{"id":"https://openalex.org/W4392867124","doi":"https://doi.org/10.48550/arxiv.2403.09048","title":"Taming Cross-Domain Representation Variance in Federated Prototype Learning with Heterogeneous Data Domains","display_name":"Taming Cross-Domain Representation Variance in Federated Prototype Learning with Heterogeneous Data Domains","publication_year":2024,"publication_date":"2024-03-14","ids":{"openalex":"https://openalex.org/W4392867124","doi":"https://doi.org/10.48550/arxiv.2403.09048"},"language":"en","primary_location":{"id":"pmh:oai:arXiv.org:2403.09048","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2403.09048","pdf_url":"https://arxiv.org/pdf/2403.09048","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,"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"},"type":"preprint","indexed_in":["arxiv","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2403.09048","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5100436173","display_name":"Lei Wang","orcid":"https://orcid.org/0009-0003-1939-5532"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Wang, Lei","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5012540094","display_name":"Jieming Bian","orcid":"https://orcid.org/0000-0002-6372-6357"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Bian, Jieming","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101664149","display_name":"Letian Zhang","orcid":"https://orcid.org/0000-0002-6920-2052"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zhang, Letian","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100418548","display_name":"Chen Chen","orcid":"https://orcid.org/0000-0003-2104-534X"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Chen, Chen","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5100956664","display_name":"Jie Xu","orcid":"https://orcid.org/0009-0009-7766-8598"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Xu, Jie","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":1,"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":0.9693999886512756,"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":0.9693999886512756,"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":0.9218000173568726,"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/variance","display_name":"Variance (accounting)","score":0.7875794172286987},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.7461436986923218},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6614170670509338},{"id":"https://openalex.org/keywords/domain","display_name":"Domain (mathematical analysis)","score":0.6049138903617859},{"id":"https://openalex.org/keywords/external-data-representation","display_name":"External Data Representation","score":0.4833240509033203},{"id":"https://openalex.org/keywords/theoretical-computer-science","display_name":"Theoretical computer science","score":0.3939730226993561},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.37151598930358887},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.32021939754486084},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.19929492473602295},{"id":"https://openalex.org/keywords/political-science","display_name":"Political science","score":0.07469165325164795},{"id":"https://openalex.org/keywords/business","display_name":"Business","score":0.07240664958953857},{"id":"https://openalex.org/keywords/accounting","display_name":"Accounting","score":0.058169931173324585}],"concepts":[{"id":"https://openalex.org/C196083921","wikidata":"https://www.wikidata.org/wiki/Q7915758","display_name":"Variance (accounting)","level":2,"score":0.7875794172286987},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.7461436986923218},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6614170670509338},{"id":"https://openalex.org/C36503486","wikidata":"https://www.wikidata.org/wiki/Q11235244","display_name":"Domain (mathematical analysis)","level":2,"score":0.6049138903617859},{"id":"https://openalex.org/C116409475","wikidata":"https://www.wikidata.org/wiki/Q1385056","display_name":"External Data Representation","level":2,"score":0.4833240509033203},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.3939730226993561},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.37151598930358887},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.32021939754486084},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.19929492473602295},{"id":"https://openalex.org/C17744445","wikidata":"https://www.wikidata.org/wiki/Q36442","display_name":"Political