{"id":"https://openalex.org/W7171943705","doi":"https://doi.org/10.1145/3770854.3780291","title":"Learning and Editing Universal Graph Prompt Tuning via Reinforcement Learning","display_name":"Learning and Editing Universal Graph Prompt Tuning via Reinforcement Learning","publication_year":2026,"publication_date":"2026-04-20","ids":{"openalex":"https://openalex.org/W7171943705","doi":"https://doi.org/10.1145/3770854.3780291"},"language":null,"primary_location":{"id":"doi:10.1145/3770854.3780291","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3770854.3780291","pdf_url":null,"source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 32nd ACM SIGKDD Conference on Knowledge Discovery and Data Mining V.1","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://doi.org/10.1145/3770854.3780291","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5009892151","display_name":"Jinfeng Xu","orcid":"https://orcid.org/0009-0001-7876-3740"},"institutions":[{"id":"https://openalex.org/I889458895","display_name":"University of Hong Kong","ror":"https://ror.org/02zhqgq86","country_code":"HK","type":"education","lineage":["https://openalex.org/I889458895"]}],"countries":["HK"],"is_corresponding":false,"raw_author_name":"Jinfeng Xu","raw_affiliation_strings":["The University of Hong Kong, Hong Kong SAR, China"],"raw_orcid":"https://orcid.org/0009-0001-7876-3740","affiliations":[{"raw_affiliation_string":"The University of Hong Kong, Hong Kong SAR, China","institution_ids":["https://openalex.org/I889458895"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101621051","display_name":"Zheyu Chen","orcid":"https://orcid.org/0009-0003-5779-3523"},"institutions":[{"id":"https://openalex.org/I125839683","display_name":"Beijing Institute of Technology","ror":"https://ror.org/01skt4w74","country_code":"CN","type":"education","lineage":["https://openalex.org/I125839683","https://openalex.org/I890469752"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zheyu Chen","raw_affiliation_strings":["Beijing Institute of Technology, Beijing, China"],"raw_orcid":"https://orcid.org/0009-0003-5779-3523","affiliations":[{"raw_affiliation_string":"Beijing Institute of Technology, Beijing, China","institution_ids":["https://openalex.org/I125839683"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101549512","display_name":"Shuo Yang","orcid":"https://orcid.org/0000-0003-1638-9623"},"institutions":[{"id":"https://openalex.org/I889458895","display_name":"University of Hong Kong","ror":"https://ror.org/02zhqgq86","country_code":"HK","type":"education","lineage":["https://openalex.org/I889458895"]}],"countries":["HK"],"is_corresponding":false,"raw_author_name":"Shuo Yang","raw_affiliation_strings":["The University of Hong Kong, Hong Kong SAR, China"],"raw_orcid":"https://orcid.org/0000-0003-1638-9623","affiliations":[{"raw_affiliation_string":"The University of Hong Kong, Hong Kong SAR, China","institution_ids":["https://openalex.org/I889458895"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5053796862","display_name":"Jinze Li","orcid":"https://orcid.org/0009-0002-6749-5442"},"institutions":[{"id":"https://openalex.org/I889458895","display_name":"University of Hong Kong","ror":"https://ror.org/02zhqgq86","country_code":"HK","type":"education","lineage":["https://openalex.org/I889458895"]}],"countries":["HK"],"is_corresponding":false,"raw_author_name":"Jinze Li","raw_affiliation_strings":["The University of Hong Kong, Hong Kong SAR, China"],"raw_orcid":"https://orcid.org/0009-0002-6749-5442","affiliations":[{"raw_affiliation_string":"The University of Hong Kong, Hong Kong SAR, China","institution_ids":["https://openalex.org/I889458895"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101836291","display_name":"Hewei Wang","orcid":"https://orcid.org/0000-0002-6952-0886"},"institutions":[{"id":"https://openalex.org/I74973139","display_name":"Carnegie Mellon University","ror":"https://ror.org/05x2bcf33","country_code":"US","type":"education","lineage":["https://openalex.org/I74973139"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Hewei Wang","raw_affiliation_strings":["Carnegie Mellon University, Pittsburgh, PA, USA"],"raw_orcid":"https://orcid.org/0000-0002-6952-0886","affiliations":[{"raw_affiliation_string":"Carnegie Mellon University, Pittsburgh, PA, USA","institution_ids":["https://openalex.org/I74973139"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5001054333","display_name":"Yijie Li","orcid":"https://orcid.org/0000-0003-2118-2280"},"institutions":[{"id":"https://openalex.org/I74973139","display_name":"Carnegie Mellon University","ror":"https://ror.org/05x2bcf33","country_code":"US","type":"education","lineage":["https://openalex.org/I74973139"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Yijie Li","raw_affiliation_strings":["Carnegie Mellon University, Pittsburgh, PA, USA"],"raw_orcid":"https://orcid.org/0000-0003-2118-2280","affiliations":[{"raw_affiliation_string":"Carnegie Mellon University, Pittsburgh, PA, USA","institution_ids":["https://openalex.org/I74973139"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5077317339","display_name":"Edith C.