{"id":"https://openalex.org/W7127892515","doi":"https://doi.org/10.48550/arxiv.2602.05424","title":"THOR: Inductive Link Prediction over Hyper-Relational Knowledge Graphs","display_name":"THOR: Inductive Link Prediction over Hyper-Relational Knowledge Graphs","publication_year":2026,"publication_date":"2026-02-05","ids":{"openalex":"https://openalex.org/W7127892515","doi":"https://doi.org/10.48550/arxiv.2602.05424"},"language":null,"primary_location":{"id":"doi:10.48550/arxiv.2602.05424","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2602.05424","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.2602.05424","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5048193554","display_name":"Weijian Yu","orcid":"https://orcid.org/0009-0009-3278-4966"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yu, Weijian","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5125175081","display_name":"Yuhuan Lu","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Lu, Yuhuan","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5123644949","display_name":"Dingqi Yang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yang, Dingqi","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":0.9904000163078308,"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":0.9904000163078308,"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/T10887","display_name":"Bioinformatics and Genomic Networks","score":0.002300000051036477,"subfield":{"id":"https://openalex.org/subfields/1312","display_name":"Molecular Biology"},"field":{"id":"https://openalex.org/fields/13","display_name":"Biochemistry, Genetics and Molecular Biology"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}},{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","score":0.0017999999690800905,"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/generalizability-theory","display_name":"Generalizability theory","score":0.48240000009536743},{"id":"https://openalex.org/keywords/link","display_name":"Link (geometry)","score":0.47690001130104065},{"id":"https://openalex.org/keywords/relation","display_name":"Relation (database)","score":0.45419999957084656},{"id":"https://openalex.org/keywords/vocabulary","display_name":"Vocabulary","score":0.4537999927997589},{"id":"https://openalex.org/keywords/embedding","display_name":"Embedding","score":0.44449999928474426},{"id":"https://openalex.org/keywords/variety","display_name":"Variety (cybernetics)","score":0.4251999855041504},{"id":"https://openalex.org/keywords/question-answering","display_name":"Question answering","score":0.40230000019073486},{"id":"https://openalex.org/keywords/key","display_name":"Key (lock)","score":0.40049999952316284},{"id":"https://openalex.org/keywords/knowledge-graph","display_name":"Knowledge graph","score":0.3977000117301941}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7080000042915344},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.49459999799728394},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.4945000112056732},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.48590001463890076},{"id":"https://openalex.org/C27158222","wikidata":"https://www.wikidata.org/wiki/Q5532422","display_name":"Generalizability theory","level":2,"score":0.48240000009536743},{"id":"https://openalex.org/C2778753846","wikidata":"https://www.wikidata.org/wiki/Q6554239","display_name":"Link (geometry)","level":2,"score":0.47690001130104065},{"id":"https://openalex.org/C25343380","wikidata":"https://www.wikidata.org/wiki/Q277521","display_name":"Relation (database)","level":2,"score":0.45419999957084656},{"id":"https://openalex.org/C2777601683","wikidata":"https://www.wikidata.org/wiki/Q6499736","display_name":"Vocabulary","level":2,"score":0.4537999927997589},{"id":"https://openalex.org/C41608201","wikidata":"https://www.wikidata.org/wiki/Q980509","display_name":"Embedding","level":2,"score":0.44449999928474426},{"id":"https://openalex.org/C136197465","wikidata":"https://www.wikidata.org/wiki/Q1729295","display_name":"Variety (cybernetics)","level":2,"score":0.4251999855041504},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.4250999987125397},{"id":"https://openalex.org/C44291984","wikidata":"https://www.wikidata.org/wiki/Q1074173","display_name":"Question answering","level":2,"score":0.40230000019073486},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.40049999952316284},{"id":"https://openalex.org/C2987255567","wikidata":"https://www.wikidata.org/wiki/Q33002955","display_name":"Knowledge graph","level":2,"score":0.3977000117301941},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.3580999970436096},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.35420000553131104},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.3456999957561493},{"id":"https://openalex.org/C152124472","wikidata":"https://www.wikidata.org/wiki/Q1204361","display_name":"Redundancy (engineering)","level":2,"score":0.3188999891281128},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.3122999966144562},{"id":"https://openalex.org/C94124525","wikidata":"https://www.wikidata.org/wiki/Q912550","display_name":"Categorization","level":2,"score":0.30410000681877136},{"id":"https://openalex.org/C118505674","wikidata":"https://www.wikidata.org/wiki/Q42586063","display_name":"Encoder","level":2,"score":0.30379998683929443},{"id":"https://openalex.org/C132525143","wikidata":"https://www.wikidata.org/wiki/Q141488","display_name":"Graph","level":2,"score":0.2957000136375427},{"id":"https://openalex.org/C161301231","wikidata":"https://www.wikidata.org/wiki/Q3478658","display_name":"Knowledge representation and reasoning","level":2,"score":0.28949999809265137},{"id":"https://openalex.org/C21563000","wikidata":"https://www.wikidata.org/wiki/Q484511","display_name":"Inductive reasoning","level":2,"score":0.27649998664855957},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.27619999647140503},{"id":"https://openalex.org/C118930307","wikidata":"https://www.wikidata.org/wiki/Q600590","display_name":"Tuple","level":2,"score":0.2621000111103058},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.2572000026702881},{"id":"https://openalex.org/C192209626","wikidata":"https://www.wikidata.org/wiki/Q190909","display_name":"Focus (optics)","level":2,"score":0.2556999921798706},{"id":"https://openalex.org/C182620335","wikidata":"https://www.wikidata.org/wiki/Q2852531","display_name":"Answer set programming","level":3,"score":0.2533999979496002},{"id":"https://openalex.org/C31170391","wikidata":"https://www.wikidata.org/wiki/Q188619","display_name":"Hierarchy","level":2,"score":0.25099998712539673},{"id":"https://openalex.org/C188198153","wikidata":"https://www.wikidata.org/wiki/Q1613840","display_name":"Limiting","level":2,"score":0.2500999867916107}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.48550/arxiv.2602.05424","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2602.05424","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.2602.05424","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2602.05424","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":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Knowledge":[0],"graphs":[1,168],"(KGs)":[2],"have":[3],"become":[4],"a":[5,9,21,43,81,95,176,189,210],"key":[6,238],"ingredient":[7],"supporting":[8],"variety":[10],"of":[11,18,32,39,54,94,192,213,232],"applications.":[12],"Beyond":[13],"the":[14,51,55,61,91,105,165,222,242],"traditional":[15],"triplet":[16,44],"representation":[17],"facts":[19],"where":[20,35,84],"relation":[22,135],"connects":[23],"two":[24,166,170],"entities,":[25],"modern":[26],"KGs":[27,76],"observe":[28],"an":[29,36,121],"increasing":[30],"number":[31,38],"hyper-relational":[33,75,195],"facts,":[34],"arbitrary":[37],"qualifiers":[40],"associated":[41],"with":[42,169,202],"provide":[45],"auxiliary":[46],"information":[47],"to":[48,111,152,162],"further":[49],"describe":[50],"rich":[52],"semantics":[53],"triplet,":[56],"which":[57,149,179],"can":[58,100],"effectively":[59],"boost":[60],"reasoning":[62],"performance":[63],"in":[64,147,194],"link":[65,70,123,196],"prediction":[66,71,124,197],"tasks.":[67,250],"However,":[68],"existing":[69],"techniques":[72],"over":[73,221],"such":[74],"(HKGs)":[77],"mostly":[78],"focus":[79],"on":[80,199],"transductive":[82],"setting,":[83],"KG":[85,97],"embedding":[86],"models":[87],"are":[88,150],"learned":[89],"from":[90,164],"specific":[92,154],"vocabulary":[93],"given":[96],"and":[98,136,144,156,184,218,226],"subsequently":[99],"only":[101],"make":[102],"predictions":[103],"within":[104],"same":[106],"vocabulary,":[107],"limiting":[108],"their":[109,141],"generalizability":[110],"previously":[112],"unseen":[113],"vocabularies.":[114],"Against":[115],"this":[116],"background,":[117],"we":[118,131],"propose":[119],"THOR,":[120],"inducTive":[122],"technique":[125],"for":[126,248],"Hyper-relational":[127],"knOwledge":[128],"gRaphs.":[129],"Specifically,":[130],"first":[132],"introduce":[133],"both":[134],"entity":[137],"foundation":[138,167],"graphs,":[139],"modeling":[140],"fundamental":[142],"inter-":[143],"intra-fact":[145],"interactions":[146],"HKGs,":[148],"agnostic":[151],"any":[153],"relations":[155],"entities.":[157],"Afterward,":[158],"THOR":[159,193,208],"is":[160],"designed":[161],"learn":[163],"parallel":[171],"graph":[172],"encoders":[173],"followed":[174],"by":[175],"transformer":[177],"decoder,":[178],"supports":[180],"efficient":[181],"masked":[182],"training":[183],"fully-inductive":[185,227],"inference.":[186],"We":[187],"conduct":[188],"thorough":[190],"evaluation":[191],"tasks":[198],"12":[200],"datasets":[201],"different":[203],"settings.":[204],"Results":[205],"show":[206],"that":[207],"outperforms":[209],"sizable":[211],"collection":[212],"baselines,":[214],"yielding":[215],"66.1%,":[216],"55.9%,":[217],"20.4%":[219],"improvement":[220],"best-performing":[223],"rule-based,":[224],"semi-inductive,":[225],"techniques,":[228],"respectively.":[229],"A":[230],"series":[231],"ablation":[233],"studies":[234],"also":[235],"reveals":[236],"our":[237],"design":[239],"factors":[240],"capturing":[241],"structural":[243],"invariance":[244],"transferable":[245],"across":[246],"HKGs":[247],"inductive":[249]},"counts_by_year":[],"updated_date":"2026-08-16T07:02:28.622633","created_date":"2026-02-07T00:00:00"}