{"id":"https://openalex.org/W7131871572","doi":"https://doi.org/10.48550/arxiv.2602.22660","title":"LEDA: Latent Semantic Distribution Alignment for Multi-domain Graph Pre-training","display_name":"LEDA: Latent Semantic Distribution Alignment for Multi-domain Graph Pre-training","publication_year":2026,"publication_date":"2026-02-26","ids":{"openalex":"https://openalex.org/W7131871572","doi":"https://doi.org/10.48550/arxiv.2602.22660"},"language":null,"primary_location":{"id":"doi:10.48550/arxiv.2602.22660","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2602.22660","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.2602.22660","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/A5127152648","display_name":"Siqi Liu","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Liu, Siqi","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5065331390","display_name":"Jiaxu Cui","orcid":"https://orcid.org/0000-0002-4922-0915"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Cui, Jiaxu","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":0.9071000218391418,"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":0.9071000218391418,"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":0.05130000039935112,"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":0.017799999564886093,"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/inference","display_name":"Inference","score":0.5892000198364258},{"id":"https://openalex.org/keywords/graph","display_name":"Graph","score":0.4724999964237213},{"id":"https://openalex.org/keywords/unification","display_name":"Unification","score":0.4693000018596649},{"id":"https://openalex.org/keywords/semantics","display_name":"Semantics (computer science)","score":0.4438000023365021},{"id":"https://openalex.org/keywords/knowledge-graph","display_name":"Knowledge graph","score":0.4138000011444092},{"id":"https://openalex.org/keywords/bridging","display_name":"Bridging (networking)","score":0.41179999709129333},{"id":"https://openalex.org/keywords/feature-learning","display_name":"Feature learning","score":0.4099999964237213},{"id":"https://openalex.org/keywords/discriminative-model","display_name":"Discriminative model","score":0.3625999987125397},{"id":"https://openalex.org/keywords/semantic-data-model","display_name":"Semantic data model","score":0.33079999685287476}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7422000169754028},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.5892000198364258},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.5400999784469604},{"id":"https://openalex.org/C132525143","wikidata":"https://www.wikidata.org/wiki/Q141488","display_name":"Graph","level":2,"score":0.4724999964237213},{"id":"https://openalex.org/C96146094","wikidata":"https://www.wikidata.org/wiki/Q609057","display_name":"Unification","level":2,"score":0.4693000018596649},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.4438000023365021},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.43220001459121704},{"id":"https://openalex.org/C2987255567","wikidata":"https://www.wikidata.org/wiki/Q33002955","display_name":"Knowledge graph","level":2,"score":0.4138000011444092},{"id":"https://openalex.org/C174348530","wikidata":"https://www.wikidata.org/wiki/Q188635","display_name":"Bridging (networking)","level":2,"score":0.41179999709129333},{"id":"https://openalex.org/C59404180","wikidata":"https://www.wikidata.org/wiki/Q17013334","display_name":"Feature learning","level":2,"score":0.4099999964237213},{"id":"https://openalex.org/C97931131","wikidata":"https://www.wikidata.org/wiki/Q5282087","display_name":"Discriminative model","level":2,"score":0.3625999987125397},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3589000105857849},{"id":"https://openalex.org/C90312973","wikidata":"https://www.wikidata.org/wiki/Q7449052","display_name":"Semantic data model","level":2,"score":0.33079999685287476},{"id":"https://openalex.org/C207685749","wikidata":"https://www.wikidata.org/wiki/Q2088941","display_name":"Domain knowledge","level":2,"score":0.3018999993801117},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.28850001096725464},{"id":"https://openalex.org/C110903229","wikidata":"https://www.wikidata.org/wiki/Q7449064","display_name":"Semantic integration","level":4,"score":0.287200003862381},{"id":"https://openalex.org/C161301231","wikidata":"https://www.wikidata.org/wiki/Q3478658","display_name":"Knowledge representation and reasoning","level":2,"score":0.28529998660087585},{"id":"https://openalex.org/C57493831","wikidata":"https://www.wikidata.org/wiki/Q3134666","display_name":"Projection (relational algebra)","level":2,"score":0.2800000011920929},{"id":"https://openalex.org/C2778828372","wikidata":"https://www.wikidata.org/wiki/Q5283209","display_name":"Distributional