{"id":"https://openalex.org/W3080997787","doi":"https://doi.org/10.1145/3394486.3403237","title":"GPT-GNN","display_name":"GPT-GNN","publication_year":2020,"publication_date":"2020-08-20","ids":{"openalex":"https://openalex.org/W3080997787","doi":"https://doi.org/10.1145/3394486.3403237","mag":"3080997787"},"language":"en","primary_location":{"id":"doi:10.1145/3394486.3403237","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3394486.3403237","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3394486.3403237","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 26th ACM SIGKDD International Conference on Knowledge Discovery & Data Mining","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://dl.acm.org/doi/pdf/10.1145/3394486.3403237","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5114973490","display_name":"Ziniu Hu","orcid":"https://orcid.org/0000-0003-4663-0166"},"institutions":[{"id":"https://openalex.org/I161318765","display_name":"University of California, Los Angeles","ror":"https://ror.org/046rm7j60","country_code":"US","type":"education","lineage":["https://openalex.org/I161318765"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Ziniu Hu","raw_affiliation_strings":["University of California, Los Angeles, Los Angeles, CA, USA"],"affiliations":[{"raw_affiliation_string":"University of California, Los Angeles, Los Angeles, CA, USA","institution_ids":["https://openalex.org/I161318765"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5052284218","display_name":"Yuxiao Dong","orcid":"https://orcid.org/0000-0002-6092-2002"},"institutions":[{"id":"https://openalex.org/I1290206253","display_name":"Microsoft (United States)","ror":"https://ror.org/00d0nc645","country_code":"US","type":"company","lineage":["https://openalex.org/I1290206253"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Yuxiao Dong","raw_affiliation_strings":["Microsoft Research, Redmond, WA, USA"],"affiliations":[{"raw_affiliation_string":"Microsoft Research, Redmond, WA, USA","institution_ids":["https://openalex.org/I1290206253"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5041659067","display_name":"Kuansan Wang","orcid":"https://orcid.org/0000-0001-7089-7966"},"institutions":[{"id":"https://openalex.org/I1290206253","display_name":"Microsoft (United States)","ror":"https://ror.org/00d0nc645","country_code":"US","type":"company","lineage":["https://openalex.org/I1290206253"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Kuansan Wang","raw_affiliation_strings":["Microsoft Research, Redmond, WA, USA"],"affiliations":[{"raw_affiliation_string":"Microsoft Research, Redmond, WA, USA","institution_ids":["https://openalex.org/I1290206253"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5087096372","display_name":"Kai-Wei Chang","orcid":"https://orcid.org/0000-0001-5365-0072"},"institutions":[{"id":"https://openalex.org/I161318765","display_name":"University of California, Los Angeles","ror":"https://ror.org/046rm7j60","country_code":"US","type":"education","lineage":["https://openalex.org/I161318765"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Kai-Wei Chang","raw_affiliation_strings":["University of California, Los Angeles, Los Angeles, CA, USA"],"affiliations":[{"raw_affiliation_string":"University of California, Los Angeles, Los Angeles, CA, USA","institution_ids":["https://openalex.org/I161318765"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5025213473","display_name":"Yizhou Sun","orcid":"https://orcid.org/0000-0003-1812-6843"},"institutions":[{"id":"https://openalex.org/I161318765","display_name":"University of California, Los Angeles","ror":"https://ror.org/046rm7j60","country_code":"US","type":"education","lineage":["https://openalex.org/I161318765"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Yizhou Sun","raw_affiliation_strings":["University of California, Los Angeles, Los Angeles, CA, USA"],"affiliations":[{"raw_affiliation_string":"University of California, Los Angeles, Los Angeles, CA, USA","institution_ids":["https://openalex.org/I161318765"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5114973490"],"corresponding_institution_ids":["https://openalex.org/I161318765"],"apc_list":null,"apc_paid":null,"fwci":30.0425,"has_fulltext":true,"cited_by_count":432,"citation_normalized_percentile":{"value":0.99743517,"is_in_top_1_percent":true,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":99,"max":100},"biblio":{"volume":null,"issue":null,"first_page":"1857","last_page":"1867"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11273","display_name":"Advanced Graph Neural