{"id":"https://openalex.org/W4300978695","doi":"https://doi.org/10.48550/arxiv.2209.15240","title":"Universal Prompt Tuning for Graph Neural Networks","display_name":"Universal Prompt Tuning for Graph Neural Networks","publication_year":2022,"publication_date":"2022-09-30","ids":{"openalex":"https://openalex.org/W4300978695","doi":"https://doi.org/10.48550/arxiv.2209.15240"},"language":"en","primary_location":{"id":"pmh:oai:arXiv.org:2209.15240","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2209.15240","pdf_url":"https://arxiv.org/pdf/2209.15240","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":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"text"},"type":"preprint","indexed_in":["arxiv","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2209.15240","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5089081657","display_name":"Taoran Fang","orcid":null},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Fang, Taoran","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102879629","display_name":"Yunchao Zhang","orcid":"https://orcid.org/0000-0002-3226-5324"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zhang, Yunchao","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100397616","display_name":"Yang Yang","orcid":"https://orcid.org/0000-0002-5070-4511"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yang, Yang","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5038718363","display_name":"Chunping Wang","orcid":"https://orcid.org/0000-0002-3841-1919"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Wang, Chunping","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"last","author":{"id":null,"display_name":"Chen, Lei","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Chen, Lei","raw_affiliation_strings":[],"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5089081657"],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":11,"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":0.9991000294685364,"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":0.9991000294685364,"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":0.974399983882904,"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/T11122","display_name":"Online Learning and Analytics","score":0.942799985408783,"subfield":{"id":"https://openalex.org/subfields/1706","display_name":"Computer Science Applications"},"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/computer-science","display_name":"Computer science","score":0.7366478443145752},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5294252038002014},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.521072506904602},{"id":"https://openalex.org/keywords/graph","display_name":"Graph","score":0.4972284138202667},{"id":"https://openalex.org/keywords/theoretical-computer-science","display_name":"Theoretical computer science","score":0.2650652527809143}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7366478443145752},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5294252038002014},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.521072506904602},{"id":"https://openalex.org/C132525143","wikidata":"https://www.wikidata.org/wiki/Q141488","display_name":"Graph","level":2,"score":0.4972284138202667},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.2650652527809143}],"mesh":[],"locations_count":2,"locations":[{"id":"pmh:oai:arXiv.org:2209.15240","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2209.15240","pdf_url":"https://arxiv.org/pdf/2209.15240","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":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"text"},{"id":"doi:10.48550/arxiv.2209.15240","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2209.15240","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":"pmh:oai:arXiv.org:2209.15240","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2209.15240","pdf_url":"https://arxiv.org/pdf/2209.15240","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":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"text"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W2961085424","https://openalex.org/W4306674287","https://openalex.org/W3046775127","https://openalex.org/W3107602296","https://openalex.org/W3170094116","https://openalex.org/W4386462264","https://openalex.org/W4364306694","https://openalex.org/W4312192474","https://openalex.org/W4283697347","https://openalex.org/W4210805261"],"abstract_inverted_index":{"In":[0,75],"recent":[1],"years,":[2],"prompt":[3],"tuning":[4,37,83,207],"has":[5,47],"sparked":[6],"a":[7,80,227],"research":[8],"surge":[9],"in":[10,20,33,148,190,196],"adapting":[11],"pre-trained":[12,68,91],"models.":[13],"Unlike":[14],"the":[15,21,24,101,126,141,145,158,214],"unified":[16],"pre-training":[17,29,60,96,132,173,215],"strategy":[18,133,216],"employed":[19],"language":[22],"field,":[23],"graph":[25,40,143],"field":[26],"exhibits":[27],"diverse":[28],"strategies,":[30],"posing":[31],"challenges":[32],"designing":[34],"appropriate":[35],"prompt-based":[36,82,206],"methods":[38,63,208],"for":[39,52,90,144,232],"neural":[41],"networks.":[42],"While":[43],"some":[44],"pioneering":[45],"work":[46],"devised":[48],"specialized":[49,205],"prompting":[50,117,127],"functions":[51],"models":[53,70,93,212],"that":[54,176],"employ":[55,137],"edge":[56],"prediction":[57],"as":[58,226],"their":[59],"tasks,":[61],"these":[62],"are":[64],"limited":[65],"to":[66,113,124,130,139,156,211,230],"specific":[67],"GNN":[69,92],"and":[71,106,162,193],"lack":[72],"broader":[73],"applicability.":[74],"this":[76],"paper,":[77],"we":[78,120,136],"introduce":[79],"universal":[81],"method":[84,178,201,225],"called":[85],"Graph":[86],"Prompt":[87],"Feature":[88],"(GPF)":[89],"under":[94,171],"any":[95,114],"strategy.":[97],"GPF":[98,138,161],"operates":[99],"on":[100],"input":[102],"graph's":[103],"feature":[104],"space":[105],"can":[107],"theoretically":[108],"achieve":[109],"an":[110,149,184],"equivalent":[111],"effect":[112],"form":[115],"of":[116,160,165,187],"function.":[118],"Consequently,":[119],"no":[121],"longer":[122],"need":[123],"illustrate":[125],"function":[128],"corresponding":[129],"each":[131],"explicitly.":[134],"Instead,":[135],"obtain":[140],"prompted":[142],"downstream":[146,233],"task":[147],"adaptive":[150],"manner.":[151],"We":[152],"provide":[153],"rigorous":[154],"derivations":[155],"demonstrate":[157],"universality":[159],"make":[163],"guarantee":[164],"its":[166],"effectiveness.":[167],"The":[168],"experimental":[169],"results":[170],"various":[172],"strategies":[174],"indicate":[175],"our":[177,200,224],"performs":[179],"better":[180],"than":[181],"fine-tuning,":[182],"with":[183],"average":[185],"improvement":[186],"about":[188,194],"1.4%":[189],"full-shot":[191],"scenarios":[192],"3.2%":[195],"few-shot":[197],"scenarios.":[198],"Moreover,":[199],"significantly":[202],"outperforms":[203],"existing":[204],"when":[209],"applied":[210],"utilizing":[213],"they":[217],"specialize":[218],"in.":[219],"These":[220],"numerous":[221],"advantages":[222],"position":[223],"compelling":[228],"alternative":[229],"fine-tuning":[231],"adaptations.":[234]},"counts_by_year":[{"year":2025,"cited_by_count":5},{"year":2024,"cited_by_count":4},{"year":2023,"cited_by_count":2}],"updated_date":"2026-02-09T09:26:11.010843","created_date":"2025-10-10T00:00:00"}