{"id":"https://openalex.org/W7160277455","doi":"https://doi.org/10.48550/arxiv.2605.02143","title":"Personalized Federated Learning for Gradient Alignment","display_name":"Personalized Federated Learning for Gradient Alignment","publication_year":2026,"publication_date":"2026-05-04","ids":{"openalex":"https://openalex.org/W7160277455","doi":"https://doi.org/10.48550/arxiv.2605.02143"},"language":null,"primary_location":{"id":"doi:10.48550/arxiv.2605.02143","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2605.02143","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"article"},"type":"preprint","indexed_in":["datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://doi.org/10.48550/arxiv.2605.02143","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5135363557","display_name":"Dongwon Kim","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Kim, Dongwon","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5002606546","display_name":"Gyuejeong Lee","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Lee, Gyuejeong","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"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":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":0.35920000076293945,"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":0.35920000076293945,"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/T13702","display_name":"Machine Learning in Healthcare","score":0.27140000462532043,"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/T10203","display_name":"Recommender Systems and Techniques","score":0.10249999910593033,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/personalization","display_name":"Personalization","score":0.7519999742507935},{"id":"https://openalex.org/keywords/federated-learning","display_name":"Federated learning","score":0.6033999919891357},{"id":"https://openalex.org/keywords/variance","display_name":"Variance (accounting)","score":0.5354999899864197},{"id":"https://openalex.org/keywords/bayesian-probability","display_name":"Bayesian probability","score":0.5077000260353088},{"id":"https://openalex.org/keywords/distortion","display_name":"Distortion (music)","score":0.4253000020980835},{"id":"https://openalex.org/keywords/bayesian-optimization","display_name":"Bayesian optimization","score":0.4009000062942505},{"id":"https://openalex.org/keywords/gradient-descent","display_name":"Gradient descent","score":0.36039999127388}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.795799970626831},{"id":"https://openalex.org/C183003079","wikidata":"https://www.wikidata.org/wiki/Q1000371","display_name":"Personalization","level":2,"score":0.7519999742507935},{"id":"https://openalex.org/C2992525071","wikidata":"https://www.wikidata.org/wiki/Q50818671","display_name":"Federated learning","level":2,"score":0.6033999919891357},{"id":"https://openalex.org/C196083921","wikidata":"https://www.wikidata.org/wiki/Q7915758","display_name":"Variance (accounting)","level":2,"score":0.5354999899864197},{"id":"https://openalex.org/C107673813","wikidata":"https://www.wikidata.org/wiki/Q812534","display_name":"Bayesian probability","level":2,"score":0.5077000260353088},{"id":"https://openalex.org/C126780896","wikidata":"https://www.wikidata.org/wiki/Q899871","display_name":"Distortion (music)","level":4,"score":0.4253000020980835},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4043999910354614},{"id":"https://openalex.org/C2778049539","wikidata":"https://www.wikidata.org/wiki/Q17002908","display_name":"Bayesian optimization","level":2,"score":0.4009000062942505},{"id":"https://openalex.org/C153258448","wikidata":"https://www.wikidata.org/wiki/Q1199743","display_name":"Gradient descent","level":3,"score":0.36039999127388},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.34389999508857727},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.31949999928474426},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.30219998955726624},{"id":"https://openalex.org/C12713177","wikidata":"https://www.wikidata.org/wiki/Q1900281","display_name":"Perspective (graphical)","level":2,"score":0.2969000041484833},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.2818000018596649},{"id":"https://openalex.org/C120314980","wikidata":"https://www.wikidata.org/wiki/Q180634","display_name":"Distributed computing","level":1,"score":0.27900001406669617},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.2639000117778778},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.2612999975681305},{"id":"https://openalex.org/C160234255","wikidata":"https://www.wikidata.org/wiki/Q812535","display_name":"Bayesian inference","level":3,"score":0.2612000107765198},{"id":"https://openalex.org/C48103436","wikidata":"https://www.wikidata.org/wiki/Q599031","display_name":"State (computer science)","level":2,"score":0.25429999828338623},{"id":"https://openalex.org/C2777211547","wikidata":"https://www.wikidata.org/wiki/Q17141490","display_name":"Training (meteorology)","level":2,"score":0.2522999942302704}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.48550/arxiv.2605.02143","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2605.02143","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"article"}],"best_oa_location":{"id":"doi:10.48550/arxiv.2605.02143","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2605.02143","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Personalized":[0],"federated":[1],"learning":[2],"(pFL)":[3],"aims":[4],"to":[5,8,17,56,78],"adapt":[6],"models":[7],"client":[9,35,41,58,82,118],"specific":[10,42,59,119],"data":[11],"distributions,":[12],"yet":[13],"it":[14],"often":[15],"fails":[16],"reliably":[18],"preserve":[19],"personalized":[20,100,114],"information.":[21,120],"Local":[22],"training":[23,64,134],"is":[24],"hindered":[25],"by":[26,31,92],"high":[27],"variance":[28,80],"gradients":[29],"induced":[30,90],"limited":[32],"and":[33,65,85,123,133],"heterogeneous":[34],"data,":[36],"while":[37],"aggregation":[38,89],"further":[39],"distorts":[40],"optimization":[43],"directions.":[44],"To":[45],"address":[46],"these":[47],"challenges,":[48],"we":[49,103],"propose":[50],"pFLAlign,":[51],"a":[52,107],"gradient":[53,76,115],"alignment":[54,116],"framework":[55],"maintain":[57],"information":[60],"during":[61,81],"both":[62],"local":[63,75],"aggregation.":[66],"pFLAlign":[67,105,128],"consists":[68],"of":[69,138],"two":[70],"complementary":[71],"mechanisms:":[72],"one":[73],"adapts":[74],"directions":[77],"reduce":[79],"side":[83],"optimization,":[84],"the":[86,94,139],"other":[87],"mitigates":[88],"distortion":[91],"realigning":[93],"global":[95],"model":[96],"with":[97],"each":[98],"client's":[99],"direction.":[101],"Theoretically,":[102],"derive":[104],"from":[106],"PAC":[108],"Bayesian":[109],"analysis,":[110],"which":[111],"reveals":[112],"how":[113],"preserves":[117],"Our":[121],"experiments":[122],"ablation":[124],"studies":[125],"show":[126],"that":[127],"consistently":[129],"improves":[130],"personalization":[131],"performance":[132],"stability,":[135],"achieving":[136],"state":[137],"art":[140],"results.":[141]},"counts_by_year":[],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2026-05-06T00:00:00"}