{"id":"https://openalex.org/W7147075079","doi":"https://doi.org/10.48550/arxiv.2603.27685","title":"CrossHGL: A Text-Free Foundation Model for Cross-Domain Heterogeneous Graph Learning","display_name":"CrossHGL: A Text-Free Foundation Model for Cross-Domain Heterogeneous Graph Learning","publication_year":2026,"publication_date":"2026-03-29","ids":{"openalex":"https://openalex.org/W7147075079","doi":"https://doi.org/10.48550/arxiv.2603.27685"},"language":null,"primary_location":{"id":"doi:10.48550/arxiv.2603.27685","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2603.27685","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.2603.27685","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5032298471","display_name":"Xuanze Chen","orcid":"https://orcid.org/0000-0002-0304-2391"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Chen, Xuanze","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5132617950","display_name":"Jiajun Zhou","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zhou, Jiajun","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5132600192","display_name":"Yadong Li","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Li, Yadong","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5132691144","display_name":"Shanqing Yu","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yu, Shanqing","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5132574106","display_name":"Qi Xuan","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Xuan, Qi","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":0.9854000210762024,"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":0.9854000210762024,"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":0.006899999920278788,"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":0.0019000000320374966,"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":0.5250999927520752},{"id":"https://openalex.org/keywords/semantics","display_name":"Semantics (computer science)","score":0.5044999718666077},{"id":"https://openalex.org/keywords/graph-rewriting","display_name":"Graph rewriting","score":0.49889999628067017},{"id":"https://openalex.org/keywords/feature-learning","display_name":"Feature learning","score":0.45210000872612},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.40630000829696655},{"id":"https://openalex.org/keywords/node","display_name":"Node (physics)","score":0.3962000012397766},{"id":"https://openalex.org/keywords/knowledge-representation-and-reasoning","display_name":"Knowledge representation and reasoning","score":0.38260000944137573}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7610999941825867},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.5615000128746033},{"id":"https://openalex.org/C132525143","wikidata":"https://www.wikidata.org/wiki/Q141488","display_name":"Graph","level":2,"score":0.5250999927520752},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.5044999718666077},{"id":"https://openalex.org/C558772884","wikidata":"https://www.wikidata.org/wiki/Q1508564","display_name":"Graph rewriting","level":3,"score":0.49889999628067017},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.459199994802475},{"id":"https://openalex.org/C59404180","wikidata":"https://www.wikidata.org/wiki/Q17013334","display_name":"Feature learning","level":2,"score":0.45210000872612},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.40630000829696655},{"id":"https://openalex.org/C62611344","wikidata":"https://www.wikidata.org/wiki/Q1062658","display_name":"Node (physics)","level":2,"score":0.3962000012397766},{"id":"https://openalex.org/C161301231","wikidata":"https://www.wikidata.org/wiki/Q3478658","display_name":"Knowledge representation and reasoning","level":2,"score":0.38260000944137573},{"id":"https://openalex.org/C2987255567","wikidata":"https://www.wikidata.org/wiki/Q33002955","display_name":"Knowledge graph","level":2,"score":0.3668000102043152},{"id":"https://openalex.org/C66882249","wikidata":"https://www.wikidata.org/wiki/Q169336","display_name":"Homogeneous","level":2,"score":0.366100013256073},{"id":"https://openalex.org/C4554734","wikidata":"https://www.wikidata.org/wiki/Q593744","display_name":"Knowledge base","level":2,"score":0.34470000863075256},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.33329999446868896},{"id":"https://openalex.org/C162307627","wikidata":"https://www.wikidata.org/wiki/Q204833","display_name":"Enhanced Data Rates for GSM Evolution","level":2,"score":0.302700012922287},{"id":"https://openalex.org/C2780966255","wikidata":"https://www.wikidata.org/wiki/Q5474306","display_name":"Foundation (evidence)","level":2,"score":0.2676999866962433},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.2590000033378601}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.48550/arxiv.2603.27685","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2603.27685","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.2603.27685","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2603.27685","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":[{"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4","score":0.40245482325553894}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Heterogeneous":[0],"graph":[1,37,174],"representation":[2],"learning":[3],"(HGRL)":[4],"is":[5],"essential":[6],"for":[7,171],"modeling":[8],"complex":[9],"systems":[10],"with":[11,26,107],"diverse":[12],"node":[13,172],"and":[14,29,58,75,117,138,145,151,167,173],"edge":[15,97],"types.":[16],"However,":[17],"most":[18],"existing":[19],"methods":[20],"are":[21],"limited":[22],"to":[23],"closed-world":[24],"settings":[25],"shared":[27],"schemas":[28],"feature":[30],"spaces,":[31],"hindering":[32],"cross-domain":[33,60],"generalization.":[34],"While":[35],"recent":[36],"foundation":[38,71],"models":[39],"improve":[40],"transferability,":[41],"they":[42],"often":[43],"target":[44],"homogeneous":[45],"graphs,":[46],"rely":[47],"on":[48,100,149],"domain-specific":[49],"schemas,":[50],"or":[51],"require":[52],"rich":[53],"textual":[54,82],"attributes.":[55],"Consequently,":[56],"text-free":[57],"few-shot":[59,140],"HGRL":[61],"remains":[62],"underexplored.":[63],"To":[64],"address":[65],"this,":[66,101],"we":[67,127],"propose":[68],"CrossHGL,":[69],"a":[70,85,102,108,129],"framework":[72,106],"that":[73,133,155],"preserves":[74],"transfers":[76],"multi-relational":[77],"structural":[78],"semantics":[79,95],"without":[80],"external":[81],"supervision.":[83],"Specifically,":[84],"semantic-preserving":[86],"transformation":[87],"strategy":[88,132],"homogenizes":[89],"heterogeneous":[90],"graphs":[91],"while":[92,177],"encoding":[93],"interaction":[94],"into":[96],"features.":[98],"Based":[99],"prompt-aware":[103],"multi-domain":[104],"pre-training":[105],"Tri-Prompt":[109],"mechanism":[110],"captures":[111],"transferable":[112],"knowledge":[113],"across":[114],"feature,":[115],"edge,":[116],"structure":[118],"perspectives":[119],"via":[120,142],"self-supervised":[121],"contrastive":[122],"learning.":[123,147],"For":[124],"target-domain":[125],"adaptation,":[126],"develop":[128],"parameter-efficient":[130],"fine-tuning":[131],"freezes":[134],"the":[135],"pre-trained":[136],"backbone":[137],"performs":[139],"classification":[141],"prompt":[143],"composition":[144],"prototypical":[146],"Experiments":[148],"node-level":[150],"graph-level":[152],"tasks":[153],"show":[154],"CrossHGL":[156],"consistently":[157],"outperforms":[158],"state-of-the-art":[159],"baselines,":[160],"yielding":[161],"average":[162],"relative":[163],"improvements":[164],"of":[165],"25.1%":[166],"7.6%":[168],"in":[169,180],"Micro-F1":[170],"classification,":[175],"respectively,":[176],"remaining":[178],"competitive":[179],"challenging":[181],"feature-degenerated":[182],"settings.":[183]},"counts_by_year":[],"updated_date":"2026-07-01T06:00:48.157686","created_date":"2026-04-02T00:00:00"}