{"id":"https://openalex.org/W4411631856","doi":"https://doi.org/10.1145/3731715.3733441","title":"Taming Vision-Language Models for Federated Foundation Models on Heterogeneous Medical Imaging Modalities","display_name":"Taming Vision-Language Models for Federated Foundation Models on Heterogeneous Medical Imaging Modalities","publication_year":2025,"publication_date":"2025-06-25","ids":{"openalex":"https://openalex.org/W4411631856","doi":"https://doi.org/10.1145/3731715.3733441"},"language":"en","primary_location":{"id":"doi:10.1145/3731715.3733441","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3731715.3733441","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2025 International Conference on Multimedia Retrieval","raw_type":"proceedings-article"},"type":"conference-paper","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/A5065161662","display_name":"Lulu Feng","orcid":null},"institutions":[{"id":"https://openalex.org/I149594827","display_name":"Xidian University","ror":"https://ror.org/05s92vm98","country_code":"CN","type":"education","lineage":["https://openalex.org/I149594827"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Lulu Feng","raw_affiliation_strings":["School of Computer Science and Technology, Xidian University, Xi'an, Shaanxi, China"],"raw_orcid":"https://orcid.org/0009-0003-5035-1626","affiliations":[{"raw_affiliation_string":"School of Computer Science and Technology, Xidian University, Xi'an, Shaanxi, China","institution_ids":["https://openalex.org/I149594827"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5072469364","display_name":"Shengchao Chen","orcid":"https://orcid.org/0000-0001-9992-2264"},"institutions":[{"id":"https://openalex.org/I114017466","display_name":"University of Technology Sydney","ror":"https://ror.org/03f0f6041","country_code":"AU","type":"education","lineage":["https://openalex.org/I114017466"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Shengchao Chen","raw_affiliation_strings":["Australian Artificial Intelligence Institute, University of Technology Sydney, Sydney, nsw, Australia"],"raw_orcid":"https://orcid.org/0000-0001-9992-2264","affiliations":[{"raw_affiliation_string":"Australian Artificial Intelligence Institute, University of Technology Sydney, Sydney, nsw, Australia","institution_ids":["https://openalex.org/I114017466"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":4,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"303","last_page":"311"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11986","display_name":"Scientific Computing and Data Management","score":0.9854999780654907,"subfield":{"id":"https://openalex.org/subfields/1802","display_name":"Information Systems and Management"},"field":{"id":"https://openalex.org/fields/18","display_name":"Decision Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},"topics":[{"id":"https://openalex.org/T11986","display_name":"Scientific Computing and Data Management","score":0.9854999780654907,"subfield":{"id":"https://openalex.org/subfields/1802","display_name":"Information Systems and Management"},"field":{"id":"https://openalex.org/fields/18","display_name":"Decision Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},{"id":"https://openalex.org/T10036","display_name":"Advanced Neural Network Applications","score":0.9764999747276306,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"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/T12702","display_name":"Brain Tumor Detection and Classification","score":0.9678999781608582,"subfield":{"id":"https://openalex.org/subfields/2808","display_name":"Neurology"},"field":{"id":"https://openalex.org/fields/28","display_name":"Neuroscience"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/modalities","display_name":"Modalities","score":0.7256548404693604},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7220039367675781},{"id":"https://openalex.org/keywords/foundation","display_name":"Foundation (evidence)","score":0.7036675810813904},{"id":"https://openalex.org/keywords/medical-imaging","display_name":"Medical imaging","score":0.5370299816131592},{"id":"https://openalex.org/keywords/human\u2013computer-interaction","display_name":"Human\u2013computer interaction","score":0.39760100841522217},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3706095218658447},{"id":"https://openalex.org/keywords/data-science","display_name":"Data science","score":0.35489100217819214}],"concepts":[{"id":"https://openalex.org/C2779903281","wikidata":"https://www.wikidata.org/wiki/Q6888026","display_name":"Modalities","level":2,"score":0.7256548404693604},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7220039367675781},{"id":"https://openalex.org/C2780966255","wikidata":"https://www.wikidata.org/wiki/Q5474306","display_name":"Foundation (evidence)","level":2,"score":0.7036675810813904},{"id":"https://openalex.org/C31601959","wikidata":"https://www.wikidata.org/wiki/Q931309","display_name":"Medical