{"id":"https://openalex.org/W4412875519","doi":"https://doi.org/10.1145/3711896.3736833","title":"Advancing Graph Foundation Models: A Data-Centric Perspective","display_name":"Advancing Graph Foundation Models: A Data-Centric Perspective","publication_year":2025,"publication_date":"2025-08-03","ids":{"openalex":"https://openalex.org/W4412875519","doi":"https://doi.org/10.1145/3711896.3736833"},"language":"en","primary_location":{"id":"doi:10.1145/3711896.3736833","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3711896.3736833","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3711896.3736833","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 31st ACM SIGKDD Conference on Knowledge Discovery and Data Mining V.2","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/10.1145/3711896.3736833","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5100332402","display_name":"Yuhan Li","orcid":"https://orcid.org/0000-0003-1324-5819"},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Yuhan Li","raw_affiliation_strings":["HKUST (GZ), Guangzhou, China"],"affiliations":[{"raw_affiliation_string":"HKUST (GZ), Guangzhou, China","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5069691746","display_name":"Y.X. Wang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yuyao Wang","raw_affiliation_strings":["HKUST (GZ), Guangzhou, China"],"affiliations":[{"raw_affiliation_string":"HKUST (GZ), Guangzhou, China","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101551804","display_name":"Jianheng Tang","orcid":"https://orcid.org/0000-0001-9341-7312"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Jianheng Tang","raw_affiliation_strings":["HKUST (GZ), Guangzhou, China"],"affiliations":[{"raw_affiliation_string":"HKUST (GZ), Guangzhou, China","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5027050251","display_name":"Heng Chang","orcid":"https://orcid.org/0000-0002-4978-8041"},"institutions":[{"id":"https://openalex.org/I2250955327","display_name":"Huawei Technologies (China)","ror":"https://ror.org/00cmhce21","country_code":"CN","type":"company","lineage":["https://openalex.org/I2250955327"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Heng Chang","raw_affiliation_strings":["Huawei Technologies Co., Ltd., Beijing, China"],"affiliations":[{"raw_affiliation_string":"Huawei Technologies Co., Ltd., Beijing, China","institution_ids":["https://openalex.org/I2250955327"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5057157471","display_name":"Yuxiang Ren","orcid":"https://orcid.org/0000-0001-8829-3984"},"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"]},{"id":"https://openalex.org/I881766915","display_name":"Nanjing University","ror":"https://ror.org/01rxvg760","country_code":"CN","type":"education","lineage":["https://openalex.org/I881766915"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yuxiang Ren","raw_affiliation_strings":["Nanjing University, Suzhou, China"],"affiliations":[{"raw_affiliation_string":"Nanjing University, Suzhou, China","institution_ids":["https://openalex.org/I3923682","https://openalex.org/I881766915"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100405697","display_name":"Jia Li","orcid":"https://orcid.org/0000-0002-6362-4385"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Jia Li","raw_affiliation_strings":["HKUST (GZ), Guangzhou, China"],"affiliations":[{"raw_affiliation_string":"HKUST (GZ), Guangzhou, China","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":6,"corresponding_author_ids":["https://openalex.org/A5100332402"],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":{"value":0.09303825,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1635","last_page":"1646"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11273","display_name":"Advanced Graph Neural Networks","score":0.9997000098228455,"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":0.9997000098228455,"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":0.9944999814033508,"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"}},{"id":"https://openalex.org/T10538","display_name":"Data Mining Algorithms and Applications","score":0.9908000230789185,"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":0.6731516122817993},{"id":"https://openalex.org/keywords/foundation","display_name":"Foundation (evidence)","score":0.5884968042373657},{"id":"https://openalex.org/keywords/perspective","display_name":"Perspective (graphical)","score":0.567740261554718},{"id":"https://openalex.org/keywords/graph","display_name":"Graph","score":0.46690207719802856},{"id":"https://openalex.org/keywords/data-science","display_name":"Data science","score":0.45960545539855957},{"id":"https://openalex.org/keywords/graph-theory","display_name":"Graph