{"id":"https://openalex.org/W7129059544","doi":"https://doi.org/10.48550/arxiv.2602.12708","title":"Mixture of Predefined Experts: Maximizing Data Usage on Vertical Federated Learning","display_name":"Mixture of Predefined Experts: Maximizing Data Usage on Vertical Federated Learning","publication_year":2026,"publication_date":"2026-02-13","ids":{"openalex":"https://openalex.org/W7129059544","doi":"https://doi.org/10.48550/arxiv.2602.12708"},"language":null,"primary_location":{"id":"pmh:doi:10.48550/arxiv.2602.12708","is_oa":true,"landing_page_url":null,"pdf_url":null,"source":{"id":"https://openalex.org/S4406922384","display_name":"Open MIND","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":"publisher-specific-oa","license_id":"https://openalex.org/licenses/publisher-specific-oa","version":"submittedVersion","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":null,"any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5114617573","display_name":"Jon Irureta","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Irureta, Jon","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5007160780","display_name":"Gorka Azkune","orcid":"https://orcid.org/0000-0002-2506-7426"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Azkune, Gorka","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5126079059","display_name":"Jon Imaz","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Imaz, Jon","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5123006086","display_name":"Aizea Lojo","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Lojo, Aizea","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5126118718","display_name":"Javier Fernandez-Marques","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Fernandez-Marques, Javier","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":5,"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":0.7764999866485596,"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":0.7764999866485596,"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/T11980","display_name":"Human Mobility and Location-Based Analysis","score":0.01889999955892563,"subfield":{"id":"https://openalex.org/subfields/3313","display_name":"Transportation"},"field":{"id":"https://openalex.org/fields/33","display_name":"Social Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},{"id":"https://openalex.org/T11704","display_name":"Mobile Crowdsensing and Crowdsourcing","score":0.017999999225139618,"subfield":{"id":"https://openalex.org/subfields/1706","display_name":"Computer Science Applications"},"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/interpretability","display_name":"Interpretability","score":0.7348999977111816},{"id":"https://openalex.org/keywords/federated-learning","display_name":"Federated learning","score":0.6448000073432922},{"id":"https://openalex.org/keywords/inference","display_name":"Inference","score":0.5992000102996826},{"id":"https://openalex.org/keywords/robustness","display_name":"Robustness (evolution)","score":0.5551000237464905},{"id":"https://openalex.org/keywords/sample","display_name":"Sample (material)","score":0.48249998688697815},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.38839998841285706},{"id":"https://openalex.org/keywords/leverage","display_name":"Leverage (statistics)","score":0.3783999979496002},{"id":"https://openalex.org/keywords/encoder","display_name":"Encoder","score":0.320499986410141}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7994999885559082},{"id":"https://openalex.org/C2781067378","wikidata":"https://www.wikidata.org/wiki/Q17027399","display_name":"Interpretability","level":2,"score":0.7348999977111816},{"id":"https://openalex.org/C2992525071","wikidata":"https://www.wikidata.org/wiki/Q50818671","display_name":"Federated learning","level":2,"score":0.6448000073432922},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.5992000102996826},{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.5551000237464905},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.5400999784469604},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5008000135421753},{"id":"https://openalex.org/C198531522","wikidata":"https://www.wikidata.org/wiki/Q485146","display_name":"Sample (material)","level":2,"score":0.48249998688697815},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.4327000081539154},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.38839998841285706},{"id":"https://openalex.org/C153083717","wikidata":"https://www.wikidata.org/wiki/Q6535263","display_name":"Leverage (statistics)","level":2,"score":0.3783999979496002},{"id":"https://openalex.org/C118505674","wikidata":"https://www.wikidata.org/wiki/Q42586063","display_name":"Encoder","level":2,"score":0.320499986410141},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.31279999017715454},{"id":"https://openalex.org/C67186912","wikidata":"https://www.wikidata.org/wiki/Q367664","display_name":"Data modeling","level":2,"score":0.31139999628067017},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.2896000146865845},{"id":"https://openalex.org/C160920958","wikidata":"https://www.wikidata.org/wiki/Q7662746","display_name":"Synthetic