Networks","score":0.9998999834060669,"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":0.9998999834060669,"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":0.9983999729156494,"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/T10203","display_name":"Recommender Systems and Techniques","score":0.9882000088691711,"subfield":{"id":"https://openalex.org/subfields/1710","display_name":"Information Systems"},"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":0.7794771194458008},{"id":"https://openalex.org/keywords/graph","display_name":"Graph","score":0.5954484343528748},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.5045987367630005},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4972589313983917},{"id":"https://openalex.org/keywords/generative-model","display_name":"Generative model","score":0.46857950091362},{"id":"https://openalex.org/keywords/generative-grammar","display_name":"Generative grammar","score":0.44517266750335693},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.4318326711654663},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.37381553649902344},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.3406824767589569},{"id":"https://openalex.org/keywords/theoretical-computer-science","display_name":"Theoretical computer science","score":0.2240837812423706}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7794771194458008},{"id":"https://openalex.org/C132525143","wikidata":"https://www.wikidata.org/wiki/Q141488","display_name":"Graph","level":2,"score":0.5954484343528748},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.5045987367630005},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4972589313983917},{"id":"https://openalex.org/C167966045","wikidata":"https://www.wikidata.org/wiki/Q5532625","display_name":"Generative model","level":3,"score":0.46857950091362},{"id":"https://openalex.org/C39890363","wikidata":"https://www.wikidata.org/wiki/Q36108","display_name":"Generative grammar","level":2,"score":0.44517266750335693},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.4318326711654663},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.37381553649902344},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3406824767589569},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.2240837812423706},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0},{"id":"https://openalex.org/C187736073","wikidata":"https://www.wikidata.org/wiki/Q2920921","display_name":"Management","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3394486.3403237","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3394486.3403237","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3394486.3403237","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 26th ACM SIGKDD International Conference on Knowledge Discovery & Data Mining","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.1145/3394486.3403237","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3394486.3403237","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3394486.3403237","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 26th ACM SIGKDD International Conference on Knowledge Discovery & Data Mining","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G1171700966","display_name":null,"funder_award_id":"NSF CAREER","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G1600646250","display_name":"HDR DSC: Collaborative Research: The Data Science WAV: Experiential Learning with Local Community Organizations","funder_award_id":"1924032","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G4291750258","display_name":null,"funder_award_id":"1741634","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G4396638795","display_name":null,"funder_award_id":"III-1705169","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G6671297155","display_name":null,"funder_award_id":"CAREER","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G7851417135","display_name":"III: Medium: Collaborative Research: StructNet: Constructing and Mining Structure-Rich Information Networks for Scientific Research","funder_award_id":"1705169","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G7868173616","display_name":null,"funder_award_id":"HR00112090027","funder_id":"https://openalex.org/F4320332180","funder_display_name":"Defense Advanced Research Projects Agency"},{"id":"https://openalex.org/G8700651539","display_name":null,"funder_award_id":"N6600119240","funder_id":"https://openalex.org/F4320332180","funder_display_name":"Defense Advanced Research Projects Agency"},{"id":"https://openalex.org/G8823166825","display_name":null,"funder_award_id":"DARPA HR00112090027","funder_id":"https://openalex.org/F4320332180","funder_display_name":"Defense Advanced Research Projects Agency"}],"funders":[{"id":"https://openalex.org/F4320306076","display_name":"National Science