{"id":"https://openalex.org/W4393956393","doi":"https://doi.org/10.1145/3603166.3632559","title":"Architecture-Based FedAvg for Vertical Federated Learning","display_name":"Architecture-Based FedAvg for Vertical Federated Learning","publication_year":2023,"publication_date":"2023-12-04","ids":{"openalex":"https://openalex.org/W4393956393","doi":"https://doi.org/10.1145/3603166.3632559"},"language":"en","primary_location":{"id":"doi:10.1145/3603166.3632559","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3603166.3632559","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3603166.3632559","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the IEEE/ACM 16th International Conference on Utility and Cloud Computing","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://dl.acm.org/doi/pdf/10.1145/3603166.3632559","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5005431414","display_name":"Bruno Casella","orcid":"https://orcid.org/0000-0002-9513-6087"},"institutions":[{"id":"https://openalex.org/I55143463","display_name":"University of Turin","ror":"https://ror.org/048tbm396","country_code":"IT","type":"education","lineage":["https://openalex.org/I55143463"]}],"countries":["IT"],"is_corresponding":true,"raw_author_name":"Bruno Casella","raw_affiliation_strings":["Computer Science, University of Turin, Turin, Piedmont, IT"],"raw_orcid":"https://orcid.org/0000-0002-9513-6087","affiliations":[{"raw_affiliation_string":"Computer Science, University of Turin, Turin, Piedmont, IT","institution_ids":["https://openalex.org/I55143463"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5093750804","display_name":"Samuele Fonio","orcid":"https://orcid.org/0009-0003-1870-4233"},"institutions":[{"id":"https://openalex.org/I55143463","display_name":"University of Turin","ror":"https://ror.org/048tbm396","country_code":"IT","type":"education","lineage":["https://openalex.org/I55143463"]}],"countries":["IT"],"is_corresponding":false,"raw_author_name":"Samuele Fonio","raw_affiliation_strings":["Computer Science, Universit\u00e0 degli studi di Torino, Turin, Piedmont, IT"],"raw_orcid":"https://orcid.org/0009-0003-1870-4233","affiliations":[{"raw_affiliation_string":"Computer Science, Universit\u00e0 degli studi di Torino, Turin, Piedmont, IT","institution_ids":["https://openalex.org/I55143463"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5005431414"],"corresponding_institution_ids":["https://openalex.org/I55143463"],"apc_list":null,"apc_paid":null,"fwci":0.6816,"has_fulltext":true,"cited_by_count":4,"citation_normalized_percentile":{"value":0.77160504,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":94,"max":96},"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"6"},"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/T10237","display_name":"Cryptography and Data Security","score":0.9990000128746033,"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":0.9815000295639038,"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/computer-science","display_name":"Computer science","score":0.7485281229019165},{"id":"https://openalex.org/keywords/architecture","display_name":"Architecture","score":0.6535604000091553},{"id":"https://openalex.org/keywords/computer-architecture","display_name":"Computer architecture","score":0.5841472148895264},{"id":"https://openalex.org/keywords/software-engineering","display_name":"Software engineering","score":0.3543889820575714}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7485281229019165},{"id":"https://openalex.org/C123657996","wikidata":"https://www.wikidata.org/wiki/Q12271","display_name":"Architecture","level":2,"score":0.6535604000091553},{"id":"https://openalex.org/C118524514","wikidata":"https://www.wikidata.org/wiki/Q173212","display_name":"Computer architecture","level":1,"score":0.5841472148895264},{"id":"https://openalex.org/C115903868","wikidata":"https://www.wikidata.org/wiki/Q80993","display_name":"Software engineering","level":1,"score":0.3543889820575714},{"id":"https://openalex.org/C153349607","wikidata":"https://www.wikidata.org/wiki/Q36649","display_name":"Visual arts","level":1,"score":0.0},{"id":"https://openalex.org/C142362112","wikidata":"https://www.wikidata.org/wiki/Q735","display_name":"Art","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3603166.3632559","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3603166.3632559","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3603166.3632559","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the IEEE/ACM 16th International Conference on Utility and Cloud Computing","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.1145/3603166.3632559","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3603166.3632559","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3603166.3632559","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the IEEE/ACM 16th International