{"id":"https://openalex.org/W7161064601","doi":"https://doi.org/10.48550/arxiv.2605.11919","title":"STAGE: Tackling Semantic Drift in Multimodal Federated Graph Learning","display_name":"STAGE: Tackling Semantic Drift in Multimodal Federated Graph Learning","publication_year":2026,"publication_date":"2026-05-12","ids":{"openalex":"https://openalex.org/W7161064601","doi":"https://doi.org/10.48550/arxiv.2605.11919"},"language":null,"primary_location":{"id":"doi:10.48550/arxiv.2605.11919","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2605.11919","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":"Preprint"},"type":"preprint","indexed_in":["datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://doi.org/10.48550/arxiv.2605.11919","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5136079848","display_name":"Zekai Chen","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Chen, Zekai","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5136050459","display_name":"Xun Wu","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Wu, Xun","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5136052556","display_name":"Xunkai Li","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Li, Xunkai","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100300641","display_name":"Yihan Sun","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Sun, Yihan","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5136011897","display_name":"Rong-Hua Li","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Li, Rong-Hua","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5136002181","display_name":"Guoren Wang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Wang, Guoren","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":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/T11273","display_name":"Advanced Graph Neural Networks","score":0.9574999809265137,"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/T11273","display_name":"Advanced Graph Neural Networks","score":0.9574999809265137,"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/T10764","display_name":"Privacy-Preserving Technologies in Data","score":0.011699999682605267,"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/T13702","display_name":"Machine Learning in Healthcare","score":0.007600000128149986,"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/graph","display_name":"Graph","score":0.5778999924659729},{"id":"https://openalex.org/keywords/encoder","display_name":"Encoder","score":0.4059000015258789},{"id":"https://openalex.org/keywords/knowledge-graph","display_name":"Knowledge graph","score":0.36719998717308044},{"id":"https://openalex.org/keywords/feature-learning","display_name":"Feature learning","score":0.3327000141143799},{"id":"https://openalex.org/keywords/semantic-memory","display_name":"Semantic memory","score":0.3296000063419342},{"id":"https://openalex.org/keywords/linked-data","display_name":"Linked data","score":0.3041999936103821},{"id":"https://openalex.org/keywords/modality","display_name":"Modality (human\u2013computer interaction)","score":0.2964000105857849},{"id":"https://openalex.org/keywords/semantic-data-model","display_name":"Semantic data model","score":0.2921000123023987}],"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/C132525143","wikidata":"https://www.wikidata.org/wiki/Q141488","display_name":"Graph","level":2,"score":0.5778999924659729},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.4372999966144562},{"id":"https://openalex.org/C118505674","wikidata":"https://www.wikidata.org/wiki/Q42586063","display_name":"Encoder","level":2,"score":0.4059000015258789},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3815999925136566},{"id":"https://openalex.org/C2987255567","wikidata":"https://www.wikidata.org/wiki/Q33002955","display_name":"Knowledge graph","level":2,"score":0.36719998717308044},{"id":"https://openalex.org/C59404180","wikidata":"https://www.wikidata.org/wiki/Q17013334","display_name":"Feature learning","level":2,"score":0.3327000141143799},{"id":"https://openalex.org/C197914299","wikidata":"https://www.wikidata.org/wiki/Q18650","display_name":"Semantic memory","level":3,"score":0.3296000063419342},{"id":"https://openalex.org/C69075417","wikidata":"https://www.wikidata.org/wiki/Q515701","display_name":"Linked data","level":3,"score":0.3041999936103821},{"id":"https://openalex.org/C2780226545","wikidata":"https://www.wikidata.org/wiki/Q6888030","display_name":"Modality (human\u2013computer interaction)","level":2,"score":0.2964000105857849},{"id":"https://openalex.org/C90312973","wikidata":"https://www.wikidata.org/wiki/Q7449052","display_name":"Semantic