Foundation","ror":"https://ror.org/021nxhr62"},{"id":"https://openalex.org/F4320332180","display_name":"Defense Advanced Research Projects Agency","ror":"https://ror.org/02caytj08"}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W3080997787.pdf","grobid_xml":"https://content.openalex.org/works/W3080997787.grobid-xml"},"referenced_works_count":46,"referenced_works":["https://openalex.org/W103340358","https://openalex.org/W1662382123","https://openalex.org/W1888005072","https://openalex.org/W1973435495","https://openalex.org/W1975563293","https://openalex.org/W2022322548","https://openalex.org/W2098711168","https://openalex.org/W2102605133","https://openalex.org/W2108598243","https://openalex.org/W2155541015","https://openalex.org/W2250539671","https://openalex.org/W2342877626","https://openalex.org/W2518108298","https://openalex.org/W2519887557","https://openalex.org/W2554952599","https://openalex.org/W2604314403","https://openalex.org/W2624431344","https://openalex.org/W2743104969","https://openalex.org/W2842511635","https://openalex.org/W2893944917","https://openalex.org/W2896457183","https://openalex.org/W2908510526","https://openalex.org/W2911286998","https://openalex.org/W2950133940","https://openalex.org/W2950813464","https://openalex.org/W2951101948","https://openalex.org/W2952205826","https://openalex.org/W2952254971","https://openalex.org/W2962756421","https://openalex.org/W2963858333","https://openalex.org/W2970090796","https://openalex.org/W2971196067","https://openalex.org/W2978498781","https://openalex.org/W2979826702","https://openalex.org/W2987283559","https://openalex.org/W2994710732","https://openalex.org/W2996604169","https://openalex.org/W3002924435","https://openalex.org/W3005680577","https://openalex.org/W3010021337","https://openalex.org/W3042085764","https://openalex.org/W3100848837","https://openalex.org/W3103995645","https://openalex.org/W3105705953","https://openalex.org/W4291474301","https://openalex.org/W6603321306"],"related_works":["https://openalex.org/W4385572368","https://openalex.org/W1534961803","https://openalex.org/W2310403681","https://openalex.org/W2952072295","https://openalex.org/W4289760695","https://openalex.org/W2874782909","https://openalex.org/W4379924457","https://openalex.org/W4385374140","https://openalex.org/W4287126800","https://openalex.org/W4226510483"],"abstract_inverted_index":{"Graph":[0],"neural":[1],"networks":[2],"(GNNs)":[3],"have":[4],"been":[5],"demonstrated":[6],"to":[7,27,32,38,55,71,85,162],"be":[8],"powerful":[9],"in":[10],"modeling":[11,120],"graph-structured":[12],"data.":[13],"However,":[14],"training":[15],"GNNs":[16,73],"requires":[17],"abundant":[18],"task-specific":[19],"labeled":[20],"data,":[21],"which":[22],"is":[23,37],"often":[24],"arduously":[25],"expensive":[26],"obtain.":[28],"One":[29],"effective":[30],"way":[31],"reduce":[33],"the":[34,52,68,94,100,104,125,135,141],"labeling":[35],"effort":[36],"pre-train":[39,86],"an":[40],"expressive":[41],"GNN":[42,88,156],"model":[43,54],"on":[44,140],"unlabelled":[45],"data":[46,149],"with":[47,58],"self-supervision":[48],"and":[49,96,115,131,146],"then":[50],"transfer":[51],"learned":[53],"downstream":[56,166],"tasks":[57],"only":[59],"a":[60,79,87],"few":[61],"labels.":[62],"In":[63],"this":[64],"paper,":[65],"we":[66],"present":[67],"GPT-GNN":[69,77,123,152],"framework":[70],"initialize":[72],"by":[74,160],"generative":[75,136],"pre-training.":[76],"introduces":[78],"self-supervised":[80],"attributed":[81],"graph":[82,107,132,145],"generation":[83,108,114],"task":[84],"so":[89],"that":[90,151],"it":[91],"can":[92],"capture":[93],"structural":[95],"semantic":[97],"properties":[98],"of":[99,106],"graph.":[101],"We":[102],"factorize":[103],"likelihood":[105],"into":[109],"two":[110],"components:":[111],"1)":[112],"attribute":[113],"2)":[116],"edge":[117],"generation.":[118],"By":[119],"both":[121],"components,":[122],"captures":[124],"inherent":[126],"dependency":[127],"between":[128],"node":[129],"attributes":[130],"structure":[133],"during":[134],"process.":[137],"Comprehensive":[138],"experiments":[139],"billion-scale":[142],"open":[143],"academic":[144],"Amazon":[147],"recommendation":[148],"demonstrate":[150],"significantly":[153],"outperforms":[154],"state-of-the-art":[155],"models":[157],"without":[158],"pre-training":[159],"up":[161],"9.1%":[163],"across":[164],"various":[165],"tasks?":[167]},"counts_by_year":[{"year":2026,"cited_by_count":8},{"year":2025,"cited_by_count":90},{"year":2024,"cited_by_count":113},{"year":2023,"cited_by_count":74},{"year":2022,"cited_by_count":60},{"year":2021,"cited_by_count":76},{"year":2020,"cited_by_count":11}],"updated_date":"2026-04-10T15:06:20.359241","created_date":"2020-09-01T00:00:00"}