{"id":"https://openalex.org/W7154371741","doi":"https://doi.org/10.48550/arxiv.2604.11257","title":"Unified Graph Prompt Learning via Low-Rank Graph Message Prompting","display_name":"Unified Graph Prompt Learning via Low-Rank Graph Message Prompting","publication_year":2026,"publication_date":"2026-04-13","ids":{"openalex":"https://openalex.org/W7154371741","doi":"https://doi.org/10.48550/arxiv.2604.11257"},"language":null,"primary_location":{"id":"doi:10.48550/arxiv.2604.11257","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2604.11257","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.2604.11257","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5133607200","display_name":"Beibei Wang","orcid":null},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Wang, Beibei","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5133620287","display_name":"Bo Jiang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Jiang, Bo","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5133614589","display_name":"Ziyan Zhang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zhang, Ziyan","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5133586193","display_name":"Jin Tang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Tang, Jin","raw_affiliation_strings":[],"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5133607200"],"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":0.9776999950408936,"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":0.9776999950408936,"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":0.004100000020116568,"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":0.0019000000320374966,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/graph","display_name":"Graph","score":0.5782999992370605},{"id":"https://openalex.org/keywords/voltage-graph","display_name":"Voltage graph","score":0.4390000104904175},{"id":"https://openalex.org/keywords/null-graph","display_name":"Null graph","score":0.4198000133037567},{"id":"https://openalex.org/keywords/graph-property","display_name":"Graph property","score":0.37929999828338623},{"id":"https://openalex.org/keywords/line-graph","display_name":"Line graph","score":0.37040001153945923},{"id":"https://openalex.org/keywords/complement-graph","display_name":"Complement graph","score":0.3483999967575073}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6629999876022339},{"id":"https://openalex.org/C132525143","wikidata":"https://www.wikidata.org/wiki/Q141488","display_name":"Graph","level":2,"score":0.5782999992370605},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.5130000114440918},{"id":"https://openalex.org/C22149727","wikidata":"https://www.wikidata.org/wiki/Q7940747","display_name":"Voltage graph","level":4,"score":0.4390000104904175},{"id":"https://openalex.org/C17169500","wikidata":"https://www.wikidata.org/wiki/Q3033506","display_name":"Null graph","level":5,"score":0.4198000133037567},{"id":"https://openalex.org/C64339825","wikidata":"https://www.wikidata.org/wiki/Q722659","display_name":"Graph property","level":5,"score":0.37929999828338623},{"id":"https://openalex.org/C203776342","wikidata":"https://www.wikidata.org/wiki/Q1378376","display_name":"Line graph","level":3,"score":0.37040001153945923},{"id":"https://openalex.org/C168291704","wikidata":"https://www.wikidata.org/wiki/Q902252","display_name":"Complement graph","level":5,"score":0.3483999967575073},{"id":"https://openalex.org/C5737132","wikidata":"https://www.wikidata.org/wiki/Q1101814","display_name":"Clique-width","level":5,"score":0.34450000524520874},{"id":"https://openalex.org/C59404180","wikidata":"https://www.wikidata.org/wiki/Q17013334","display_name":"Feature learning","level":2,"score":0.30390000343322754},{"id":"https://openalex.org/C146380142","wikidata":"https://www.wikidata.org/wiki/Q1137726","display_name":"Directed graph","level":2,"score":0.3034999966621399},{"id":"https://openalex.org/C106891557","wikidata":"https://www.wikidata.org/wiki/Q4148051","display_name":"Wait-for graph","level":4,"score":0.2897999882698059},{"id":"https://openalex.org/C176225458","wikidata":"https://www.wikidata.org/wiki/Q595971","display_name":"Graph database","level":3,"score":0.2709999978542328}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.48550/arxiv.2604.11257","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2604.11257","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.2604.11257","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2604.11257","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":0.7269318103790283,"display_name":"Decent work and economic growth","id":"https://metadata.un.org/sdg/8"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Graph":[0,95],"Data":[1],"Prompt":[2,97],"(GDP),":[3],"which":[4,116],"introduces":[5],"specific":[6],"prompts":[7],"in":[8,77,147],"graph":[9,22,35,52,70,108,127,136,145,166],"data":[10],"for":[11,33,51,67],"efficiently":[12],"adapting":[13],"pre-trained":[14],"GNNs,":[15],"has":[16],"become":[17],"a":[18,63,85,106,148],"mainstream":[19],"approach":[20],"to":[21,83,121],"fine-tuning":[23],"learning":[24,110],"problem.":[25],"However,":[26],"existing":[27,89],"GDPs":[28,90,132],"have":[29],"been":[30],"respectively":[31],"designed":[32],"distinct":[34,135],"component":[36],"(e.g.,":[37],"node":[38],"features,":[39,41],"edge":[40,42],"weights)":[43],"and":[44,125,156,172],"thus":[45],"operate":[46],"within":[47],"limited":[48],"prompt":[49,109,119,128],"spaces":[50],"data.":[53],"To":[54,73],"the":[55,170],"best":[56],"of":[57,88,94,174],"our":[58,175],"knowledge,":[59],"it":[60],"still":[61],"lacks":[62],"unified":[64,149],"prompter":[65],"suitable":[66],"targeting":[68],"all":[69,144],"components":[71,137,146],"simultaneously.":[72],"address":[74],"this":[75,78],"challenge,":[76],"paper,":[79],"we":[80,103],"first":[81],"propose":[82],"reinterpret":[84],"wide":[86],"range":[87],"from":[91],"an":[92,123],"aspect":[93],"Message":[96],"(GMP)":[98],"paradigm.":[99],"Based":[100],"on":[101,143,158,164],"GMP,":[102],"then":[104],"introduce":[105],"novel":[107],"approach,":[111],"termed":[112],"Low-Rank":[113],"GMP":[114],"(LR-GMP),":[115],"leverages":[117],"low-rank":[118],"representation":[120],"achieve":[122],"effective":[124],"compact":[126],"learning.":[129],"Unlike":[130],"traditional":[131],"that":[133],"target":[134],"separately,":[138],"LR-GMP":[139],"concurrently":[140],"performs":[141],"prompting":[142],"manner,":[150],"thereby":[151],"achieving":[152],"significantly":[153],"superior":[154],"generalization":[155],"robustness":[157],"diverse":[159],"downstream":[160],"tasks.":[161],"Extensive":[162],"experiments":[163],"several":[165],"benchmark":[167],"datasets":[168],"demonstrate":[169],"effectiveness":[171],"advantages":[173],"proposed":[176],"LR-GMP.":[177]},"counts_by_year":[],"updated_date":"2026-04-15T06:04:33.058270","created_date":"2026-04-15T00:00:00"}