{"id":"https://openalex.org/W4385567591","doi":"https://doi.org/10.1145/3580305.3599548","title":"When to Pre-Train Graph Neural Networks? From Data Generation Perspective!","display_name":"When to Pre-Train Graph Neural Networks? From Data Generation Perspective!","publication_year":2023,"publication_date":"2023-08-04","ids":{"openalex":"https://openalex.org/W4385567591","doi":"https://doi.org/10.1145/3580305.3599548","pmid":"https://pubmed.ncbi.nlm.nih.gov/38333106"},"language":"en","primary_location":{"id":"doi:10.1145/3580305.3599548","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3580305.3599548","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 29th ACM SIGKDD Conference on Knowledge Discovery and Data Mining","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref","pubmed"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://pmc.ncbi.nlm.nih.gov/articles/PMC10853019/pdf/nihms-1964220.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5074179471","display_name":"Yuxuan Cao","orcid":"https://orcid.org/0009-0000-2867-8938"},"institutions":[{"id":"https://openalex.org/I24943067","display_name":"Fudan University","ror":"https://ror.org/013q1eq08","country_code":"CN","type":"education","lineage":["https://openalex.org/I24943067"]},{"id":"https://openalex.org/I76130692","display_name":"Zhejiang University","ror":"https://ror.org/00a2xv884","country_code":"CN","type":"education","lineage":["https://openalex.org/I76130692"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Yuxuan Cao","raw_affiliation_strings":["Zhejiang University &amp; Fudan University, Hangzhou, China"],"affiliations":[{"raw_affiliation_string":"Zhejiang University &amp; Fudan University, Hangzhou, China","institution_ids":["https://openalex.org/I76130692","https://openalex.org/I24943067"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5076289391","display_name":"Jiarong Xu","orcid":"https://orcid.org/0000-0003-2973-1889"},"institutions":[{"id":"https://openalex.org/I24943067","display_name":"Fudan University","ror":"https://ror.org/013q1eq08","country_code":"CN","type":"education","lineage":["https://openalex.org/I24943067"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jiarong Xu","raw_affiliation_strings":["Fudan University, Shanghai, China"],"affiliations":[{"raw_affiliation_string":"Fudan University, Shanghai, China","institution_ids":["https://openalex.org/I24943067"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5006897094","display_name":"Carl Yang","orcid":"https://orcid.org/0000-0001-9145-4531"},"institutions":[{"id":"https://openalex.org/I150468666","display_name":"Emory University","ror":"https://ror.org/03czfpz43","country_code":"US","type":"education","lineage":["https://openalex.org/I150468666"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Carl Yang","raw_affiliation_strings":["Emory University, Atlanta, GA, USA"],"affiliations":[{"raw_affiliation_string":"Emory University, Atlanta, GA, USA","institution_ids":["https://openalex.org/I150468666"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5062115445","display_name":"Jiaan Wang","orcid":"https://orcid.org/0000-0002-2587-7648"},"institutions":[{"id":"https://openalex.org/I3923682","display_name":"Soochow University","ror":"https://ror.org/05t8y2r12","country_code":"CN","type":"education","lineage":["https://openalex.org/I3923682"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jiaan Wang","raw_affiliation_strings":["Soochow University, Suzhou, China"],"affiliations":[{"raw_affiliation_string":"Soochow University, Suzhou, China","institution_ids":["https://openalex.org/I3923682"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102879629","display_name":"Yunchao Zhang","orcid":"https://orcid.org/0000-0002-3226-5324"},"institutions":[{"id":"https://openalex.org/I76130692","display_name":"Zhejiang University","ror":"https://ror.org/00a2xv884","country_code":"CN","type":"education","lineage":["https://openalex.org/I76130692"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yunchao Zhang","raw_affiliation_strings":["Zhejiang University, Hangzhou, China"],"affiliations":[{"raw_affiliation_string":"Zhejiang University, Hangzhou, China","institution_ids":["https://openalex.org/I76130692"]}]},{"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":"Chunping