data model","level":2,"score":0.2921000123023987},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.2831999957561493},{"id":"https://openalex.org/C176225458","wikidata":"https://www.wikidata.org/wiki/Q595971","display_name":"Graph database","level":3,"score":0.2808000147342682},{"id":"https://openalex.org/C130318100","wikidata":"https://www.wikidata.org/wiki/Q2268914","display_name":"Semantic similarity","level":2,"score":0.2800999879837036},{"id":"https://openalex.org/C146380142","wikidata":"https://www.wikidata.org/wiki/Q1137726","display_name":"Directed graph","level":2,"score":0.26649999618530273},{"id":"https://openalex.org/C197115733","wikidata":"https://www.wikidata.org/wiki/Q1003136","display_name":"Forcing (mathematics)","level":2,"score":0.26420000195503235},{"id":"https://openalex.org/C2129575","wikidata":"https://www.wikidata.org/wiki/Q54837","display_name":"Semantic Web","level":2,"score":0.2639999985694885},{"id":"https://openalex.org/C110893760","wikidata":"https://www.wikidata.org/wiki/Q3115590","display_name":"Named graph","level":5,"score":0.2621000111103058},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.2605000138282776},{"id":"https://openalex.org/C85407183","wikidata":"https://www.wikidata.org/wiki/Q1045785","display_name":"Semantic network","level":2,"score":0.25949999690055847},{"id":"https://openalex.org/C2778572836","wikidata":"https://www.wikidata.org/wiki/Q380933","display_name":"Space (punctuation)","level":2,"score":0.2531999945640564}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.48550/arxiv.2605.11919","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2605.11919","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":"Preprint"}],"best_oa_location":{"id":"doi:10.48550/arxiv.2605.11919","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2605.11919","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":"Preprint"},"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":{"Federated":[0],"graph":[1,8,14,28,99,151,172],"learning":[2,29],"(FGL)":[3],"enables":[4],"collaborative":[5],"training":[6],"on":[7,123,176],"data":[9,15],"across":[10,106,180],"multiple":[11],"clients.":[12],"As":[13],"increasingly":[16],"contain":[17],"multimodal":[18,26,137],"node":[19],"attributes":[20],"such":[21],"as":[22],"text":[23],"and":[24,77,98,142,183],"images,":[25],"federated":[27],"(MM-FGL)":[30],"has":[31],"become":[32],"an":[33],"important":[34],"yet":[35],"substantially":[36],"harder":[37],"setting.":[38],"The":[39],"key":[40],"challenge":[41],"is":[42],"that":[43,133,187],"clients":[44],"from":[45],"different":[46],"modality":[47],"domains":[48],"may":[49,93,102],"not":[50,157],"share":[51],"a":[52,88,115,129],"common":[53],"semantic":[54,91,96,131,161],"space:":[55],"even":[56],"for":[57,118],"the":[58,166],"same":[59],"concept,":[60],"their":[61],"local":[62,150],"encoders":[63],"can":[64],"produce":[65],"inconsistent":[66],"representations":[67,86,141,147],"before":[68],"collaboration":[69],"begins.":[70],"This":[71],"makes":[72],"direct":[73,124],"parameter":[74,125],"coordination":[75],"unreliable":[76],"further":[78],"causes":[79],"two":[80],"downstream":[81],"problems:":[82],"forcing":[83],"heterogeneous":[84,136],"client":[85],"into":[87,139],"naively":[89],"shared":[90,130],"space":[92,132],"create":[94],"false":[95],"agreement,":[97],"message":[100],"passing":[101],"amplify":[103],"residual":[104],"inconsistency":[105,169],"neighborhoods.":[107],"To":[108],"address":[109],"this":[110,154],"issue,":[111],"we":[112],"propose":[113],"\\textbf{STAGE},":[114],"protocol-first":[116],"framework":[117],"MM-FGL.":[119],"Instead":[120],"of":[121,168],"relying":[122],"averaging,":[126],"STAGE":[127,156,188],"builds":[128],"first":[134],"translates":[135],"features":[138],"comparable":[140],"then":[143],"regulates":[144],"how":[145],"these":[146],"propagate":[148],"over":[149],"structures.":[152],"In":[153],"way,":[155],"only":[158],"improves":[159],"cross-client":[160],"calibration,":[162],"but":[163],"also":[164],"reduces":[165],"risk":[167],"amplification":[170],"during":[171],"learning.":[173],"Extensive":[174],"experiments":[175],"8":[177],"multimodal-attributed":[178],"graphs":[179],"5":[181],"graph-centric":[182],"modality-centric":[184],"tasks":[185],"show":[186],"consistently":[189],"achieves":[190],"state-of-the-art":[191],"performance":[192],"while":[193],"reducing":[194],"per-round":[195],"communication":[196],"payload.":[197]},"counts_by_year":[],"updated_date":"2026-07-01T06:00:48.157686","created_date":"2026-05-14T00:00:00"}