{"id":"https://openalex.org/W7169778580","doi":"https://doi.org/10.48550/arxiv.2607.15687","title":"Toward Federated Multimodal Graph Foundation Models: A Topology-Aware Multimodal Alignment Framework","display_name":"Toward Federated Multimodal Graph Foundation Models: A Topology-Aware Multimodal Alignment Framework","publication_year":2026,"publication_date":"2026-07-17","ids":{"openalex":"https://openalex.org/W7169778580","doi":"https://doi.org/10.48550/arxiv.2607.15687"},"language":null,"primary_location":{"id":"doi:10.48550/arxiv.2607.15687","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2607.15687","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":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.2607.15687","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5141220274","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/A5124817066","display_name":"Guohao Fu","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Fu, Guohao","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5115792432","display_name":"Yuming Ai","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Ai, Yuming","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5104036081","display_name":"Z Z Wu","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Wu, Zhengyu","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5059652667","display_name":"Hongchao Qin","orcid":"https://orcid.org/0000-0003-4364-0633"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Qin, Hongchao","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5052597908","display_name":"R K 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/A5141185232","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":0.9648000001907349,"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":0.9648000001907349,"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":0.0052999998442828655,"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/T11307","display_name":"Domain Adaptation and Few-Shot Learning","score":0.004800000227987766,"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":0.5277000069618225},{"id":"https://openalex.org/keywords/encoder","display_name":"Encoder","score":0.4611999988555908},{"id":"https://openalex.org/keywords/feature-learning","display_name":"Feature learning","score":0.44699999690055847},{"id":"https://openalex.org/keywords/exploit","display_name":"Exploit","score":0.44119998812675476},{"id":"https://openalex.org/keywords/knowledge-graph","display_name":"Knowledge graph","score":0.352400004863739},{"id":"https://openalex.org/keywords/dependency-graph","display_name":"Dependency graph","score":0.3215000033378601},{"id":"https://openalex.org/keywords/semantic-heterogeneity","display_name":"Semantic heterogeneity","score":0.31540000438690186}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7955999970436096},{"id":"https://openalex.org/C132525143","wikidata":"https://www.wikidata.org/wiki/Q141488","display_name":"Graph","level":2,"score":0.5277000069618225},{"id":"https://openalex.org/C118505674","wikidata":"https://www.wikidata.org/wiki/Q42586063","display_name":"Encoder","level":2,"score":0.4611999988555908},{"id":"https://openalex.org/C59404180","wikidata":"https://www.wikidata.org/wiki/Q17013334","display_name":"Feature learning","level":2,"score":0.44699999690055847},{"id":"https://openalex.org/C165696696","wikidata":"https://www.wikidata.org/wiki/Q11287","display_name":"Exploit","level":2,"score":0.44119998812675476},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.41190001368522644},{"id":"https://openalex.org/C2987255567","wikidata":"https://www.wikidata.org/wiki/Q33002955","display_name":"Knowledge graph","level":2,"score":0.352400004863739},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.34369999170303345},{"id":"https://openalex.org/C16311509","wikidata":"https://www.wikidata.org/wiki/Q4148050","display_name":"Dependency graph","level":3,"score":0.3215000033378601},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.319599986076355},{"id":"https://openalex.org/C2778180026","wikidata":"https://www.wikidata.org/wiki/Q18378163","display_name":"Semantic