Wang","raw_affiliation_strings":["Finvolution Group, Shanghai, China"],"affiliations":[{"raw_affiliation_string":"Finvolution Group, Shanghai, China","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5064062823","display_name":"Lei Chen","orcid":"https://orcid.org/0000-0002-4912-3293"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Lei CHEN","raw_affiliation_strings":["Finvolution Group, Shanghai, China"],"affiliations":[{"raw_affiliation_string":"Finvolution Group, Shanghai, China","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5035227503","display_name":"Yang Yang","orcid":"https://orcid.org/0000-0002-5058-4417"},"institutions":[{"id":"https://openalex.org/I76130692","display_name":"Zhejiang University","ror":"https://ror.org/00a2xv884","country_code":"CN","type":"education","lineage":["https://openalex.org/I76130692"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yang Yang","raw_affiliation_strings":["Zhejiang University, Hangzhou, China"],"affiliations":[{"raw_affiliation_string":"Zhejiang University, Hangzhou, China","institution_ids":["https://openalex.org/I76130692"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":8,"corresponding_author_ids":["https://openalex.org/A5074179471"],"corresponding_institution_ids":["https://openalex.org/I24943067","https://openalex.org/I76130692"],"apc_list":null,"apc_paid":null,"fwci":2.9254,"has_fulltext":true,"cited_by_count":17,"citation_normalized_percentile":{"value":0.92691238,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":90,"max":99},"biblio":{"volume":"2023","issue":null,"first_page":"142","last_page":"153"},"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":0.9833999872207642,"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":0.9821000099182129,"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/computer-science","display_name":"Computer science","score":0.7790879011154175},{"id":"https://openalex.org/keywords/graph","display_name":"Graph","score":0.5738614797592163},{"id":"https://openalex.org/keywords/generator","display_name":"Generator (circuit theory)","score":0.5370819568634033},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.5315157175064087},{"id":"https://openalex.org/keywords/downstream","display_name":"Downstream (manufacturing)","score":0.5173563361167908},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.47802433371543884},{"id":"https://openalex.org/keywords/training-set","display_name":"Training set","score":0.47111108899116516},{"id":"https://openalex.org/keywords/generative-grammar","display_name":"Generative grammar","score":0.46355903148651123},{"id":"https://openalex.org/keywords/perspective","display_name":"Perspective (graphical)","score":0.42263075709342957},{"id":"https://openalex.org/keywords/theoretical-computer-science","display_name":"Theoretical computer science","score":0.35901379585266113},{"id":"https://openalex.org/keywords/data-science","display_name":"Data science","score":0.34776771068573},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.345139741897583},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.07868671417236328}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7790879011154175},{"id":"https://openalex.org/C132525143","wikidata":"https://www.wikidata.org/wiki/Q141488","display_name":"Graph","level":2,"score":0.5738614797592163},{"id":"https://openalex.org/C2780992000","wikidata":"https://www.wikidata.org/wiki/Q17016113","display_name":"Generator (circuit theory)","level":3,"score":0.5370819568634033},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.5315157175064087},{"id":"https://openalex.org/C2776207758","wikidata":"https://www.wikidata.org/wiki/Q5303302","display_name":"Downstream (manufacturing)","level":2,"score":0.5173563361167908},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.47802433371543884},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.47111108899116516},{"id":"https://openalex.org/C39890363","wikidata":"https://www.wikidata.org/wiki/Q36108","display_name":"Generative grammar","level":2,"score":0.46355903148651123},{"id":"https://openalex.org/C12713177","wikidata":"https://www.wikidata.org/wiki/Q1900281","display_name":"Perspective (graphical)","level":2,"score":0.42263075709342957},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.35901379585266113},{"id":"https://openalex.org/C2522767166","wikidata":"https://www.wikidata.org/wiki/Q2374463","display_name":"Data science","level":1,"score":0.34776771068573},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.345139741897583},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.07868671417236328},{"id":"https://openalex.org/C163258240","wikidata":"https://www.wikidata.org/wiki/Q25342","display_name":"Power (physics)","level":2,"score":0.0},{"id":"https://openalex.org/C21547014","wikidata":"https://www.wikidata.org/wiki/Q1423657","display_name":"Operations management","level":1,"score":0.0},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1145/3580305.3599548","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3580305.3599548","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 29th ACM SIGKDD Conference on Knowledge Discovery and Data Mining","raw_type":"proceedings-article"},{"id":"pmid:38333106","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/38333106","pdf_url":null,"source":{"id":"https://openalex.org/S4306525036","display_name":"PubMed","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1299303238","host_organization_name":"National Institutes of Health","host_organization_lineage":["https://openalex.org/I1299303238"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"KDD : proceedings. International Conference on Knowledge Discovery & Data Mining","raw_type":null},{"id":"pmh:oai:pubmedcentral.nih.gov:10853019","is_oa":true,"landing_page_url":"https://www.ncbi.nlm.nih.gov/pmc/articles/10853019","pdf_url":"https://pmc.ncbi.nlm.nih.gov/articles/PMC10853019/pdf/nihms-1964220.pdf","source":{"id":"https://openalex.org/S2764455111","display_name":"PubMed Central","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1299303238","host_organization_name":"National Institutes of Health","host_organization_lineage":["https://openalex.org/I1299303238"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"KDD","raw_type":"Text"}],"best_oa_location":{"id":"pmh:oai:pubmedcentral.nih.gov:10853019","is_oa":true,"landing_page_url":"https://www.ncbi.nlm.nih.gov/pmc/articles/10853019","pdf_url":"https://pmc.ncbi.nlm.nih.gov/articles/PMC10853019/pdf/nihms-1964220.pdf","source":{"id":"https://openalex.org/S2764455111","display_name":"PubMed Central","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1299303238","host_organization_name":"National Institutes of Health","host_organization_lineage":["https://openalex.org/I1299303238"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"KDD","raw_type":"Text"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G2087396116","display_name":null,"funder_award_id":"China","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G2376276132","display_name":null,"funder_award_id":"China","funder_id":"https://openalex.org/F4320335787","funder_display_name":"Fundamental Research Funds for the Central Universities"},{"id":"https://openalex.org/G391238517","display_name":null,"funder_award_id":", and","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G4020255992","display_name":null,"funder_award_id":"Project","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G5087339601","display_name":null,"funder_award_id":"01019","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"}],"funders":[{"id":"https://openalex.org/F4320306076","display_name":"National Science Foundation","ror":"https://ror.org/021nxhr62"},{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"},{"id":"https://openalex.org/F4320335787","display_name":"Fundamental Research Funds for the Central Universities","ror":null}],"has_content":{"grobid_xml":false,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4385567591.pdf"},"referenced_works_count":35,"referenced_works":["https://openalex.org/W273178449","https://openalex.org/W950821216","https://openalex.org/W1757990252","https://openalex.org/W1888005072","https://openalex.org/W2033193852","https://openalex.org/W2058357179","https://openalex.org/W2082734581","https://openalex.org/W2153624566","https://openalex.org/W2154851992","https://openalex.org/W2594183968","https://openalex.org/W2737925311","https://openalex.org/W2792234394","https://openalex.org/W2962756421","https://openalex.org/W2963723689","https://openalex.org/W2966