science","level":0,"score":0.07469165325164795},{"id":"https://openalex.org/C144133560","wikidata":"https://www.wikidata.org/wiki/Q4830453","display_name":"Business","level":0,"score":0.07240664958953857},{"id":"https://openalex.org/C121955636","wikidata":"https://www.wikidata.org/wiki/Q4116214","display_name":"Accounting","level":1,"score":0.058169931173324585},{"id":"https://openalex.org/C94625758","wikidata":"https://www.wikidata.org/wiki/Q7163","display_name":"Politics","level":2,"score":0.0},{"id":"https://openalex.org/C199539241","wikidata":"https://www.wikidata.org/wiki/Q7748","display_name":"Law","level":1,"score":0.0},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"pmh:oai:arXiv.org:2403.09048","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2403.09048","pdf_url":"https://arxiv.org/pdf/2403.09048","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,"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.2403.09048","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2403.09048","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,"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:2403.09048","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2403.09048","pdf_url":"https://arxiv.org/pdf/2403.09048","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,"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":[],"awards":[{"id":"https://openalex.org/G1946296","display_name":"Collaborative Research: CCSS: Hierarchical Federated Learning over Highly-Dense and Overlapping NextG Wireless Deployments: Orchestrating Resources for Performance","funder_award_id":"2319780","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G3136170333","display_name":"Collaborative Research: CNS Core: Small: Towards Automated and QoE-driven Machine Learning Model Selection for Edge Inference","funder_award_id":"2006630","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G8997940623","display_name":"CCSS: Collaborative Research: Towards a Resource Rationing Framework for Wireless Federated Learning","funder_award_id":"2033681","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"}],"funders":[{"id":"https://openalex.org/F4320306076","display_name":"National Science Foundation","ror":"https://ror.org/021nxhr62"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4392867124.pdf","grobid_xml":"https://content.openalex.org/works/W4392867124.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W2062195135","https://openalex.org/W2795079307","https://openalex.org/W2917844847","https://openalex.org/W2036757537","https://openalex.org/W2759085743","https://openalex.org/W2096451653","https://openalex.org/W4282930045","https://openalex.org/W4238546310","https://openalex.org/W2143706788","https://openalex.org/W4387415041"],"abstract_inverted_index":{"Federated":[0,29],"learning":[1,6],"(FL)":[2],"allows":[3],"collaborative":[4],"machine":[5],"training":[7],"without":[8],"sharing":[9],"private":[10,105],"data.":[11],"While":[12],"most":[13],"FL":[14],"methods":[15,49],"assume":[16],"identical":[17],"data":[18,27,70,106,120],"domains":[19],"across":[20],"clients,":[21],"real-world":[22],"scenarios":[23],"often":[24],"involve":[25],"heterogeneous":[26],"domains.":[28],"Prototype":[30],"Learning":[31],"(FedPL)":[32],"addresses":[33],"this":[34],"issue,":[35],"using":[36],"mean":[37],"feature":[38,75],"vectors":[39],"as":[40],"prototypes":[41,55,85,96,102,111],"to":[42,60,113],"enhance":[43],"model":[44],"generalization.":[45],"However,":[46],"existing":[47,150],"FedPL":[48],"create":[50],"the":[51],"same":[52],"number":[53],"of":[54],"for":[56,66],"each":[57],"client,":[58],"leading":[59],"cross-domain":[61,74],"performance":[62],"gaps":[63],"and":[64,87,117,134,142],"disparities":[65],"clients":[67],"with":[68],"varied":[69],"distributions.":[71],"To":[72],"mitigate":[73],"representation":[76],"variance,":[77],"we":[78],"introduce":[79],"FedPLVM,":[80],"which":[81],"establishes":[82],"variance-aware":[83],"dual-level":[84,95],"clustering":[86,97,112],"employs":[88],"a":[89],"novel":[90],"$\u03b1$-sparsity":[91,123],"prototype":[92,124],"loss.":[93],"The":[94,122],"strategy":[98],"creates":[99],"local":[100,119],"clustered":[101],"based":[103],"on":[104,139],"features,":[107],"then":[108],"performs":[109],"global":[110],"reduce":[114],"communication":[115],"complexity":[116],"preserve":[118],"privacy.":[121],"loss":[125],"aligns":[126],"samples":[127],"from":[128],"underrepresented":[129],"domains,":[130],"enhancing":[131],"intra-class":[132],"similarity":[133],"reducing":[135],"inter-class":[136],"similarity.":[137],"Evaluations":[138],"Digit-5,":[140],"Office-10,":[141],"DomainNet":[143],"datasets":[144],"demonstrate":[145],"our":[146],"method's":[147],"superiority":[148],"over":[149],"approaches.":[151]},"counts_by_year":[{"year":2025,"cited_by_count":1}],"updated_date":"2026-08-26T07:47:46.906454","created_date":"2025-10-10T00:00:00"}