{"id":"https://openalex.org/W7162649744","doi":"https://doi.org/10.48550/arxiv.2605.28347","title":"FedMPT: Federated Multi-label Prompt Tuning of Vision-Language Models","display_name":"FedMPT: Federated Multi-label Prompt Tuning of Vision-Language Models","publication_year":2026,"publication_date":"2026-05-27","ids":{"openalex":"https://openalex.org/W7162649744","doi":"https://doi.org/10.48550/arxiv.2605.28347"},"language":null,"primary_location":{"id":"doi:10.48550/arxiv.2605.28347","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2605.28347","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":false,"raw_source_name":null,"raw_type":"article"},"type":"preprint","indexed_in":["datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://doi.org/10.48550/arxiv.2605.28347","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5001240232","display_name":"X.S. Wang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Wang, Xucong","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5137286213","display_name":"Pengkun Wang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Wang, Pengkun","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5137269965","display_name":"Zhe Zhao","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zhao, Zhe","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5137282257","display_name":"Liheng Yu","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yu, Liheng","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5137259919","display_name":"Shuang Wang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Wang, Shuang","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5137296145","display_name":"Yang Wang","orcid":"https://orcid.org/0009-0006-6828-7185"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Wang, Yang","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":6,"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/T11307","display_name":"Domain Adaptation and Few-Shot Learning","score":0.43860000371932983,"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/T11307","display_name":"Domain Adaptation and Few-Shot Learning","score":0.43860000371932983,"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/T11550","display_name":"Text and Document Classification Technologies","score":0.23559999465942383,"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":0.0478999987244606,"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/leverage","display_name":"Leverage (statistics)","score":0.7742000222206116},{"id":"https://openalex.org/keywords/overfitting","display_name":"Overfitting","score":0.7221999764442444},{"id":"https://openalex.org/keywords/spurious-relationship","display_name":"Spurious relationship","score":0.6732000112533569},{"id":"https://openalex.org/keywords/decipher","display_name":"DECIPHER","score":0.6043000221252441},{"id":"https://openalex.org/keywords/oracle","display_name":"Oracle","score":0.517799973487854},{"id":"https://openalex.org/keywords/pipeline","display_name":"Pipeline (software)","score":0.508899986743927},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.48159998655319214},{"id":"https://openalex.org/keywords/key","display_name":"Key (lock)","score":0.3880000114440918}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7900000214576721},{"id":"https://openalex.org/C153083717","wikidata":"https://www.wikidata.org/wiki/Q6535263","display_name":"Leverage (statistics)","level":2,"score":0.7742000222206116},{"id":"https://openalex.org/C22019652","wikidata":"https://www.wikidata.org/wiki/Q331309","display_name":"Overfitting","level":3,"score":0.7221999764442444},{"id":"https://openalex.org/C97256817","wikidata":"https://www.wikidata.org/wiki/Q1462316","display_name":"Spurious relationship","level":2,"score":0.6732000112533569},{"id":"https://openalex.org/C164614171","wikidata":"https://www.wikidata.org/wiki/Q5204775","display_name":"DECIPHER","level":2,"score":0.6043000221252441},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5401999950408936},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.5199000239372253},{"id":"https://openalex.org/C55166926","wikidata":"https://www.wikidata.org/wiki/Q2892946","display_name":"Oracle","level":2,"score":0.517799973487854},{"id":"https://openalex.org/C43521106","wikidata":"https://www.wikidata.org/wiki/Q2165493","display_name":"Pipeline (software)","level":2,"score":0.508899986743927},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.48159998655319214},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.3880000114440918},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.38659998774528503},{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.3831000030040741},{"id":"https://openalex.org/C67186912","wikidata":"https://www.wikidata.org/wiki/Q367664","display_name":"Data modeling","level":2,"score":0.35690000653266907},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.3418999910354614},{"id":"https://openalex.org/C46686674","wikidata":"https://www.wikidata.org/wiki/Q466303","display_name":"Boosting (machine learning)","level":2,"score":0.3172000050544739},{"id":"https://openalex.org/C2776145971","wikidata":"https://www.wikidata.org/wiki/Q30673951","display_name":"Labeled data","level":2,"score":0.31690001487731934},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.30709999799728394},{"id":"https://openalex.org/C2164484","wikidata":"https://www.wikidata.org/wiki/Q5170150","display_name":"Core (optical fiber)","level":2,"score":0.2939000129699707},{"id":"https://openalex.org/C136389625","wikidata":"https://www.wikidata.org/wiki/Q334384","display_name":"Supervised learning","level":3,"score":0.27140000462532043},{"id":"https://openalex.org/C36503486","wikidata":"https://www.wikidata.org/wiki/Q11235244","display_name":"Domain (mathematical analysis)","level":2,"score":0.25049999356269836}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.48550/arxiv.2605.28347","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2605.28347","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":"doi:10.48550/arxiv.2605.28347","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2605.28347","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":false,"raw_source_name":null,"raw_type":"article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Multi-Label":[0],"Recognition":[1],"(MLR)":[2],"based":[3],"on":[4,185],"Vision-Language":[5],"Models":[6],"(VLMs)":[7],"aims":[8],"to":[9,14,34,47,119,123,127,143,166],"leverage":[10,120],"their":[11],"pre-trained":[12],"knowledge":[13],"better":[15],"adapt":[16],"complex":[17],"recognition":[18],"scenarios,":[19],"thereby":[20],"enhancing":[21],"model":[22,46],"robustness.":[23],"However,":[24],"for":[25,69,110],"realistic":[26],"decentralized":[27],"applications":[28],"requiring":[29],"federated":[30,67,111,125],"learning,":[31],"adapting":[32],"VLMs":[33],"each":[35],"client":[36],"that":[37,91,148,190],"possesses":[38],"private":[39],"and":[40,82,162,197],"heterogeneous":[41],"data":[42],"can":[43],"cause":[44],"the":[45,66,84,93,105,145,159,163],"overfit":[48],"spurious":[49],"label":[50,95,130,150],"correlations,":[51],"consequently":[52],"triggering":[53],"irrelevant":[54],"categories":[55],"when":[56],"encountering":[57],"new":[58],"samples.":[59],"To":[60,132],"tackle":[61],"this":[62],"problem,":[63],"we":[64,77,101,153,172],"reconsider":[65],"learning":[68],"MLR":[70,85,126],"with":[71,179],"a":[72,79,180],"causal":[73],"model,":[74],"in":[75],"which":[76],"adopt":[78],"front-door":[80],"adjustment":[81],"decouple":[83],"modeling":[86],"process":[87],"by":[88,98],"intermediate":[89],"variables":[90],"magnify":[92],"oracle":[94],"co-occurrence.":[96],"Guided":[97],"our":[99,103,191],"analysis,":[100],"propose":[102],"FedMPT,":[104],"first":[106],"method":[107],"specifically":[108],"designed":[109],"MLR.":[112],"The":[113],"core":[114],"idea":[115],"of":[116],"FedMPT":[117,135],"is":[118],"generalizable":[121],"conditions":[122,147,178],"steer":[124],"mitigate":[128],"erroneous":[129],"activations.":[131],"achieve":[133],"this,":[134],"introduces":[136],"an":[137,155],"Large":[138],"Language":[139],"Model":[140],"(LLM)-driven":[141],"pipeline":[142],"decipher":[144],"underlying":[146],"govern":[149],"dependencies.":[151],"Furthermore,":[152],"introduce":[154],"optimal":[156],"transport":[157],"between":[158],"condition-enriched":[160],"prompts":[161],"image":[164],"patches":[165],"uncover":[167],"multiple":[168,186],"region-level":[169],"semantics.":[170],"Finally,":[171],"generate":[173],"synergistic":[174],"predictions":[175],"from":[176],"different":[177],"crafted":[181],"gating":[182],"mechanism.":[183],"Experiments":[184],"benchmark":[187],"datasets":[188],"show":[189],"proposed":[192],"approach":[193],"achieves":[194],"competitive":[195],"results":[196],"outperforms":[198],"SOTA":[199],"methods":[200],"under":[201],"varied":[202],"settings.":[203]},"counts_by_year":[],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2026-05-29T00:00:00"}