694634","https://openalex.org/W2990908872","https://openalex.org/W2998269939","https://openalex.org/W3034792570","https://openalex.org/W3035065454","https://openalex.org/W3035739162","https://openalex.org/W3036446966","https://openalex.org/W3095602948","https://openalex.org/W3099152386","https://openalex.org/W3102794461","https://openalex.org/W3104097132","https://openalex.org/W3105561612","https://openalex.org/W3106006733","https://openalex.org/W3195415198","https://openalex.org/W3203495984","https://openalex.org/W3213940558","https://openalex.org/W4210958102","https://openalex.org/W4285600341","https://openalex.org/W4290874890","https://openalex.org/W4290876361","https://openalex.org/W6784694379"],"related_works":["https://openalex.org/W1583765404","https://openalex.org/W4214653257","https://openalex.org/W2380075625","https://openalex.org/W2055438207","https://openalex.org/W2521424917","https://openalex.org/W3040203686","https://openalex.org/W4249524554","https://openalex.org/W2349021146","https://openalex.org/W3005996785","https://openalex.org/W4386984417"],"abstract_inverted_index":{"In":[0,139,199],"recent":[1,24],"years,":[2],"graph":[3,16,37,64,112,234],"pre-training":[4,65,117,134,145,168,205,246],"has":[5],"gained":[6],"significant":[7],"attention,":[8],"focusing":[9],"on":[10,48],"acquiring":[11],"transferable":[12,161],"knowledge":[13],"from":[14,122,132,182,197,217],"unlabeled":[15],"data":[17,135,146,193,216,247],"to":[18,40,53,57,83,94,101,126,136,178,248],"improve":[19],"downstream":[20,41,137,192,215,250],"performance.":[21,251],"Despite":[22],"these":[23],"endeavors,":[25],"the":[26,49,75,96,128,133,144,187,202,210,214,221,230,238,259,267],"problem":[27],"of":[28,51,63,99,111,152,167,173,204,213,233,240],"negative":[29],"transfer":[30],"remains":[31],"a":[32,61,90,123,156,159,165,179,254],"major":[33],"concern":[34],"when":[35],"utilizing":[36],"pre-trained":[38,235],"models":[39],"tasks.":[42],"Previous":[43],"studies":[44],"made":[45],"great":[46],"efforts":[47],"issue":[50],"<i>what":[52],"pre-train</i>":[54,58,102],"and":[55,66,79,242,262],"<i>how":[56],"by":[59,164],"designing":[60],"variety":[62],"fine-tuning":[67],"strategies.":[68],"However,":[69],"there":[70],"are":[71],"cases":[72],"where":[73],"even":[74],"most":[76],"advanced":[77],"\"pre-train":[78],"fine-tune\"":[80],"paradigms":[81],"fail":[82],"yield":[84],"distinct":[85],"benefits.":[86],"This":[87],"paper":[88],"introduces":[89],"generic":[91],"framework":[92],"W2PGNN":[93,141,224],"answer":[95],"crucial":[97],"question":[98],"<i>when":[100],"(<i>i.e</i>.,":[103,155],"in":[104,220,244],"what":[105],"situations":[106],"could":[107],"we":[108],"take":[109],"advantage":[110],"pre-training)":[113],"before":[114],"performing":[115],"effortful":[116],"or":[118],"fine-tuning.":[119],"We":[120,252],"start":[121],"new":[124],"perspective":[125],"explore":[127],"complex":[129],"generative":[130],"mechanisms":[131],"data.":[138],"particular,":[140],"first":[142,260],"fits":[143],"into":[147],"graphon":[148,153,174],"bases,":[149],"each":[150],"element":[151],"basis":[154],"graphon)":[157],"identifies":[158],"fundamental":[160],"pattern":[162],"shared":[163],"collection":[166],"graphs.":[169],"All":[170],"convex":[171],"combinations":[172],"bases":[175],"give":[176],"rise":[177],"generator":[180,219,222],"space,":[181],"which":[183],"graphs":[184],"generated":[185],"form":[186],"solution":[188,257],"space":[189],"for":[190,258,266],"those":[191],"that":[194],"can":[195,206],"benefit":[196],"pre-training.":[198],"this":[200],"manner,":[201],"feasibility":[203,239],"be":[207],"quantified":[208],"as":[209],"generation":[211],"probability":[212],"any":[218],"space.":[223],"offers":[225],"three":[226],"broad":[227],"applications:":[228],"providing":[229],"application":[231,261],"scope":[232],"models,":[236],"quantifying":[237],"pre-training,":[241],"assistance":[243],"selecting":[245],"enhance":[249],"provide":[253],"theoretically":[255],"sound":[256],"extensive":[263],"empirical":[264],"justifications":[265],"latter":[268],"two":[269],"applications.":[270]},"counts_by_year":[{"year":2025,"cited_by_count":10},{"year":2024,"cited_by_count":6},{"year":2023,"cited_by_count":1}],"updated_date":"2026-04-15T08:11:43.952461","created_date":"2025-10-10T00:00:00"}