\u2010H. Ngai","orcid":"https://orcid.org/0000-0002-3454-8731"},"institutions":[{"id":"https://openalex.org/I889458895","display_name":"University of Hong Kong","ror":"https://ror.org/02zhqgq86","country_code":"HK","type":"education","lineage":["https://openalex.org/I889458895"]}],"countries":["HK"],"is_corresponding":false,"raw_author_name":"Edith C. H. Ngai","raw_affiliation_strings":["University of Hong Kong, Hong Kong SAR, China"],"raw_orcid":"https://orcid.org/0000-0002-3454-8731","affiliations":[{"raw_affiliation_string":"University of Hong Kong, Hong Kong SAR, China","institution_ids":["https://openalex.org/I889458895"]}]}],"institutions":[],"countries_distinct_count":3,"institutions_distinct_count":3,"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":"1673","last_page":"1682"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":null,"topics":[],"keywords":[{"id":"https://openalex.org/keywords/graph","display_name":"Graph","score":0.5446000099182129},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.5415999889373779},{"id":"https://openalex.org/keywords/universality","display_name":"Universality (dynamical systems)","score":0.49459999799728394},{"id":"https://openalex.org/keywords/feature-learning","display_name":"Feature learning","score":0.3424000144004822},{"id":"https://openalex.org/keywords/exploit","display_name":"Exploit","score":0.3246000111103058},{"id":"https://openalex.org/keywords/network-topology","display_name":"Network topology","score":0.32420000433921814},{"id":"https://openalex.org/keywords/adaptability","display_name":"Adaptability","score":0.31299999356269836}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6700000166893005},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.5730000138282776},{"id":"https://openalex.org/C132525143","wikidata":"https://www.wikidata.org/wiki/Q141488","display_name":"Graph","level":2,"score":0.5446000099182129},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.5415999889373779},{"id":"https://openalex.org/C183992945","wikidata":"https://www.wikidata.org/wiki/Q2495574","display_name":"Universality (dynamical systems)","level":2,"score":0.49459999799728394},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3806999921798706},{"id":"https://openalex.org/C59404180","wikidata":"https://www.wikidata.org/wiki/Q17013334","display_name":"Feature learning","level":2,"score":0.3424000144004822},{"id":"https://openalex.org/C165696696","wikidata":"https://www.wikidata.org/wiki/Q11287","display_name":"Exploit","level":2,"score":0.3246000111103058},{"id":"https://openalex.org/C199845137","wikidata":"https://www.wikidata.org/wiki/Q145490","display_name":"Network topology","level":2,"score":0.32420000433921814},{"id":"https://openalex.org/C177606310","wikidata":"https://www.wikidata.org/wiki/Q5674297","display_name":"Adaptability","level":2,"score":0.31299999356269836},{"id":"https://openalex.org/C195818886","wikidata":"https://www.wikidata.org/wiki/Q5421724","display_name":"Expressive power","level":2,"score":0.30320000648498535},{"id":"https://openalex.org/C558772884","wikidata":"https://www.wikidata.org/wiki/Q1508564","display_name":"Graph rewriting","level":3,"score":0.2736999988555908},{"id":"https://openalex.org/C188198153","wikidata":"https://www.wikidata.org/wiki/Q1613840","display_name":"Limiting","level":2,"score":0.26820001006126404},{"id":"https://openalex.org/C108710211","wikidata":"https://www.wikidata.org/wiki/Q11538","display_name":"Mathematical proof","level":2,"score":0.2644999921321869},{"id":"https://openalex.org/C88230418","wikidata":"https://www.wikidata.org/wiki/Q131476","display_name":"Graph theory","level":2,"score":0.2590000033378601},{"id":"https://openalex.org/C64339825","wikidata":"https://www.wikidata.org/wiki/Q722659","display_name":"Graph property","level":5,"score":0.25220000743865967},{"id":"https://openalex.org/C146380142","wikidata":"https://www.wikidata.org/wiki/Q1137726","display_name":"Directed