{"id":"https://openalex.org/W7131824416","doi":"https://doi.org/10.48550/arxiv.2602.22645","title":"MUG: Meta-path-aware Universal Heterogeneous Graph Pre-Training","display_name":"MUG: Meta-path-aware Universal Heterogeneous Graph Pre-Training","publication_year":2026,"publication_date":"2026-02-26","ids":{"openalex":"https://openalex.org/W7131824416","doi":"https://doi.org/10.48550/arxiv.2602.22645"},"language":null,"primary_location":{"id":"doi:10.48550/arxiv.2602.22645","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2602.22645","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":"article"},"type":"preprint","indexed_in":["datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://doi.org/10.48550/arxiv.2602.22645","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5109714735","display_name":"Lianze Shan","orcid":null},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Shan, Lianze","raw_affiliation_strings":[],"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":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5117111494","display_name":"Dongxiao He","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"He, Dongxiao","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102880698","display_name":"Yongqi Huang","orcid":"https://orcid.org/0009-0006-5607-8140"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Huang, Yongqi","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5127081355","display_name":"Zhiyong Feng","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Feng, Zhiyong","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5068659777","display_name":"Weixiong Zhang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zhang, Weixiong","raw_affiliation_strings":[],"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":6,"corresponding_author_ids":["https://openalex.org/A5109714735"],"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":0.992900013923645,"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":0.992900013923645,"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/T12292","display_name":"Graph Theory and Algorithms","score":0.0017000000225380063,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"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":0.0006000000284984708,"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/unification","display_name":"Unification","score":0.5809999704360962},{"id":"https://openalex.org/keywords/graph","display_name":"Graph","score":0.548799991607666},{"id":"https://openalex.org/keywords/semantics","display_name":"Semantics (computer science)","score":0.45500001311302185},{"id":"https://openalex.org/keywords/encoder","display_name":"Encoder","score":0.38659998774528503},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.38109999895095825},{"id":"https://openalex.org/keywords/homogeneous","display_name":"Homogeneous","score":0.3767000138759613},{"id":"https://openalex.org/keywords/focus","display_name":"Focus (optics)","score":0.3765999972820282}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6875},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.619700014591217},{"id":"https://openalex.org/C96146094","wikidata":"https://www.wikidata.org/wiki/Q609057","display_name":"Unification","level":2,"score":0.5809999704360962},{"id":"https://openalex.org/C132525143","wikidata":"https://www.wikidata.org/wiki/Q141488","display_name":"Graph","level":2,"score":0.548799991607666},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.45500001311302185},{"id":"https://openalex.org/C118505674","wikidata":"https://www.wikidata.org/wiki/Q42586063","display_name":"Encoder","level":2,"score":0.38659998774528503},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.38109999895095825},{"id":"https://openalex.org/C66882249","wikidata":"https://www.wikidata.org/wiki/Q169336","display_name":"Homogeneous","level":2,"score":0.3767000138759613},{"id":"https://openalex.org/C192209626","wikidata":"https://www.wikidata.org/wiki/Q190909","display_name":"Focus (optics)","level":2,"score":0.3765999972820282},{"id":"https://openalex.org/C2779808786","wikidata":"https://www.wikidata.org/wiki/Q6664603","display_name":"Locality","level":2,"score":0.3450999855995178},{"id":"https://openalex.org/C125411270","wikidata":"https://www.wikidata.org/wiki/Q18653","display_name":"Encoding (memory)","level":2,"score":0.2930000126361847},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.28360000252723694},{"id":"https://openalex.org/C140146324","wikidata":"https://www.wikidata.org/wiki/Q1144319","display_name":"Predicate (mathematical logic)","level":2,"score":0.2770000100135803},{"id":"https://openalex.org/C168167062","wikidata":"https://www.wikidata.org/wiki/Q1117970","display_name":"Component (thermodynamics)","level":2,"score":0.2574000060558319},{"id":"https://openalex.org/C62611344","wikidata":"https://www.wikidata.org/wiki/Q1062658","display_name":"Node (physics)","level":2,"score":0.2551000118255615},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.2547000050544739}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.48550/arxiv.2602.22645","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2602.22645","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":"article"}],"best_oa_location":{"id":"doi:10.48550/arxiv.2602.22645","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2602.22645","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":"article"},"sustainable_development_goals":[{"score":0.7456737160682678,"display_name":"Reduced inequalities","id":"https://metadata.un.org/sdg/10"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Universal":[0,127],"graph":[1,10,43,155],"pre-training":[2,44,130],"has":[3],"emerged":[4],"as":[5],"a":[6,14,32,72,90,124,139,157,165,169,184,204],"key":[7],"paradigm":[8],"in":[9,41],"representation":[11,92,160],"learning,":[12],"offering":[13],"promising":[15],"way":[16],"to":[17,20,28,70,114,116,187],"train":[18,71],"encoders":[19],"learn":[21],"transferable":[22],"representations":[23],"from":[24,110,146],"unlabeled":[25],"graphs":[26,49,175],"and":[27,50,61,97,106,149,209],"effectively":[29],"generalize":[30],"across":[31,102,174,192],"wide":[33],"range":[34],"of":[35,89,99,218],"downstream":[36],"tasks.":[37],"However,":[38],"recent":[39],"explorations":[40],"universal":[42,73],"primarily":[45],"focus":[46],"on":[47,199,220],"homogeneous":[48],"it":[51,67],"remains":[52],"unexplored":[53],"for":[54,75,134,179],"heterogeneous":[55,77,128,154],"graphs,":[56],"which":[57],"exhibit":[58],"greater":[59],"structural":[60,190],"semantic":[62],"complexity.":[63],"This":[64],"heterogeneity":[65],"makes":[66],"highly":[68],"challenging":[69],"encoder":[74,186],"diverse":[76,81,177,193],"graphs:":[78],"(i)":[79],"the":[80,87,95,216],"types":[82,151],"with":[83,176],"dataset-specific":[84,200,211],"semantics":[85,98],"hinder":[86],"construction":[88],"unified":[91,158],"space;":[93],"(ii)":[94],"number":[96],"meta-paths":[100],"vary":[101],"datasets,":[103],"making":[104],"encoding":[105],"aggregation":[107,201],"patterns":[108,191],"learned":[109],"one":[111],"dataset":[112],"difficult":[113],"apply":[115],"others.":[117],"To":[118],"address":[119],"these":[120],"challenges,":[121],"we":[122],"propose":[123],"novel":[125],"Meta-path-aware":[126],"Graph":[129],"(MUG)":[131],"approach.":[132],"Specifically,":[133],"challenge":[135,180],"(i),":[136],"MUG":[137,182,219],"introduces":[138],"input":[140],"unification":[141],"module":[142],"that":[143],"integrates":[144],"information":[145],"multiple":[147],"node":[148],"relation":[150],"within":[152],"each":[153],"into":[156,164],"representation.This":[159],"is":[161],"then":[162],"projected":[163],"shared":[166,185],"space":[167],"by":[168],"dimension-aware":[170],"encoder,":[171],"enabling":[172],"alignment":[173],"schemas.Furthermore,":[178],"(ii),":[181],"trains":[183],"capture":[188],"consistent":[189],"meta-path":[194],"views":[195],"rather":[196],"than":[197],"relying":[198],"strategies,":[202],"while":[203],"global":[205],"objective":[206],"encourages":[207],"discriminability":[208],"reduces":[210],"biases.":[212],"Extensive":[213],"experiments":[214],"demonstrate":[215],"effectiveness":[217],"some":[221],"real":[222],"datasets.":[223]},"counts_by_year":[],"updated_date":"2026-02-28T06:18:59.386488","created_date":"2026-02-28T00:00:00"}