imaging","level":2,"score":0.5370299816131592},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.39760100841522217},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3706095218658447},{"id":"https://openalex.org/C2522767166","wikidata":"https://www.wikidata.org/wiki/Q2374463","display_name":"Data science","level":1,"score":0.35489100217819214},{"id":"https://openalex.org/C36289849","wikidata":"https://www.wikidata.org/wiki/Q34749","display_name":"Social science","level":1,"score":0.0},{"id":"https://openalex.org/C166957645","wikidata":"https://www.wikidata.org/wiki/Q23498","display_name":"Archaeology","level":1,"score":0.0},{"id":"https://openalex.org/C144024400","wikidata":"https://www.wikidata.org/wiki/Q21201","display_name":"Sociology","level":0,"score":0.0},{"id":"https://openalex.org/C95457728","wikidata":"https://www.wikidata.org/wiki/Q309","display_name":"History","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3731715.3733441","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3731715.3733441","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2025 International Conference on Multimedia Retrieval","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":31,"referenced_works":["https://openalex.org/W2108598243","https://openalex.org/W2804649465","https://openalex.org/W3038022836","https://openalex.org/W3198377975","https://openalex.org/W4312310776","https://openalex.org/W4317436377","https://openalex.org/W4321483961","https://openalex.org/W4367046615","https://openalex.org/W4385627126","https://openalex.org/W4385764384","https://openalex.org/W4385767379","https://openalex.org/W4386065763","https://openalex.org/W4386071547","https://openalex.org/W4390872376","https://openalex.org/W4390874269","https://openalex.org/W4390874575","https://openalex.org/W4393160079","https://openalex.org/W4393386071","https://openalex.org/W4394593022","https://openalex.org/W4396571157","https://openalex.org/W4396982288","https://openalex.org/W4399316998","https://openalex.org/W4401024639","https://openalex.org/W4401024811","https://openalex.org/W4403813223","https://openalex.org/W4404658388","https://openalex.org/W4409347139","https://openalex.org/W6600553734","https://openalex.org/W6600704668","https://openalex.org/W6759238902","https://openalex.org/W6824583106"],"related_works":["https://openalex.org/W2185469136","https://openalex.org/W2381393187","https://openalex.org/W2332779545","https://openalex.org/W2199184806","https://openalex.org/W127837312","https://openalex.org/W2922283411","https://openalex.org/W4384789578","https://openalex.org/W4387421317","https://openalex.org/W4379801084","https://openalex.org/W1512386104"],"abstract_inverted_index":{"Training":[0],"federated":[1,49],"foundation":[2],"models":[3],"(FFMs)":[4],"for":[5,57],"sensitive":[6],"medical":[7,61,66,74,141],"images":[8],"presents":[9],"open":[10],"challenges":[11],"due":[12],"to":[13,35,81,111,114],"complex":[14],"data":[15],"heterogeneity.":[16],"Related":[17],"studies":[18],"focus":[19],"on":[20,139],"the":[21,32,72,115,145],"problem":[22],"within":[23],"a":[24,48,127],"single":[25],"imaging":[26,42,67,96],"modality;":[27],"however,":[28],"these":[29],"methods":[30],"lacks":[31],"flexibility":[33],"required":[34],"generalize":[36],"related":[37],"tasks":[38],"uniformly":[39],"across":[40,64,99,133],"different":[41],"modalities.":[43,68],"This":[44],"paper":[45],"proposes":[46],"FFMed,":[47],"learning":[50,93],"framework":[51],"that":[52,130],"tames":[53],"pretrained":[54],"Vision-Language":[55],"Models":[56],"FFMs":[58],"training,":[59],"targeting":[60],"image":[62,142],"classification":[63],"heterogeneous":[65],"Specifically,":[69],"FFMed":[70,125],"improves":[71],"CLIP's":[73],"image-text":[75],"alignment":[76],"through":[77],"Adaptive":[78],"Prompt":[79],"Generation":[80],"introduce":[82],"task/domain-specific,":[83],"informative":[84],"prompts":[85],"in":[86],"conjunction":[87],"with":[88],"low-rank":[89],"adaption.":[90],"To":[91],"mitigate":[92],"bias":[94],"from":[95],"modalities":[97],"heterogeneity":[98],"clients,":[100],"we":[101],"propose":[102],"Anchor-based":[103],"Dynamic":[104],"Regularization,":[105],"which":[106],"dynamically":[107],"constrains":[108],"local":[109],"optimization":[110],"remain":[112],"close":[113],"global":[116,122],"stationary":[117],"point,":[118],"thereby":[119],"promoting":[120],"optimal":[121],"consensus.":[123],"Ultimately,":[124],"fosters":[126],"unified":[128],"model":[129],"effectively":[131],"generalizes":[132],"diverse":[134],"non-IID":[135],"environments.":[136],"Extensive":[137],"experiment":[138],"real-world":[140],"datasets":[143],"demonstrate":[144],"effectiveness":[146],"and":[147],"superiority":[148],"of":[149],"FFMed.":[150]},"counts_by_year":[{"year":2026,"cited_by_count":3},{"year":2025,"cited_by_count":1}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}