{"id":"https://openalex.org/W4407948867","doi":"https://doi.org/10.1109/cdc56724.2024.10886134","title":"Distributionally Robust Clustered Federated Learning: A Case Study in Healthcare","display_name":"Distributionally Robust Clustered Federated Learning: A Case Study in Healthcare","publication_year":2024,"publication_date":"2024-12-16","ids":{"openalex":"https://openalex.org/W4407948867","doi":"https://doi.org/10.1109/cdc56724.2024.10886134"},"language":"en","primary_location":{"id":"doi:10.1109/cdc56724.2024.10886134","is_oa":false,"landing_page_url":"https://doi.org/10.1109/cdc56724.2024.10886134","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 IEEE 63rd Conference on Decision and Control (CDC)","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/A5109819186","display_name":"Xenia Konti","orcid":null},"institutions":[{"id":"https://openalex.org/I170897317","display_name":"Duke University","ror":"https://ror.org/00py81415","country_code":"US","type":"education","lineage":["https://openalex.org/I170897317"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Xenia Konti","raw_affiliation_strings":["Duke University,Dept. of Computer Science"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Duke University,Dept. of Computer Science","institution_ids":["https://openalex.org/I170897317"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5014188872","display_name":"Hans Riess","orcid":"https://orcid.org/0000-0002-3768-0017"},"institutions":[{"id":"https://openalex.org/I170897317","display_name":"Duke University","ror":"https://ror.org/00py81415","country_code":"US","type":"education","lineage":["https://openalex.org/I170897317"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Hans Riess","raw_affiliation_strings":["Duke University,Dept. of Electrical and Computer Engineering"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Duke University,Dept. of Electrical and Computer Engineering","institution_ids":["https://openalex.org/I170897317"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5109819187","display_name":"Manos Giannopoulos","orcid":null},"institutions":[{"id":"https://openalex.org/I170897317","display_name":"Duke University","ror":"https://ror.org/00py81415","country_code":"US","type":"education","lineage":["https://openalex.org/I170897317"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Manos Giannopoulos","raw_affiliation_strings":["Duke University,Dept. of Computer Science"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Duke University,Dept. of Computer Science","institution_ids":["https://openalex.org/I170897317"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5009683062","display_name":"Yi Shen","orcid":"https://orcid.org/0009-0009-1578-4542"},"institutions":[{"id":"https://openalex.org/I170897317","display_name":"Duke University","ror":"https://ror.org/00py81415","country_code":"US","type":"education","lineage":["https://openalex.org/I170897317"]},{"id":"https://openalex.org/I4210129794","display_name":"Division of Materials Science and Engineering","ror":"https://ror.org/03rs0fg31","country_code":"AU","type":"facility","lineage":["https://openalex.org/I1292875679","https://openalex.org/I2801453606","https://openalex.org/I4210129794","https://openalex.org/I4387156119"]}],"countries":["AU","US"],"is_corresponding":false,"raw_author_name":"Yi Shen","raw_affiliation_strings":["Duke University,Dept. of Mechanical Engineering & Materials Science"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Duke University,Dept. of Mechanical Engineering & Materials Science","institution_ids":["https://openalex.org/I4210129794","https://openalex.org/I170897317"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5064002558","display_name":"Michael Pencina","orcid":"https://orcid.org/0000-0002-1968-2641"},"institutions":[{"id":"https://openalex.org/I170897317","display_name":"Duke University","ror":"https://ror.org/00py81415","country_code":"US","type":"education","lineage":["https://openalex.org/I170897317"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Michael J. Pencina","raw_affiliation_strings":["Duke University,School of Medicine"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Duke University,School of Medicine","institution_ids":["https://openalex.org/I170897317"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5062106549","display_name":"Nicoleta Economou-Zavlanos","orcid":"https://orcid.org/0009-0000-4078-9809"},"institutions":[{"id":"https://openalex.org/I170897317","display_name":"Duke University","ror":"https://ror.org/00py81415","country_code":"US","type":"education","lineage":["https://openalex.org/I170897317"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Nicoleta J Economou-Zavlanos","raw_affiliation_strings":["Duke University,School of Medicine"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Duke University,School of Medicine","institution_ids":["https://openalex.org/I170897317"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5080808780","display_name":"Michael M. Zavlanos","orcid":"https://orcid.org/0000-0003-1748-8228"},"institutions":[{"id":"https://openalex.org/I170897317","display_name":"Duke University","ror":"https://ror.org/00py81415","country_code":"US","type":"education","lineage":["https://openalex.org/I170897317"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Michael M. Zavlanos","raw_affiliation_strings":["Duke University,Dept. of Computer Science"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Duke University,Dept. of