theory","score":0.4384550452232361},{"id":"https://openalex.org/keywords/data-modeling","display_name":"Data modeling","score":0.43842005729675293},{"id":"https://openalex.org/keywords/theoretical-computer-science","display_name":"Theoretical computer science","score":0.3085600733757019},{"id":"https://openalex.org/keywords/software-engineering","display_name":"Software engineering","score":0.23345351219177246},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.18987366557121277},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.1010880172252655},{"id":"https://openalex.org/keywords/political-science","display_name":"Political science","score":0.07016968727111816}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6731516122817993},{"id":"https://openalex.org/C2780966255","wikidata":"https://www.wikidata.org/wiki/Q5474306","display_name":"Foundation (evidence)","level":2,"score":0.5884968042373657},{"id":"https://openalex.org/C12713177","wikidata":"https://www.wikidata.org/wiki/Q1900281","display_name":"Perspective (graphical)","level":2,"score":0.567740261554718},{"id":"https://openalex.org/C132525143","wikidata":"https://www.wikidata.org/wiki/Q141488","display_name":"Graph","level":2,"score":0.46690207719802856},{"id":"https://openalex.org/C2522767166","wikidata":"https://www.wikidata.org/wiki/Q2374463","display_name":"Data science","level":1,"score":0.45960545539855957},{"id":"https://openalex.org/C88230418","wikidata":"https://www.wikidata.org/wiki/Q131476","display_name":"Graph theory","level":2,"score":0.4384550452232361},{"id":"https://openalex.org/C67186912","wikidata":"https://www.wikidata.org/wiki/Q367664","display_name":"Data modeling","level":2,"score":0.43842005729675293},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.3085600733757019},{"id":"https://openalex.org/C115903868","wikidata":"https://www.wikidata.org/wiki/Q80993","display_name":"Software engineering","level":1,"score":0.23345351219177246},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.18987366557121277},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.1010880172252655},{"id":"https://openalex.org/C17744445","wikidata":"https://www.wikidata.org/wiki/Q36442","display_name":"Political science","level":0,"score":0.07016968727111816},{"id":"https://openalex.org/C114614502","wikidata":"https://www.wikidata.org/wiki/Q76592","display_name":"Combinatorics","level":1,"score":0.0},{"id":"https://openalex.org/C199539241","wikidata":"https://www.wikidata.org/wiki/Q7748","display_name":"Law","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1145/3711896.3736833","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3711896.3736833","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3711896.3736833","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 31st ACM SIGKDD Conference on Knowledge Discovery and Data Mining V.2","raw_type":"proceedings-article"},{"id":"pmh:oai:repository.hkust.edu.hk:1783.1-165818","is_oa":false,"landing_page_url":"http://repository.hkust.edu.hk/ir/Record/1783.1-165818","pdf_url":null,"source":{"id":"https://openalex.org/S4306401796","display_name":"Rare & Special e-Zone (The Hong Kong University of Science and Technology)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I200769079","host_organization_name":"Hong Kong University of Science and Technology","host_organization_lineage":["https://openalex.org/I200769079"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Conference paper"}],"best_oa_location":{"id":"doi:10.1145/3711896.3736833","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3711896.3736833","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3711896.3736833","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 31st ACM SIGKDD Conference on Knowledge Discovery and Data Mining V.2","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G1402809924","display_name":null,"funder_award_id":"2023YFF0725100","funder_id":"https://openalex.org/F4320335777","funder_display_name":"National Key Research and Development Program of China"}],"funders":[{"id":"https://openalex.org/F4320335777","display_name":"National Key Research and Development Program of