data","level":2,"score":0.27219998836517334},{"id":"https://openalex.org/C2780719617","wikidata":"https://www.wikidata.org/wiki/Q1030752","display_name":"Salient","level":2,"score":0.2720000147819519},{"id":"https://openalex.org/C123201435","wikidata":"https://www.wikidata.org/wiki/Q456632","display_name":"Information privacy","level":2,"score":0.2694999873638153},{"id":"https://openalex.org/C48044578","wikidata":"https://www.wikidata.org/wiki/Q727490","display_name":"Scalability","level":2,"score":0.26260000467300415},{"id":"https://openalex.org/C61326573","wikidata":"https://www.wikidata.org/wiki/Q1496376","display_name":"Gaussian process","level":3,"score":0.260699987411499},{"id":"https://openalex.org/C2780513914","wikidata":"https://www.wikidata.org/wiki/Q18210350","display_name":"Bottleneck","level":2,"score":0.258899986743927},{"id":"https://openalex.org/C72634772","wikidata":"https://www.wikidata.org/wiki/Q386824","display_name":"Data integration","level":2,"score":0.2556000053882599},{"id":"https://openalex.org/C136389625","wikidata":"https://www.wikidata.org/wiki/Q334384","display_name":"Supervised learning","level":3,"score":0.2524000108242035},{"id":"https://openalex.org/C2778023277","wikidata":"https://www.wikidata.org/wiki/Q321703","display_name":"Premise","level":2,"score":0.2508000135421753}],"mesh":[],"locations_count":2,"locations":[{"id":"pmh:doi:10.48550/arxiv.2602.12708","is_oa":true,"landing_page_url":null,"pdf_url":null,"source":{"id":"https://openalex.org/S4406922384","display_name":"Open MIND","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":"publisher-specific-oa","license_id":"https://openalex.org/licenses/publisher-specific-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Article"},{"id":"doi:10.48550/arxiv.2602.12708","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2602.12708","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":null,"license_id":null,"version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"article"}],"best_oa_location":{"id":"pmh:doi:10.48550/arxiv.2602.12708","is_oa":true,"landing_page_url":null,"pdf_url":null,"source":{"id":"https://openalex.org/S4406922384","display_name":"Open MIND","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":"publisher-specific-oa","license_id":"https://openalex.org/licenses/publisher-specific-oa","version":"submittedVersion","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":{"Vertical":[0,184],"Federated":[1],"Learning":[2,60],"(VFL)":[3],"has":[4],"emerged":[5],"as":[6,18,181],"a":[7,38,54,62,117],"critical":[8],"paradigm":[9],"for":[10,108],"collaborative":[11],"model":[12],"training":[13,96],"in":[14,43,116,187],"privacy-sensitive":[15],"domains":[16],"such":[17,180],"finance":[19],"and":[20,97,150,167,183],"healthcare.":[21],"However,":[22],"most":[23],"existing":[24,133],"VFL":[25],"frameworks":[26],"rely":[27],"on":[28,164],"the":[29,123],"idealized":[30],"assumption":[31],"of":[32,65,73],"full":[33,101],"sample":[34,102,137],"alignment":[35],"across":[36],"participants,":[37],"premise":[39],"that":[40,57,135,174],"rarely":[41],"holds":[42],"real-world":[44],"scenarios.":[45],"To":[46],"bridge":[47],"this":[48,50,139],"gap,":[49],"work":[51],"introduces":[52],"Split-MoPE,":[53],"novel":[55,140],"framework":[56],"integrates":[58],"Split":[59],"with":[61,190],"specialized":[63],"Mixture":[64,72],"Predefined":[66],"Experts":[67,74],"(MoPE)":[68],"architecture.":[69],"Unlike":[70],"standard":[71],"(MoE),":[75],"where":[76],"routing":[77],"is":[78],"learned":[79],"dynamically,":[80],"MoPE":[81],"uses":[82],"predefined":[83],"experts":[84],"to":[85,127,159],"process":[86],"specific":[87],"data":[88,92,110,192],"alignments,":[89],"effectively":[90],"maximizing":[91],"usage":[93],"during":[94],"both":[95],"inference":[98],"without":[99],"requiring":[100],"overlap.":[103],"By":[104],"leveraging":[105],"pretrained":[106],"encoders":[107],"target":[109],"domains,":[111],"Split-MoPE":[112,175],"achieves":[113],"state-of-the-art":[114,178],"performance":[115],"single":[118],"communication":[119,124],"round,":[120],"significantly":[121],"reducing":[122],"footprint":[125],"compared":[126],"multi-round":[128],"end-to-end":[129],"training.":[130],"Furthermore,":[131],"unlike":[132],"proposals":[134],"address":[136],"misalignment,":[138],"architecture":[141],"provides":[142],"inherent":[143],"robustness":[144],"against":[145],"malicious":[146],"or":[147],"noisy":[148],"participants":[149],"offers":[151],"per-sample":[152],"interpretability":[153],"by":[154],"quantifying":[155],"each":[156,160],"collaborator's":[157],"contribution":[158],"prediction.":[161],"Extensive":[162],"evaluations":[163],"vision":[165],"(CIFAR-10/100)":[166],"tabular":[168],"(Breast":[169],"Cancer":[170],"Wisconsin)":[171],"datasets":[172],"demonstrate":[173],"consistently":[176],"outperforms":[177],"systems":[179],"LASER":[182],"SplitNN,":[185],"particularly":[186],"challenging":[188],"scenarios":[189],"high":[191],"missingness.":[193]},"counts_by_year":[],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2026-02-17T00:00:00"}