{"id":"https://openalex.org/W7151272514","doi":"https://doi.org/10.1109/icmla66185.2025.00012","title":"Information-Geometric Barycenters for Bayesian Federated Learning","display_name":"Information-Geometric Barycenters for Bayesian Federated Learning","publication_year":2025,"publication_date":"2025-12-03","ids":{"openalex":"https://openalex.org/W7151272514","doi":"https://doi.org/10.1109/icmla66185.2025.00012"},"language":null,"primary_location":{"id":"doi:10.1109/icmla66185.2025.00012","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icmla66185.2025.00012","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 International Conference on Machine Learning and Applications (ICMLA)","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/A5115505720","display_name":"Nour Jamoussi","orcid":null},"institutions":[{"id":"https://openalex.org/I1902872","display_name":"EURECOM","ror":"https://ror.org/00sse7z02","country_code":"FR","type":"education","lineage":["https://openalex.org/I1902872","https://openalex.org/I205703379"]}],"countries":["FR"],"is_corresponding":true,"raw_author_name":"Nour Jamoussi","raw_affiliation_strings":["EURECOM,Communication Systems Department,France"],"affiliations":[{"raw_affiliation_string":"EURECOM,Communication Systems Department,France","institution_ids":["https://openalex.org/I1902872"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5133093559","display_name":"Giuseppe Serra","orcid":null},"institutions":[{"id":"https://openalex.org/I1902872","display_name":"EURECOM","ror":"https://ror.org/00sse7z02","country_code":"FR","type":"education","lineage":["https://openalex.org/I1902872","https://openalex.org/I205703379"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"Giuseppe Serra","raw_affiliation_strings":["EURECOM,Communication Systems Department,France"],"affiliations":[{"raw_affiliation_string":"EURECOM,Communication Systems Department,France","institution_ids":["https://openalex.org/I1902872"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5111606657","display_name":"Photios A. Stavrou","orcid":null},"institutions":[{"id":"https://openalex.org/I1902872","display_name":"EURECOM","ror":"https://ror.org/00sse7z02","country_code":"FR","type":"education","lineage":["https://openalex.org/I1902872","https://openalex.org/I205703379"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"Photios A. Stavrou","raw_affiliation_strings":["EURECOM,Communication Systems Department,France"],"affiliations":[{"raw_affiliation_string":"EURECOM,Communication Systems Department,France","institution_ids":["https://openalex.org/I1902872"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5088602155","display_name":"Marios Kountouris","orcid":"https://orcid.org/0000-0003-1143-080X"},"institutions":[{"id":"https://openalex.org/I1902872","display_name":"EURECOM","ror":"https://ror.org/00sse7z02","country_code":"FR","type":"education","lineage":["https://openalex.org/I1902872","https://openalex.org/I205703379"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"Marios Kountouris","raw_affiliation_strings":["EURECOM,Communication Systems Department,France"],"affiliations":[{"raw_affiliation_string":"EURECOM,Communication Systems Department,France","institution_ids":["https://openalex.org/I1902872"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5115505720"],"corresponding_institution_ids":["https://openalex.org/I1902872"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.87274824,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"39","last_page":"46"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10764","display_name":"Privacy-Preserving Technologies in Data","score":0.6103000044822693,"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":0.6103000044822693,"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/T11689","display_name":"Adversarial Robustness in Machine Learning","score":0.07819999754428864,"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/T12814","display_name":"Gaussian Processes and Bayesian Inference","score":0.07349999994039536,"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/bayesian-probability","display_name":"Bayesian probability","score":0.4846000075340271},{"id":"https://openalex.org/keywords/federated-learning","display_name":"Federated learning","score":0.4505000114440918},{"id":"https://openalex.org/keywords/key","display_name":"Key (lock)","score":0.298799991607666},{"id":"https://openalex.org/keywords/bayesian-inference","display_name":"Bayesian inference","score":0.2921999990940094},{"id":"https://openalex.org/keywords/term","display_name":"Term (time)","score":0.28850001096725464}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6826000213623047},{"id":"https://openalex.org/C107673813","wikidata":"https://www.wikidata.org/wiki/Q812534","display_name":"Bayesian