China","ror":null}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4412875519.pdf","grobid_xml":"https://content.openalex.org/works/W4412875519.grobid-xml"},"referenced_works_count":54,"referenced_works":["https://openalex.org/W2055935910","https://openalex.org/W2131904035","https://openalex.org/W2142498761","https://openalex.org/W2168190036","https://openalex.org/W2803697594","https://openalex.org/W2970641574","https://openalex.org/W2990138404","https://openalex.org/W3012577990","https://openalex.org/W3026160437","https://openalex.org/W3032942478","https://openalex.org/W3033780210","https://openalex.org/W3034251946","https://openalex.org/W3080281801","https://openalex.org/W3081203761","https://openalex.org/W3092835783","https://openalex.org/W3095809828","https://openalex.org/W3110072028","https://openalex.org/W3113682753","https://openalex.org/W3155886566","https://openalex.org/W3180672483","https://openalex.org/W3186377753","https://openalex.org/W4206648492","https://openalex.org/W4224952733","https://openalex.org/W4226271719","https://openalex.org/W4287105380","https://openalex.org/W4288335875","https://openalex.org/W4318812488","https://openalex.org/W4321851522","https://openalex.org/W4367046867","https://openalex.org/W4367046880","https://openalex.org/W4383468961","https://openalex.org/W4385562584","https://openalex.org/W4385567591","https://openalex.org/W4386083062","https://openalex.org/W4387757693","https://openalex.org/W4388329034","https://openalex.org/W4391901119","https://openalex.org/W4393159476","https://openalex.org/W4396722529","https://openalex.org/W4396735838","https://openalex.org/W4400611187","https://openalex.org/W4401023489","https://openalex.org/W4401856690","https://openalex.org/W4401857188","https://openalex.org/W4401857377","https://openalex.org/W4401862897","https://openalex.org/W4404102180","https://openalex.org/W4409657360","https://openalex.org/W6600757733","https://openalex.org/W6601949647","https://openalex.org/W6681029592","https://openalex.org/W6751494907","https://openalex.org/W7053149942","https://openalex.org/W7055594382"],"related_works":["https://openalex.org/W2381393187","https://openalex.org/W2332779545","https://openalex.org/W2358060160","https://openalex.org/W2035483685","https://openalex.org/W1969764885","https://openalex.org/W2532801570","https://openalex.org/W4385627933","https://openalex.org/W2480127678","https://openalex.org/W2806270048","https://openalex.org/W4310605282"],"abstract_inverted_index":{"Recently,":[0],"Graph":[1],"Foundation":[2],"Models":[3],"(GFMs)":[4],"have":[5],"emerged":[6],"as":[7,52],"a":[8,85,91,106,143,167,185],"significant":[9],"research":[10],"topic":[11],"in":[12,63,180],"graph":[13,19,39],"machine":[14],"learning.":[15],"Compared":[16],"with":[17,152,176,184],"traditional":[18],"neural":[20],"networks,":[21],"GFMs":[22,48],"demonstrate":[23,195],"impressive":[24],"zero-shot":[25],"generalization":[26],"across":[27,99],"different":[28],"domains":[29],"and":[30,37,56,61,122,134,161,165,198,214],"tasks":[31],"through":[32],"large-scale":[33],"pre-training":[34,64,82,128,182,211],"on":[35,191],"extensive":[36],"diverse":[38],"data.":[40,65,212],"Despite":[41],"the":[42,57,72,114,127,159,210],"initial":[43],"success":[44],"of":[45,59,75,87,116,139,163,209],"pre-training,":[46],"existing":[47],"face":[49],"challenges":[50],"such":[51],"extreme":[53],"time":[54],"consumption":[55],"presence":[58],"redundancy":[60],"noise":[62],"To":[66],"alleviate":[67],"these":[68],"issues,":[69],"we":[70],"present":[71],"first":[73],"exploration":[74],"data-centric":[76],"GFM,":[77],"which":[78],"aims":[79],"to":[80,89,119],"optimize":[81],"data":[83,117,215],"(i.e.,":[84],"set":[86],"subgraphs)":[88],"establish":[90],"more":[92],"efficient":[93],"GFM":[94,111,193],"while":[95],"maintaining":[96],"robust":[97],"performance":[98,205],"various":[100],"downstream":[101],"tasks.":[102],"We":[103],"propose":[104],"DCGFM,":[105],"plug-and-play":[107],"approach":[108],"for":[109],"Data-Centric":[110],"that":[112,148,172],"incorporates":[113],"idea":[115],"pruning":[118,146,170],"remove":[120],"redundant":[121],"less":[123],"informative":[124],"subgraphs":[125,151,175],"from":[126],"data,":[129],"thereby":[130],"improving":[131],"both":[132,158],"efficiency":[133,197],"effectiveness.":[135,199],"Specifically,":[136],"DCGFM":[137,201],"consists":[138],"two":[140],"components:":[141],"(1)":[142],"model-agnostic":[144],"hard":[145],"module":[147,171],"filters":[149],"out":[150],"lower":[153,177],"informativity":[154],"scores":[155],"by":[156],"considering":[157],"semantics":[160],"structures":[162],"subgraphs;":[164],"(2)":[166],"model-aware":[168],"soft":[169],"dynamically":[173],"prunes":[174],"loss":[178],"values":[179],"each":[181],"epoch":[183],"gradient":[186],"rescaling":[187],"strategy.":[188],"Extensive":[189],"experiments":[190],"representative":[192],"backbones":[194],"DCGFM's":[196],"Remarkably,":[200],"achieves":[202],"even":[203],"better":[204],"using":[206],"only":[207],"30%":[208],"Codes":[213],"are":[216],"available":[217],"at":[218],"https://github.com/Yuhan1i/DCGFM.":[219]},"counts_by_year":[],"updated_date":"2026-04-10T15:06:20.359241","created_date":"2025-10-10T00:00:00"}