{"id":"https://openalex.org/W7126195750","doi":"https://doi.org/10.48550/arxiv.2601.21369","title":"Rethinking Federated Graph Foundation Models: A Graph-Language Alignment-based Approach","display_name":"Rethinking Federated Graph Foundation Models: A Graph-Language Alignment-based Approach","publication_year":2026,"publication_date":"2026-01-29","ids":{"openalex":"https://openalex.org/W7126195750","doi":"https://doi.org/10.48550/arxiv.2601.21369"},"language":null,"primary_location":{"id":"pmh:doi:10.48550/arxiv.2601.21369","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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","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":null,"display_name":"Zhu, Yinlin","orcid":null},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Zhu, Yinlin","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5124453864","display_name":"Di Wu","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Wu, Di","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5124387210","display_name":"Xianzhi Zhang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zhang, Xianzhi","raw_affiliation_strings":[],"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":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5113402587","display_name":"Xunkai Li","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Li, Xunkai","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5124413106","display_name":"Miao Hu","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Hu, Miao","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5124385671","display_name":"Guocong Quan","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Quan, Guocong","raw_affiliation_strings":[],"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":7,"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":0.9650999903678894,"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":0.9650999903678894,"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":0.0044999998062849045,"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/T10028","display_name":"Topic Modeling","score":0.004000000189989805,"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":0.5063999891281128},{"id":"https://openalex.org/keywords/embedding","display_name":"Embedding","score":0.4239000082015991},{"id":"https://openalex.org/keywords/orthogonality","display_name":"Orthogonality","score":0.41780000925064087},{"id":"https://openalex.org/keywords/knowledge-graph","display_name":"Knowledge graph","score":0.3928999900817871},{"id":"https://openalex.org/keywords/security-token","display_name":"Security token","score":0.38040000200271606},{"id":"https://openalex.org/keywords/federated-learning","display_name":"Federated learning","score":0.32899999618530273},{"id":"https://openalex.org/keywords/overhead","display_name":"Overhead (engineering)","score":0.32749998569488525},{"id":"https://openalex.org/keywords/tuple","display_name":"Tuple","score":0.3010999858379364},{"id":"https://openalex.org/keywords/encoder","display_name":"Encoder","score":0.2953000068664551}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8111000061035156},{"id":"https://openalex.org/C132525143","wikidata":"https://www.wikidata.org/wiki/Q141488","display_name":"Graph","level":2,"score":0.5063999891281128},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.4578000009059906},{"id":"https://openalex.org/C41608201","wikidata":"https://www.wikidata.org/wiki/Q980509","display_name":"Embedding","level":2,"score":0.4239000082015991},{"id":"https://openalex.org/C17137986","wikidata":"https://www.wikidata.org/wiki/Q215067","display_name":"Orthogonality","level":2,"score":0.41780000925064087},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.39820000529289246},{"id":"https://openalex.org/C2987255567","wikidata":"https://www.wikidata.org/wiki/Q33002955","display_name":"Knowledge graph","level":2,"score":0.3928999900817871},{"id":"https://openalex.org/C48145219","wikidata":"https://www.wikidata.org/wiki/Q1335365","display_name":"Security token","level":2,"score":0.38040000200271606},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.36570000648498535},{"id":"https://openalex.org/C120314980","wikidata":"https://www.wikidata.org/wiki/Q180634","display_name":"Distributed computing","level":1,"score":0.3393999934196472},{"id":"https://openalex.org/C2992525071","wikidata":"https://www.wikidata.org/wiki/Q50818671","display_name":"Federated learning","level":2,"score":0.32899999618530273},{"id":"https://openalex.org/C2779960059","wikidata":"https://www.wikidata.org/wiki/Q7113681","display_name":"Overhead (engineering)","level":2,"score":0.32749998569488525},{"id":"https://openalex.org/C118930307","wikidata":"https://www.wikidata.org/wiki/Q600590","display_name":"Tuple","level":2,"score":0.3010999858379364},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.2955000102519989},{"id":"https://openalex.org/C118505674","wikidata":"https://www.wikidata.org/wiki/Q42586063","display_name":"Encoder","level":2,"score":0.2953000068664551},{"id":"https://openalex.org/C178005623","wikidata":"https://www.wikidata.org/wiki/Q308859","display_name":"Anonymity","level":2,"score":0.29269999265670776},{"id":"https://openalex.org/C33762810","wikidata":"https://www.wikidata.org/wiki/Q461671","display_name":"Data