probability","level":2,"score":0.4846000075340271},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.48030000925064087},{"id":"https://openalex.org/C2992525071","wikidata":"https://www.wikidata.org/wiki/Q50818671","display_name":"Federated learning","level":2,"score":0.4505000114440918},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.29989999532699585},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.298799991607666},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.2944999933242798},{"id":"https://openalex.org/C160234255","wikidata":"https://www.wikidata.org/wiki/Q812535","display_name":"Bayesian inference","level":3,"score":0.2921999990940094},{"id":"https://openalex.org/C61797465","wikidata":"https://www.wikidata.org/wiki/Q1188986","display_name":"Term (time)","level":2,"score":0.28850001096725464},{"id":"https://openalex.org/C77618280","wikidata":"https://www.wikidata.org/wiki/Q1155772","display_name":"Scheme (mathematics)","level":2,"score":0.28619998693466187},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.2842000126838684},{"id":"https://openalex.org/C33724603","wikidata":"https://www.wikidata.org/wiki/Q812540","display_name":"Bayesian network","level":2,"score":0.25060001015663147}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icmla66185.2025.00012","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icmla66185.2025.00012","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 International Conference on Machine Learning and Applications (ICMLA)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.4584071934223175,"id":"https://metadata.un.org/sdg/13","display_name":"Climate action"}],"awards":[],"funders":[{"id":"https://openalex.org/F4320334678","display_name":"European Research Council","ror":"https://ror.org/0472cxd90"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":18,"referenced_works":["https://openalex.org/W1516111018","https://openalex.org/W1968333723","https://openalex.org/W2001610032","https://openalex.org/W2024522552","https://openalex.org/W2225156818","https://openalex.org/W2617587433","https://openalex.org/W2804763455","https://openalex.org/W2995022099","https://openalex.org/W3043426275","https://openalex.org/W3192098883","https://openalex.org/W4220861777","https://openalex.org/W4287332481","https://openalex.org/W4307362130","https://openalex.org/W4386075712","https://openalex.org/W4386608426","https://openalex.org/W4387449201","https://openalex.org/W4388156124","https://openalex.org/W4393178359"],"related_works":[],"abstract_inverted_index":{"Federated":[0,103],"learning":[1],"(FL)":[2],"is":[3,35],"a":[4,40,62,75,134],"widely":[5],"used":[6],"and":[7,83,110,160],"impactful":[8],"distributed":[9,112],"optimization":[10],"framework":[11,77],"that":[12,78,97,123],"achieves":[13,125],"consensus":[14],"by":[15],"averaging":[16],"locally":[17],"trained":[18],"models.":[19],"While":[20],"effective,":[21],"this":[22],"approach":[23],"may":[24],"not":[25],"align":[26],"well":[27],"with":[28,118],"Bayesian":[29,148,155],"inference,":[30],"where":[31],"the":[32,52,56,67,99,138,152],"model":[33,161],"space":[34],"more":[36],"naturally":[37],"represented":[38],"as":[39,51],"distribution":[41],"space.":[42],"Taking":[43],"an":[44,95],"information-geometric":[45],"perspective,":[46],"we":[47,114,142],"reinterpret":[48],"FL":[49],"aggregation":[50,120,139],"problem":[53],"of":[54,58,102,137,154],"finding":[55],"barycenter":[57],"local":[59],"posteriors":[60],"using":[61],"predefined":[63],"divergence":[64],"metric,":[65],"minimizing":[66],"average":[68],"discrepancy":[69],"across":[70],"clients.":[71],"This":[72],"perspective":[73],"provides":[74],"unifying":[76],"generalizes":[79],"many":[80],"existing":[81],"methods":[82,130],"offers":[84],"crisp":[85],"insights":[86],"into":[87],"their":[88],"theoretical":[89],"underpinnings.":[90],"We":[91],"then":[92],"propose":[93],"BA-BFL,":[94],"algorithm":[96],"retains":[98],"convergence":[100],"properties":[101],"Averaging":[104],"in":[105],"non-convex":[106],"settings.":[107],"In":[108],"non-independent":[109],"identically":[111],"scenarios,":[113],"conduct":[115],"extensive":[116],"comparisons":[117],"statistical":[119],"techniques,":[121],"showing":[122],"BA-BFL":[124],"performance":[126],"comparable":[127],"to":[128,146],"state-of-the-art":[129],"while":[131],"also":[132],"providing":[133],"geometric":[135],"interpretation":[136],"phase.":[140],"Additionally,":[141],"extend":[143],"our":[144],"analysis":[145],"Hybrid":[147],"Deep":[149],"Learning,":[150],"exploring":[151],"impact":[153],"layers":[156],"on":[157],"uncertainty":[158],"quantification":[159],"calibration.":[162]},"counts_by_year":[],"updated_date":"2026-04-09T06:08:40.794217","created_date":"2026-04-08T00:00:00"}