{"id":"https://openalex.org/W7161252855","doi":"https://doi.org/10.48550/arxiv.2605.14907","title":"KGPFN: Unlocking the Potential of Knowledge Graph Foundation Model via In-Context Learning","display_name":"KGPFN: Unlocking the Potential of Knowledge Graph Foundation Model via In-Context Learning","publication_year":2026,"publication_date":"2026-05-14","ids":{"openalex":"https://openalex.org/W7161252855","doi":"https://doi.org/10.48550/arxiv.2605.14907"},"language":null,"primary_location":{"id":"doi:10.48550/arxiv.2605.14907","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2605.14907","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":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.2605.14907","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5136192637","display_name":"Yisen Gao","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Gao, Yisen","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5136195960","display_name":"Jiaxin Bai","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Bai, Jiaxin","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5136267655","display_name":"Haoyu Huang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Huang, Haoyu","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5136216365","display_name":"Zhongwei Xie","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Xie, Zhongwei","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5136251443","display_name":"Yufei Li","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Li, Yufei","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5133804776","display_name":"Hong Ting Tsang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Tsang, Hong Ting","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5136273201","display_name":"Sirui Han","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Han, Sirui","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5136256563","display_name":"Yangqiu Song","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Song, Yangqiu","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":0.9850000143051147,"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":0.9850000143051147,"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":0.005499999970197678,"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/T11719","display_name":"Data Quality and Management","score":0.00139999995008111,"subfield":{"id":"https://openalex.org/subfields/1803","display_name":"Management Science and Operations Research"},"field":{"id":"https://openalex.org/fields/18","display_name":"Decision Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/relation","display_name":"Relation (database)","score":0.6863999962806702},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.554099977016449},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.5149000287055969},{"id":"https://openalex.org/keywords/foundation","display_name":"Foundation (evidence)","score":0.49810001254081726},{"id":"https://openalex.org/keywords/statistical-relational-learning","display_name":"Statistical relational learning","score":0.492000013589859},{"id":"https://openalex.org/keywords/graph","display_name":"Graph","score":0.45410001277923584},{"id":"https://openalex.org/keywords/adaptation","display_name":"Adaptation (eye)","score":0.4345000088214874}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7026000022888184},{"id":"https://openalex.org/C25343380","wikidata":"https://www.wikidata.org/wiki/Q277521","display_name":"Relation (database)","level":2,"score":0.6863999962806702},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.554099977016449},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.5149000287055969},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4993000030517578},{"id":"https://openalex.org/C2780966255","wikidata":"https://www.wikidata.org/wiki/Q5474306","display_name":"Foundation (evidence)","level":2,"score":0.49810001254081726},{"id":"https://openalex.org/C177877439","wikidata":"https://www.wikidata.org/wiki/Q7604413","display_name":"Statistical relational learning","level":3,"score":0.492000013589859},{"id":"https://openalex.org/C132525143","wikidata":"https://www.wikidata.org/wiki/Q141488","display_name":"Graph","level":2,"score":0.45410001277923584},{"id":"https://openalex.org/C139807058","wikidata":"https://www.wikidata.org/wiki/Q352374","display_name":"Adaptation (eye)","level":2,"score":0.4345000088214874},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.38440001010894775},{"id":"https://openalex.org/C183322885","wikidata":"https://www.wikidata.org/wiki/Q17007702","display_name":"Context model","level":3,"score":0.3813000023365021},{"id":"https://openalex.org/C2987255567","wikidata":"https://www.wikidata.org/wiki/Q33002955","display_name":"Knowledge graph","level":2,"score":0.36059999465942383},{"id":"https://openalex.org/C5655090","wikidata":"https://www.wikidata.org/wiki/Q192588","display_name":"Relational database","level":2,"score":0.3515999913215637},{"id":"https://openalex.org/C40207289","wikidata":"https://www.wikidata.org/wiki/Q755662","display_name":"Relational model","level":3,"score":0.31040000915527344},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.2865000069141388},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.2854999899864197},{"id":"https://openalex.org/C2776760102","wikidata":"https://www.wikidata.org/wiki/Q5139990","display_name":"Code (set theory)","level":3,"score":0.28200000524520874},{"id":"https://openalex.org/C105289051","wikidata":"https://www.wikidata.org/wiki/Q1930094","display_name":"Pillar","level":2,"score":0.250900000333786}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.48550/arxiv.2605.14907","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2605.14907","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":"Preprint"}],"best_oa_location":{"id":"doi:10.48550/arxiv.2605.14907","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2605.14907","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":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":{"Knowledge":[0],"graph":[1],"(KG)":[2],"foundation":[3,35,82,217],"models":[4,36],"aim":[5],"to":[6,111,181,187,204],"generalize":[7],"across":[8,74],"graphs":[9,110,207],"with":[10,93,153],"unseen":[11,206],"entities":[12,61],"and":[13,48,157,169,185],"relations":[14],"by":[15,141],"learning":[16,96,210],"transferable":[17,90],"relational":[18,91,114],"structure.":[19],"However,":[20],"most":[21],"existing":[22],"methods":[23],"primarily":[24],"emphasize":[25],"relation-level":[26],"universality,":[27],"while":[28],"in-context":[29,95,209],"learning,":[30],"the":[31,55,59,65,149],"other":[32],"pillar":[33],"of":[34,146,148],"remains":[37],"under-explored":[38],"for":[39],"KG":[40,81,196,216],"reasoning.":[41],"In":[42],"KGs,":[43,177],"context":[44,57,67,140],"is":[45,221],"inherently":[46],"structured":[47,98],"heterogeneous:":[49],"effective":[50],"prediction":[51],"requires":[52],"conditioning":[53],"on":[54,108,175,194],"local":[56,121,128,155],"around":[58],"query":[60,150],"as":[62,64,127],"well":[63],"global":[66,134,139],"that":[68,88,166,199],"summarizes":[69],"how":[70],"a":[71,80,124,143,161],"relation":[72,103,109,151],"behaves":[73],"many":[75],"instances.":[76],"We":[77],"propose":[78],"KGPFN,":[79],"model":[83],"using":[84,123,190],"Prior-data":[85],"Fitted":[86,163],"Network":[87,164],"unifies":[89],"regularities":[92],"inference-time":[94],"from":[97],"context.":[99,129],"KGPFN":[100,178,200],"first":[101],"learns":[102,179],"representations":[104],"via":[105],"message":[106],"passing":[107],"capture":[112],"cross-graph":[113],"invariances.":[115],"For":[116],"query-specific":[117],"reasoning,":[118],"it":[119,136],"encodes":[120],"neighborhoods":[122],"multi-layer":[125],"NBFNet":[126],"To":[130],"enable":[131],"ICL":[132],"at":[133,223],"scale,":[135],"constructs":[137],"relation-specific":[138],"retrieving":[142],"large":[144],"set":[145],"instances":[147],"together":[152],"their":[154],"neighborhoods,":[156],"aggregates":[158],"them":[159,189],"within":[160],"Prior-Data":[162],"framework":[165],"combines":[167],"feature-level":[168],"sample-level":[170],"attention.":[171],"Through":[172],"multi-graph":[173],"pretraining":[174],"diverse":[176],"when":[180,186],"instantiate":[182],"reusable":[183],"patterns":[184],"override":[188],"contextual":[191],"evidence.":[192],"Experiments":[193],"57":[195],"benchmarks":[197],"demonstrate":[198],"achieves":[201],"strong":[202],"adaptation":[203],"previously":[205],"through":[208],"alone,":[211],"consistently":[212],"outperforming":[213],"competitive":[214],"fine-tuned":[215],"models.":[218],"Our":[219],"code":[220],"available":[222],"https://github.com/HKUST-KnowComp/KGPFN.":[224]},"counts_by_year":[],"updated_date":"2026-07-01T06:00:48.157686","created_date":"2026-05-16T00:00:00"}