Conference on Utility and Cloud Computing","raw_type":"proceedings-article"},"sustainable_development_goals":[{"display_name":"Industry, innovation and infrastructure","score":0.4300000071525574,"id":"https://metadata.un.org/sdg/9"},{"display_name":"Partnerships for the goals","score":0.4099999964237213,"id":"https://metadata.un.org/sdg/17"}],"awards":[{"id":"https://openalex.org/G4324742202","display_name":null,"funder_award_id":"826647","funder_id":"https://openalex.org/F4320332999","funder_display_name":"Horizon 2020 Framework Programme"},{"id":"https://openalex.org/G4339894583","display_name":null,"funder_award_id":"826647","funder_id":"https://openalex.org/F4320320300","funder_display_name":"European Commission"},{"id":"https://openalex.org/G4937468798","display_name":null,"funder_award_id":"H2020","funder_id":"https://openalex.org/F4320320300","funder_display_name":"European Commission"}],"funders":[{"id":"https://openalex.org/F4320320300","display_name":"European Commission","ror":"https://ror.org/00k4n6c32"},{"id":"https://openalex.org/F4320332999","display_name":"Horizon 2020 Framework Programme","ror":"https://ror.org/00k4n6c32"}],"has_content":{"grobid_xml":false,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4393956393.pdf"},"referenced_works_count":13,"referenced_works":["https://openalex.org/W1483118642","https://openalex.org/W2194775991","https://openalex.org/W2560584411","https://openalex.org/W2761668583","https://openalex.org/W2889669663","https://openalex.org/W2912213068","https://openalex.org/W2949185485","https://openalex.org/W3122794187","https://openalex.org/W3197337676","https://openalex.org/W4287332481","https://openalex.org/W4316468938","https://openalex.org/W4387408303","https://openalex.org/W4387546967"],"related_works":["https://openalex.org/W2748952813","https://openalex.org/W2390279801","https://openalex.org/W2358668433","https://openalex.org/W2376932109","https://openalex.org/W2001405890","https://openalex.org/W2382290278","https://openalex.org/W2478288626","https://openalex.org/W4391913857","https://openalex.org/W2350741829","https://openalex.org/W2038503502"],"abstract_inverted_index":{"Federated":[0],"Learning":[1,17],"(FL)":[2],"has":[3],"emerged":[4],"as":[5,90],"a":[6,81,91,97,157,178],"promising":[7],"solution":[8],"to":[9,57,169,195],"address":[10],"privacy":[11],"concerns":[12],"by":[13,193,205],"collaboratively":[14],"training":[15,201],"Deep":[16],"(DL)":[18],"models":[19,56,192],"across":[20],"distributed":[21],"parties.":[22],"This":[23,111],"work":[24],"proposes":[25],"an":[26],"architecture-based":[27],"aggregation":[28],"strategy":[29,102],"in":[30,149,156],"Vertical":[31],"FL,":[32],"where":[33,83],"parties":[34],"hold":[35],"data":[36,153,159],"with":[37,67,145],"different":[38,55,70],"attributes":[39],"but":[40,189],"shared":[41],"instances.":[42],"Our":[43],"approach":[44,124],"leverages":[45],"the":[46,104,130,134,146,152,170,183,208],"identical":[47,109],"architectural":[48],"parts,":[49],"i.e.":[50],"neural":[51],"network":[52],"layers,":[53],"of":[54,72],"selectively":[58],"aggregate":[59],"weights,":[60],"which":[61,150],"is":[62],"particularly":[63],"relevant":[64],"when":[65],"collaborating":[66],"institutions":[68],"holding":[69],"types":[71],"datasets,":[73,128],"i.e.,":[74,129],"image,":[75],"text,":[76],"or":[77],"tabular":[78],"datasets.":[79],"In":[80,166],"scenario":[82],"two":[84,126],"entities":[85],"train":[86],"DL":[87],"models,":[88,172],"such":[89],"Convolutional":[92],"Neural":[93],"Network":[94],"(CNN)":[95],"and":[96,118,133,161],"Multi-Layer":[98],"Perceptron":[99],"(MLP),":[100],"our":[101,123,140,173],"computes":[103],"average":[105],"only":[106,207],"for":[107],"architecturally":[108],"segments.":[110],"preserves":[112],"data-specific":[113],"features":[114],"learned":[115],"from":[116,163],"demographic":[117],"clinical":[119,127],"data.":[120],"We":[121],"tested":[122],"on":[125,182],"COVID-CXR":[131,184],"dataset":[132,185],"ADNI":[135,191],"study.":[136],"Results":[137],"show":[138],"that":[139],"method":[141],"achieves":[142],"comparable":[143],"results":[144],"centralized":[147],"scenario,":[148],"all":[151],"are":[154,203],"collected":[155],"single":[158],"lake,":[160],"benefits":[162],"FL":[164],"generalizability.":[165],"particular,":[167],"compared":[168],"non-federated":[171],"proposed":[174],"proof-of-concept":[175],"model":[176],"exhibits":[177],"slight":[179],"performance":[180],"loss":[181],"(less":[186],"than":[187],"8%),":[188],"outperforms":[190],"up":[194],"12%.":[196],"Moreover,":[197],"communication":[198],"costs":[199],"between":[200],"rounds":[202],"minimized":[204],"exchanging":[206],"dense":[209],"layer":[210],"parameters.":[211]},"counts_by_year":[{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":2}],"updated_date":"2025-12-26T23:08:49.675405","created_date":"2025-10-10T00:00:00"}