heterogeneity","level":4,"score":0.31540000438690186},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.3084999918937683},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.299699991941452},{"id":"https://openalex.org/C2992525071","wikidata":"https://www.wikidata.org/wiki/Q50818671","display_name":"Federated learning","level":2,"score":0.2840000092983246},{"id":"https://openalex.org/C2779903281","wikidata":"https://www.wikidata.org/wiki/Q6888026","display_name":"Modalities","level":2,"score":0.2612999975681305},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.26019999384880066},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.257099986076355},{"id":"https://openalex.org/C64543145","wikidata":"https://www.wikidata.org/wiki/Q162942","display_name":"Intersection (aeronautics)","level":2,"score":0.25369998812675476}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.48550/arxiv.2607.15687","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2607.15687","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":"doi:10.48550/arxiv.2607.15687","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2607.15687","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":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":{"Multimodal-attributed":[0],"graphs":[1,35,145],"(MAGs),":[2],"whose":[3],"nodes":[4],"carry":[5],"modalities":[6],"such":[7,34],"as":[8,103],"images":[9],"and":[10,22,45,74,112,139,146,150,161,186],"text":[11],"alongside":[12],"topological":[13],"structure,":[14],"now":[15],"pervade":[16],"applications":[17],"including":[18],"social":[19],"platforms,":[20],"e-commerce,":[21],"biomedical":[23],"networks,":[24],"offering":[25],"richer":[26],"semantic":[27,119,138,143],"signals":[28],"than":[29],"single-modality":[30],"graphs.":[31],"In":[32],"practice,":[33],"are":[36],"fragmented":[37],"across":[38,205],"privacy-restricted":[39],"silos":[40],"owned":[41],"by":[42],"different":[43],"platforms":[44],"institutions,":[46],"so":[47],"learning":[48,73,102,231],"a":[49,104,117,132,151,179,200],"broadly":[50],"transferable":[51],"model":[52],"over":[53],"them":[54],"demands":[55],"collaborative":[56],"training":[57],"that":[58],"never":[59],"exposes":[60],"raw":[61,166],"data.":[62,167],"This":[63],"places":[64],"the":[65,68,88,172],"task":[66],"at":[67],"intersection":[69],"of":[70,84,109,203,210],"multimodal":[71,99,193],"graph":[72,100,134,162,194],"federated":[75,98,110],"learning,":[76],"yet":[77],"existing":[78],"methods":[79],"cover":[80],"only":[81],"one":[82],"side":[83],"it.":[85],"To":[86],"address":[87],"challenges":[89],"from":[90,124,159],"these":[91],"two":[92],"perspectives,":[93],"we":[94],"propose":[95],"FedGAMMA,":[96],"casting":[97],"foundation":[101],"two-stage":[105],"semantic-structural":[106],"alignment":[107],"problem":[108],"pre-training":[111],"prompt-based":[113],"fine-tuning.":[114],"During":[115,168],"pre-training,":[116],"shared-private":[118],"enhancer":[120],"disentangles":[121],"cross-modal":[122],"commonality":[123],"modality-specific":[125],"information,":[126],"aligning":[127],"it":[128],"through":[129,175],"optimal":[130],"transport,":[131],"topology-aware":[133],"fusion":[135],"module":[136],"decouples":[137],"structural":[140],"views":[141],"via":[142],"residual":[144],"dual":[147],"positional":[148],"encodings,":[149],"dual-channel":[152],"affinity-aware":[153],"aggregation":[154],"mechanism":[155],"estimates":[156],"client":[157],"similarity":[158],"feature":[160],"centroids":[163],"without":[164],"exposing":[165],"fine-tuning,":[169],"FedGAMMA":[170,197,214],"adapts":[171],"pretrained":[173],"encoder":[174],"lightweight":[176],"graph-aware":[177],"prompts,":[178],"shared":[180],"prompt":[181,188],"pool":[182],"with":[183,208,225],"controlled":[184],"exploration,":[185],"channel-wise":[187],"synchronization.":[189],"Experiments":[190],"on":[191,222],"twelve":[192],"datasets":[195,221],"show":[196],"consistently":[198],"surpassing":[199],"broad":[201],"range":[202],"baselines":[204,218],"downstream":[206],"tasks,":[207],"gains":[209],"up":[211,226],"to":[212,227],"12.96%.":[213],"further":[215],"outperforms":[216],"competitive":[217],"accross":[219],"multi-domain":[220],"multiple":[223],"tasks":[224],"5.71%":[228],"under":[229],"few-shot":[230],"scenario.":[232]},"counts_by_year":[],"updated_date":"2026-07-28T07:46:37.118299","created_date":"2026-07-21T00:00:00"}