Computer Science","institution_ids":["https://openalex.org/I170897317"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":7,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.6109,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":{"value":0.76304138,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":95,"max":96},"biblio":{"volume":null,"issue":null,"first_page":"4165","last_page":"4172"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10764","display_name":"Privacy-Preserving Technologies in Data","score":0.9599999785423279,"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":0.9599999785423279,"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/health-care","display_name":"Health care","score":0.7205975651741028},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6324710249900818},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4383890628814697},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.32302212715148926},{"id":"https://openalex.org/keywords/economics","display_name":"Economics","score":0.10096636414527893}],"concepts":[{"id":"https://openalex.org/C160735492","wikidata":"https://www.wikidata.org/wiki/Q31207","display_name":"Health care","level":2,"score":0.7205975651741028},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6324710249900818},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4383890628814697},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.32302212715148926},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.10096636414527893},{"id":"https://openalex.org/C50522688","wikidata":"https://www.wikidata.org/wiki/Q189833","display_name":"Economic growth","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/cdc56724.2024.10886134","is_oa":false,"landing_page_url":"https://doi.org/10.1109/cdc56724.2024.10886134","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 IEEE 63rd Conference on Decision and Control (CDC)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320306157","display_name":"Duke Endowment","ror":"https://ror.org/00rs28409"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":34,"referenced_works":["https://openalex.org/W2035028841","https://openalex.org/W2116200501","https://openalex.org/W2156909104","https://openalex.org/W2435667741","https://openalex.org/W2541678333","https://openalex.org/W2891400669","https://openalex.org/W2903777941","https://openalex.org/W2963450292","https://openalex.org/W2995022099","https://openalex.org/W3080934299","https://openalex.org/W3081178085","https://openalex.org/W3100779497","https://openalex.org/W3104631511","https://openalex.org/W3112044954","https://openalex.org/W3133814152","https://openalex.org/W3193589553","https://openalex.org/W4226461837","https://openalex.org/W4281753687","https://openalex.org/W4306317443","https://openalex.org/W4312703068","https://openalex.org/W4360995590","https://openalex.org/W4376636921","https://openalex.org/W6728757088","https://openalex.org/W6755506522","https://openalex.org/W6758757267","https://openalex.org/W6759226220","https://openalex.org/W6774195376","https://openalex.org/W6779468803","https://openalex.org/W6785768294","https://openalex.org/W6802056399","https://openalex.org/W6810945648","https://openalex.org/W6839017601","https://openalex.org/W6839684855","https://openalex.org/W6853654570"],"related_works":["https://openalex.org/W2961085424","https://openalex.org/W4306674287","https://openalex.org/W4387369504","https://openalex.org/W3046775127","https://openalex.org/W4394896187","https://openalex.org/W3170094116","https://openalex.org/W4386462264","https://openalex.org/W3107602296","https://openalex.org/W4364306694","https://openalex.org/W4312192474"],"abstract_inverted_index":{"In":[0],"this":[1],"paper,":[2],"we":[3,21,105],"address":[4],"the":[5,32,50,69,83,113],"challenge":[6],"of":[7,55,74,115],"heterogeneous":[8,89],"data":[9],"distributions":[10],"in":[11,49,82],"cross-silo":[12],"federated":[13,108],"learning":[14,109],"by":[15,87],"introducing":[16],"a":[17,62,107,118],"novel":[18],"algorithm,":[19],"which":[20],"term":[22],"Cross-silo":[23],"Robust":[24],"Clustered":[25],"Federated":[26],"Learning":[27],"(CS-RCFL).":[28],"Our":[29],"approach":[30],"leverages":[31],"Wasserstein":[33],"distance":[34],"to":[35,67],"construct":[36],"ambiguity":[37],"sets":[38],"around":[39],"each":[40],"client\u2019s":[41],"empirical":[42],"distribution":[43,47],"that":[44,79,111],"capture":[45],"possible":[46,80],"shifts":[48],"local":[51,84],"data,":[52],"enabling":[53],"evaluation":[54],"worst-case":[56],"model":[57],"performance.":[58],"We":[59,128],"then":[60],"propose":[61],"model-agnostic":[63],"integer":[64],"fractional":[65],"program":[66],"determine":[68],"optimal":[70],"distributionally":[71],"robust":[72],"clustering":[73],"clients":[75,124],"into":[76],"coalitions":[77],"so":[78],"biases":[81],"models":[85],"caused":[86],"statistically":[88],"client":[90,116],"datasets":[91],"are":[92,125],"avoided,":[93],"and":[94,100,134],"analyze":[95],"our":[96,130],"method":[97],"for":[98,121],"linear":[99],"logistic":[101],"regression":[102],"models.":[103],"Finally,":[104],"discuss":[106],"protocol":[110],"ensures":[112],"privacy":[114],"distributions,":[117],"critical":[119],"consideration,":[120],"instance,":[122],"when":[123],"healthcare":[126,136],"institutions.":[127],"evaluate":[129],"algorithm":[131],"on":[132],"synthetic":[133],"real-world":[135],"data.":[137]},"counts_by_year":[{"year":2025,"cited_by_count":2}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}