integrity","level":2,"score":0.29120001196861267},{"id":"https://openalex.org/C28855332","wikidata":"https://www.wikidata.org/wiki/Q198099","display_name":"Quantization (signal processing)","level":2,"score":0.2870999872684479},{"id":"https://openalex.org/C75564084","wikidata":"https://www.wikidata.org/wiki/Q5597085","display_name":"Graph embedding","level":3,"score":0.28459998965263367},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.2842000126838684},{"id":"https://openalex.org/C67186912","wikidata":"https://www.wikidata.org/wiki/Q367664","display_name":"Data modeling","level":2,"score":0.2791999876499176},{"id":"https://openalex.org/C77618280","wikidata":"https://www.wikidata.org/wiki/Q1155772","display_name":"Scheme (mathematics)","level":2,"score":0.2720000147819519},{"id":"https://openalex.org/C88230418","wikidata":"https://www.wikidata.org/wiki/Q131476","display_name":"Graph theory","level":2,"score":0.2687999904155731},{"id":"https://openalex.org/C165696696","wikidata":"https://www.wikidata.org/wiki/Q11287","display_name":"Exploit","level":2,"score":0.26460000872612},{"id":"https://openalex.org/C146380142","wikidata":"https://www.wikidata.org/wiki/Q1137726","display_name":"Directed graph","level":2,"score":0.2581999897956848},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.25589999556541443},{"id":"https://openalex.org/C139807058","wikidata":"https://www.wikidata.org/wiki/Q352374","display_name":"Adaptation (eye)","level":2,"score":0.2554999887943268},{"id":"https://openalex.org/C23130292","wikidata":"https://www.wikidata.org/wiki/Q5275358","display_name":"Differential privacy","level":2,"score":0.2538999915122986},{"id":"https://openalex.org/C2779582901","wikidata":"https://www.wikidata.org/wiki/Q21013010","display_name":"Distributed learning","level":2,"score":0.25119999051094055}],"mesh":[],"locations_count":2,"locations":[{"id":"pmh:doi:10.48550/arxiv.2601.21369","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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Article"},{"id":"doi:10.48550/arxiv.2601.21369","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2601.21369","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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"article"}],"best_oa_location":{"id":"pmh:doi:10.48550/arxiv.2601.21369","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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","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":{"Recent":[0],"studies":[1,39],"of":[2,14,28,179],"federated":[3,127],"graph":[4,21,80],"foundational":[5],"models":[6,77],"(FedGFMs)":[7],"break":[8],"the":[9,26,59,69,93,176],"idealized":[10],"and":[11,24,36,72,79,97,124,137,164],"untenable":[12],"assumption":[13],"having":[15],"centralized":[16],"data":[17,31,95],"storage":[18],"to":[19,134,159,170,200],"train":[20],"foundation":[22],"models,":[23],"accommodate":[25],"reality":[27],"distributed,":[29,102],"privacy-restricted":[30],"silos.":[32],"Despite":[33],"their":[34],"simplicity":[35],"intuition,":[37],"existing":[38],"that":[40,67,119,186],"project":[41],"aligned":[42],"generalizable":[43],"knowledge":[44,56],"onto":[45],"a":[46,117,141,154],"discrete":[47],"token":[48],"space":[49],"via":[50],"vector-quantized":[51],"backbones":[52],"suffer":[53],"from":[54],"irreversible":[55],"loss":[57],"during":[58],"quantization":[60],"process.":[61],"In":[62],"this":[63],"context,":[64],"we":[65,109],"argue":[66],"reconciling":[68],"semantic-structural":[70,122],"orthogonality":[71,123],"integrity":[73,125],"between":[74],"pre-trained":[75],"language":[76],"(PLMs)":[78],"neural":[81],"networks":[82],"(GNNs)":[83],"is":[84],"paramount":[85],"for":[86],"developing":[87],"effective":[88,168],"FedGFMs":[89],"while":[90,174],"simultaneously":[91],"mitigating":[92],"severe":[94],"heterogeneity":[96],"communication":[98],"constraints":[99],"inherent":[100],"in":[101,126],"resource-limited":[103],"environments.":[104],"To":[105],"address":[106],"these":[107,161],"issues,":[108],"propose":[110],"FedGALA":[111,152,187],"(Federated":[112],"Graph":[113],"And":[114],"Language":[115],"Alignment),":[116],"framework":[118],"resolves":[120],"graph-based":[121],"settings":[128],"by":[129],"employing":[130],"unsupervised":[131],"contrastive":[132],"learning":[133],"align":[135],"GNNs":[136],"frozen":[138,165],"PLMs":[139],"within":[140],"continuous":[142],"embedding":[143],"space,":[144],"thereby":[145],"capturing":[146],"robust,":[147],"transferable":[148],"general":[149],"knowledge.":[150],"Subsequently,":[151],"leverages":[153],"communication-efficient":[155],"prompt":[156],"tuning":[157],"mechanism":[158],"steer":[160],"pre-aligned":[162],"encoders":[163],"PLMs,":[166],"facilitating":[167],"adaptation":[169],"diverse":[171],"downstream":[172],"tasks":[173,197],"circumventing":[175],"prohibitive":[177],"overhead":[178],"full-parameter":[180],"fine-tuning.":[181],"The":[182],"comprehensive":[183],"experiments":[184],"validate":[185],"outperforms":[188],"all":[189],"competitive":[190],"baselines":[191],"across":[192],"multi-domain":[193],"datasets":[194],"on":[195],"multiple":[196],"with":[198],"up":[199],"14.37%":[201],"performance":[202],"improvement.":[203]},"counts_by_year":[],"updated_date":"2026-04-04T16:13:02.066488","created_date":"2026-02-01T00:00:00"}