{"id":"https://openalex.org/keywords/federated-learning","display_name":"federated learning","score":0.9980000257492065},{"id":"https://openalex.org/keywords/convergence-acceleration","display_name":"convergence acceleration","score":0.8489999771118164},{"id":"https://openalex.org/keywords/non-iid-data","display_name":"non-IID data","score":0.7260000109672546},{"id":"https://openalex.org/keywords/privacy-attacks","display_name":"privacy attacks","score":0.46299999952316284}],"concepts":[{"id":"https://openalex.org/C8642999","wikidata":"https://www.wikidata.org/wiki/Q4171168","display_name":"Hyperparameter","level":2,"score":0.8855999708175659},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8165000081062317},{"id":"https://openalex.org/C2777303404","wikidata":"https://www.wikidata.org/wiki/Q759757","display_name":"Convergence (economics)","level":2,"score":0.6510000228881836},{"id":"https://openalex.org/C23130292","wikidata":"https://www.wikidata.org/wiki/Q5275358","display_name":"Differential privacy","level":2,"score":0.5748000144958496},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.532800018787384},{"id":"https://openalex.org/C132459708","wikidata":"https://www.wikidata.org/wiki/Q744069","display_name":"Extrapolation","level":2,"score":0.5034999847412109},{"id":"https://openalex.org/C2992525071","wikidata":"https://www.wikidata.org/wiki/Q50818671","display_name":"Federated learning","level":2,"score":0.4839000105857849},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4440999925136566},{"id":"https://openalex.org/C123201435","wikidata":"https://www.wikidata.org/wiki/Q456632","display_name":"Information privacy","level":2,"score":0.37279999256134033},{"id":"https://openalex.org/C132964779","wikidata":"https://www.wikidata.org/wiki/Q2110223","display_name":"Raw data","level":2,"score":0.33970001339912415},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.337799996137619},{"id":"https://openalex.org/C2779582901","wikidata":"https://www.wikidata.org/wiki/Q21013010","display_name":"Distributed learning","level":2,"score":0.3294999897480011},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.3003000020980835},{"id":"https://openalex.org/C120314980","wikidata":"https://www.wikidata.org/wiki/Q180634","display_name":"Distributed computing","level":1,"score":0.29260000586509705},{"id":"https://openalex.org/C2779530757","wikidata":"https://www.wikidata.org/wiki/Q1207505","display_name":"Quality (philosophy)","level":2,"score":0.27480000257492065},{"id":"https://openalex.org/C179799912","wikidata":"https://www.wikidata.org/wiki/Q205084","display_name":"Computational complexity theory","level":2,"score":0.2741999924182892},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.27090001106262207},{"id":"https://openalex.org/C151201525","wikidata":"https://www.wikidata.org/wiki/Q177239","display_name":"Limit (mathematics)","level":2,"score":0.2581000030040741}],"mesh":[],"locations_count":2,"locations":[{"id":"pmh:oai:arXiv.org:2504.09850","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2504.09850","pdf_url":"https://arxiv.org/pdf/2504.09850","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":null,"raw_type":"text"},{"id":"doi:10.48550/arxiv.2504.09850","doi":"https://doi.org/10.48550/arxiv.2504.09850","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2504.09850","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":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2504.09850","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2504.09850","pdf_url":"https://arxiv.org/pdf/2504.09850","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":null,"raw_type":"text"},"sustainable_development_goals":[],"sustainable_development_goals_aurora":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4415158317.pdf","grobid_xml":"https://content.openalex.org/works/W4415158317.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"The":[0],"federated":[1],"learning":[2,12],"(FL)":[3],"framework":[4],"enables":[5],"multiple":[6],"clients":[7,113],"to":[8,23,30,56,75],"collaboratively":[9],"train":[10],"machine":[11],"models":[13],"without":[14,139],"sharing":[15],"their":[16],"raw":[17],"data,":[18],"but":[19,52],"it":[20,53,159],"remains":[21],"vulnerable":[22],"privacy":[24,33,109],"attacks.":[25],"One":[26],"promising":[27],"approach":[28],"is":[29,43,54,90,97],"incorporate":[31],"differential":[32],"(DP)-a":[34],"formal":[35],"notion":[36],"of":[37,45,65,71,103,108,135,156],"privacy-into":[38],"the":[39,46,59,63,72,106,127,133,136,154],"FL":[40],"framework.":[41],"DP-FedAvg":[42,157],"one":[44],"most":[47],"popular":[48],"algorithms":[49],"for":[50,87,165],"DP-FL,":[51],"known":[55],"suffer":[57],"from":[58],"slow":[60],"convergence":[61,155],"in":[62],"presence":[64],"heterogeneity":[66],"among":[67],"clients'":[68],"data.":[69],"Most":[70],"existing":[73,162],"methods":[74,163],"accelerate":[76],"DP-FL":[77],"require":[78],"1)":[79,94],"additional":[80,84,142],"hyperparameters":[81,104,143],"or":[82,144],"2)":[83,112],"computational":[85,146],"cost":[86],"clients,":[88],"which":[89,124],"not":[91],"desirable":[92],"since":[93],"hyperparameter":[95],"tuning":[96],"computationally":[98],"expensive":[99],"and":[100,111,158],"data-dependent":[101],"choice":[102],"raises":[105],"risk":[107],"leakage,":[110],"are":[114],"often":[115],"resource-constrained.":[116],"To":[117],"address":[118],"this":[119],"issue,":[120],"we":[121],"propose":[122],"DP-FedEXP,":[123],"adaptively":[125],"selects":[126],"global":[128],"step":[129],"size":[130],"based":[131],"on":[132],"diversity":[134],"local":[137],"updates":[138],"requiring":[140],"any":[141],"client":[145],"cost.":[147],"We":[148],"show":[149],"that":[150],"DP-FedEXP":[151],"provably":[152],"accelerates":[153],"empirically":[160],"outperforms":[161],"tailored":[164],"DP-FL.":[166]},"counts_by_year":[],"updated_date":"2026-09-29T14:09:16.559479","created_date":"2025-10-14T00:00:00"}