{"id":"https://openalex.org/W7161570118","doi":"https://doi.org/10.48550/arxiv.2605.15888","title":"CHoE: Cross-Domain Heterogeneous Graph Prompt Learning via Structure-Conditioned Experts","display_name":"CHoE: Cross-Domain Heterogeneous Graph Prompt Learning via Structure-Conditioned Experts","publication_year":2026,"publication_date":"2026-05-15","ids":{"openalex":"https://openalex.org/W7161570118","doi":"https://doi.org/10.48550/arxiv.2605.15888"},"language":null,"primary_location":{"id":"doi:10.48550/arxiv.2605.15888","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2605.15888","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.2605.15888","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5114250913","display_name":"Peiyuan Li","orcid":"https://orcid.org/0009-0002-0365-1602"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Li, Peiyuan","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5136357323","display_name":"Yongqi Huang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Huang, Yongqi","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100588104","display_name":"Jitao Zhao","orcid":"https://orcid.org/0000-0002-3909-1718"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zhao, Jitao","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5136400754","display_name":"Dongxiao He","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"He, Dongxiao","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5136424394","display_name":"Di Jin","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Jin, Di","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5068659777","display_name":"Weixiong Zhang","orcid":"https://orcid.org/0000-0002-4998-9791"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zhang, Weixiong","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":0.9843000173568726,"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":0.9843000173568726,"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":0.003599999938160181,"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":0.001500000013038516,"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/bridging","display_name":"Bridging (networking)","score":0.5985999703407288},{"id":"https://openalex.org/keywords/graph","display_name":"Graph","score":0.5281000137329102},{"id":"https://openalex.org/keywords/knowledge-graph","display_name":"Knowledge graph","score":0.4381999969482422},{"id":"https://openalex.org/keywords/downstream","display_name":"Downstream (manufacturing)","score":0.43479999899864197},{"id":"https://openalex.org/keywords/baseline","display_name":"Baseline (sea)","score":0.4000000059604645}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8026999831199646},{"id":"https://openalex.org/C174348530","wikidata":"https://www.wikidata.org/wiki/Q188635","display_name":"Bridging (networking)","level":2,"score":0.5985999703407288},{"id":"https://openalex.org/C132525143","wikidata":"https://www.wikidata.org/wiki/Q141488","display_name":"Graph","level":2,"score":0.5281000137329102},{"id":"https://openalex.org/C2987255567","wikidata":"https://www.wikidata.org/wiki/Q33002955","display_name":"Knowledge graph","level":2,"score":0.4381999969482422},{"id":"https://openalex.org/C2776207758","wikidata":"https://www.wikidata.org/wiki/Q5303302","display_name":"Downstream (manufacturing)","level":2,"score":0.43479999899864197},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4242999851703644},{"id":"https://openalex.org/C12725497","wikidata":"https://www.wikidata.org/wiki/Q810247","display_name":"Baseline (sea)","level":2,"score":0.4000000059604645},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.39879998564720154},{"id":"https://openalex.org/C59404180","wikidata":"https://www.wikidata.org/wiki/Q17013334","display_name":"Feature learning","level":2,"score":0.2709999978542328},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.25920000672340393},{"id":"https://openalex.org/C16311509","wikidata":"https://www.wikidata.org/wiki/Q4148050","display_name":"Dependency graph","level":3,"score":0.2572999894618988}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.48550/arxiv.2605.15888","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2605.15888","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.2605.15888","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2605.15888","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":"Partnerships for the goals","score":0.45670610666275024,"id":"https://metadata.un.org/sdg/17"}],"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],"Prompt":[2],"Learning":[3],"(HGPL)has":[4],"emerged":[5],"as":[6],"a":[7,89,112,133],"promising":[8],"paradigm":[9],"for":[10,36,50,125,144],"bridging":[11],"the":[12,15,47,61],"gap":[13],"between":[14],"objectives":[16],"of":[17,63],"pre-training":[18,51],"foundation":[19],"models":[20],"and":[21,46,52,72,102,106,116],"their":[22,73],"downstream":[23,53,145],"applications":[24],"in":[25,155],"heterogeneous":[26],"graph":[27],"settings.":[28],"However,":[29],"existing":[30],"HGPL":[31,65,91],"methods":[32],"are":[33],"primarily":[34],"designed":[35],"in-domain":[37,70],"scenarios,":[38],"whereas":[39],"real-world":[40],"deployments":[41],"often":[42],"span":[43],"multiple":[44,142],"domains,":[45],"data":[48],"used":[49],"tasks":[54],"may":[55],"originate":[56],"from":[57],"different":[58],"distributions.":[59],"Consequently,":[60],"applicability":[62],"current":[64],"approaches":[66],"is":[67],"limited":[68],"to":[69,120,138],"settings,":[71],"performance":[74,154],"typically":[75],"degrades":[76],"when":[77],"application":[78],"domains":[79],"shift.":[80],"To":[81],"address":[82],"this":[83],"serious":[84],"limitation,":[85],"we":[86,100,110,131],"develop":[87],"CHoE,":[88],"cross-domain":[90,157],"method":[92],"built":[93],"upon":[94],"an":[95],"expert":[96,114],"network.":[97],"During":[98],"pre-training,":[99],"introduce":[101],"train":[103],"structure-conditioned":[104],"experts,":[105],"during":[107],"prompt":[108],"tuning,":[109],"adopt":[111],"structure-aware":[113],"routing":[115],"load":[117],"balancing":[118],"mechanism":[119],"select":[121],"structurally":[122],"compatible":[123],"experts":[124],"each":[126],"meta-path":[127],"view.":[128],"In":[129],"addition,":[130],"design":[132],"prompt-based":[134],"semantic":[135],"fusion":[136],"module":[137],"integrate":[139],"representations":[140],"across":[141],"views":[143],"prediction.":[146],"Extensive":[147],"experiments":[148],"show":[149],"that":[150],"CHoE":[151],"consistently":[152],"improves":[153],"few-shot":[156],"applications,":[158],"outperforming":[159],"all":[160],"baseline":[161],"approaches.":[162]},"counts_by_year":[],"updated_date":"2026-07-01T06:00:48.157686","created_date":"2026-05-19T00:00:00"}