graph","level":2,"score":0.25110000371932983}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3770854.3780291","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3770854.3780291","pdf_url":null,"source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 32nd ACM SIGKDD Conference on Knowledge Discovery and Data Mining V.1","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.1145/3770854.3780291","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3770854.3780291","pdf_url":null,"source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 32nd ACM SIGKDD Conference on Knowledge Discovery and Data Mining V.1","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":19,"referenced_works":["https://openalex.org/W3110791298","https://openalex.org/W3153673236","https://openalex.org/W3170268576","https://openalex.org/W3204453541","https://openalex.org/W4290877635","https://openalex.org/W4312651322","https://openalex.org/W4367046771","https://openalex.org/W4380303532","https://openalex.org/W4383468961","https://openalex.org/W4385270258","https://openalex.org/W4386065763","https://openalex.org/W4393148023","https://openalex.org/W4393160432","https://openalex.org/W4403160208","https://openalex.org/W4403582579","https://openalex.org/W4409365290","https://openalex.org/W4412396206","https://openalex.org/W7133193304","https://openalex.org/W7133214065"],"related_works":[],"abstract_inverted_index":{"The":[0],"''pre-training,":[1],"prompt-tuning''":[2],"has":[3,75],"emerged":[4],"as":[5],"a":[6,19,92,173,188],"pivotal":[7],"paradigm":[8,26],"in":[9,84,253],"advancing":[10],"the":[11,28,38,85,140,153,178,203,220,227],"performance":[12],"of":[13,22,30,73,106,143,156,180,206],"graph":[14,42,48,78,97,121,135,145,158,181,208,223],"representation":[15],"learning":[16,235],"models":[17,32],"across":[18,64,249],"wide":[20],"range":[21],"downstream":[23],"tasks.":[24],"This":[25],"leverages":[27],"power":[29],"pre-trained":[31],"and":[33,44,90,191,194,230,239,246,256,265],"task-specific":[34,45,54],"prompts":[35,168,224],"to":[36,124,169,225,236],"bridge":[37],"gap":[39],"between":[40],"general":[41],"representations":[43],"requirements.":[46],"Early":[47],"prompt":[49,79,98,122,136,146,159,209],"tuning":[50,99,123,137,160,210],"approaches":[51],"relied":[52],"on":[53,112,244],"designs":[55],"for":[56,176],"Graph":[57],"Neural":[58],"Networks":[59],"(GNNs),":[60],"limiting":[61],"their":[62],"adaptability":[63],"diverse":[65],"pre-training":[66,114,251],"strategies.":[67,115],"In":[68,148],"contrast,":[69],"another":[70],"promising":[71],"line":[72],"research":[74],"investigated":[76],"universal":[77,96,144,157,207,222],"tuning,":[80],"which":[81,201],"operates":[82],"directly":[83],"input":[86],"graph's":[87],"feature":[88],"space":[89],"builds":[91],"theoretical":[93,141,154,204,228],"foundation":[94,142,155,205,229],"that":[95,132,166,260],"can":[100],"theoretically":[101],"achieve":[102],"an":[103],"equivalent":[104],"effect":[105],"any":[107],"prompting":[108],"function,":[109],"eliminating":[110],"dependence":[111],"specific":[113],"Recent":[116],"works":[117],"propose":[118,187],"selective":[119,133],"node-based":[120,134],"pursue":[125],"more":[126,213],"ideal":[127,214],"prompts.":[128,182,215,241],"However,":[129],"we":[130,151,186,217],"argue":[131],"inevitably":[138],"compromises":[139],"tuning.":[147],"this":[149,184],"paper,":[150],"strengthen":[152],"by":[161],"introducing":[162],"stricter":[163],"constraints,":[164],"demonstrating":[165],"adding":[167],"all":[170],"nodes":[171,238],"is":[172],"necessary":[174],"condition":[175],"achieving":[177],"universality":[179],"To":[183],"end,":[185],"novel":[189],"model":[190],"paradigm,":[192],"Learning":[193],"Editing":[195],"Universal":[196],"GrAph":[197],"Prompt":[198],"Tuning":[199],"(LEAP),":[200],"preserves":[202],"while":[211],"pursuing":[212],"Specifically,":[216],"first":[218],"build":[219],"basic":[221],"preserve":[226],"then":[231],"employ":[232],"actor-critic":[233],"reinforcement":[234],"select":[237],"edit":[240],"Extensive":[242],"experiments":[243],"graph-":[245],"node-level":[247],"tasks":[248],"various":[250],"strategies":[252],"both":[254],"full-shot":[255],"few-shot":[257],"scenarios":[258],"show":[259],"LEAP":[261],"consistently":[262],"outperforms":[263],"fine-tuning":[264],"other":[266],"prompt-based":[267],"approaches.":[268]},"counts_by_year":[],"updated_date":"2026-08-01T09:00:35.917206","created_date":"2026-08-01T00:00:00"}