semantics","level":3,"score":0.27889999747276306},{"id":"https://openalex.org/C36503486","wikidata":"https://www.wikidata.org/wiki/Q11235244","display_name":"Domain (mathematical analysis)","level":2,"score":0.27649998664855957},{"id":"https://openalex.org/C2775955345","wikidata":"https://www.wikidata.org/wiki/Q7449071","display_name":"Semantic mapping","level":2,"score":0.27559998631477356},{"id":"https://openalex.org/C2988382989","wikidata":"https://www.wikidata.org/wiki/Q370685","display_name":"Data space","level":2,"score":0.27559998631477356},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.27300000190734863},{"id":"https://openalex.org/C77660490","wikidata":"https://www.wikidata.org/wiki/Q244916","display_name":"Intermediate language","level":3,"score":0.26190000772476196},{"id":"https://openalex.org/C197914299","wikidata":"https://www.wikidata.org/wiki/Q18650","display_name":"Semantic memory","level":3,"score":0.25699999928474426},{"id":"https://openalex.org/C116409475","wikidata":"https://www.wikidata.org/wiki/Q1385056","display_name":"External Data Representation","level":2,"score":0.2547000050544739},{"id":"https://openalex.org/C183992945","wikidata":"https://www.wikidata.org/wiki/Q2495574","display_name":"Universality (dynamical systems)","level":2,"score":0.25380000472068787},{"id":"https://openalex.org/C67186912","wikidata":"https://www.wikidata.org/wiki/Q367664","display_name":"Data modeling","level":2,"score":0.2533999979496002},{"id":"https://openalex.org/C2129575","wikidata":"https://www.wikidata.org/wiki/Q54837","display_name":"Semantic Web","level":2,"score":0.25}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.48550/arxiv.2602.22660","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2602.22660","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.2602.22660","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2602.22660","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":[{"display_name":"Reduced inequalities","score":0.743522047996521,"id":"https://metadata.un.org/sdg/10"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Recent":[0],"advances":[1],"in":[2,36,46,98,113,117,221],"generic":[3,51],"large":[4],"models,":[5],"such":[6],"as":[7],"GPT":[8],"and":[9,24,59,87,202,217,230],"DeepSeek,":[10],"have":[11],"motivated":[12],"the":[13,71,99,181,192],"introduction":[14],"of":[15,65,73,102,215],"universality":[16],"to":[17,21,33,55,84,106,123,156,179,190],"graph":[18,31,80,146],"pre-training,":[19],"aiming":[20],"learn":[22],"rich":[23],"generalizable":[25],"knowledge":[26,49,126],"across":[27,200,211],"diverse":[28,79,159],"domains":[29,201],"using":[30],"representations":[32],"improve":[34],"performance":[35,210],"various":[37],"downstream":[38,218],"applications.":[39],"However,":[40],"most":[41],"existing":[42],"methods":[43],"face":[44],"challenges":[45],"learning":[47],"effective":[48,112,125],"from":[50,70,127],"graphs,":[52],"primarily":[53],"due":[54],"simplistic":[56,66],"data":[57,67,119],"alignment":[58,68],"limited":[60,94],"training":[61,95],"guidance.":[62],"The":[63,91,185],"issue":[64],"arises":[69],"use":[72],"a":[74,136,152,163,174,212],"straightforward":[75],"unification":[76],"for":[77,144],"highly":[78],"data,":[81],"which":[82],"fails":[83],"align":[85,158],"semantics":[86,199],"misleads":[88],"pre-training":[89,104,233],"models.":[90,234],"problem":[92],"with":[93,167,197],"guidance":[96],"lies":[97],"arbitrary":[100],"application":[101],"in-domain":[103,228],"paradigms":[105],"cross-domain":[107,204,223],"scenarios.":[108],"While":[109],"it":[110,121,196,225],"is":[111,187],"enhancing":[114],"discriminative":[115],"representation":[116],"one":[118],"space,":[120],"struggles":[122],"capture":[124],"many":[128],"graphs.":[129],"To":[130],"address":[131],"these":[132],"challenges,":[133],"we":[134,149,172],"propose":[135],"novel":[137],"Latent":[138],"sEmantic":[139],"Distribution":[140],"Alignment":[141],"(LEDA)":[142],"model":[143],"universal":[145,232],"pre-training.":[147],"Specifically,":[148],"first":[150],"introduce":[151],"dimension":[153],"projection":[154],"unit":[155],"adaptively":[157],"domain":[160,193],"features":[161],"into":[162],"shared":[164,182,198],"semantic":[165,176,205],"space":[166],"minimal":[168],"information":[169],"loss.":[170],"Furthermore,":[171],"design":[173],"variational":[175],"inference":[177],"module":[178],"obtain":[180],"latent":[183],"distribution.":[184],"distribution":[186],"then":[188],"adopted":[189],"guide":[191],"projection,":[194],"aligning":[195],"ensuring":[203],"learning.":[206],"LEDA":[207],"exhibits":[208],"strong":[209],"broad":[213],"range":[214],"graphs":[216],"tasks.":[219],"Remarkably,":[220],"few-shot":[222],"settings,":[224],"significantly":[226],"outperforms":[227],"baselines":[229],"advanced":[231]},"counts_by_year":[],"updated_date":"2026-02-28T06:18:59.386488","created_date":"2026-02-28T00:00:00"}