{"id":"https://openalex.org/W4379261299","doi":"https://doi.org/10.1145/3616855.3635786","title":"Pitfalls in Link Prediction with Graph Neural Networks: Understanding the Impact of Target-link Inclusion & Better Practices","display_name":"Pitfalls in Link Prediction with Graph Neural Networks: Understanding the Impact of Target-link Inclusion & Better Practices","publication_year":2024,"publication_date":"2024-03-04","ids":{"openalex":"https://openalex.org/W4379261299","doi":"https://doi.org/10.1145/3616855.3635786"},"language":"en","primary_location":{"id":"doi:10.1145/3616855.3635786","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3616855.3635786","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 17th ACM International Conference on Web Search and Data Mining","raw_type":"proceedings-article"},"type":"preprint","indexed_in":["arxiv","crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2306.00899","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5100317533","display_name":"Jing Zhu","orcid":"https://orcid.org/0000-0002-5364-151X"},"institutions":[{"id":"https://openalex.org/I27837315","display_name":"University of Michigan","ror":"https://ror.org/00jmfr291","country_code":"US","type":"education","lineage":["https://openalex.org/I27837315"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Jing Zhu","raw_affiliation_strings":["University of Michigan, Ann Arbor, USA"],"affiliations":[{"raw_affiliation_string":"University of Michigan, Ann Arbor, USA","institution_ids":["https://openalex.org/I27837315"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101972658","display_name":"Yuhang Zhou","orcid":"https://orcid.org/0000-0003-2563-3712"},"institutions":[{"id":"https://openalex.org/I66946132","display_name":"University of Maryland, College Park","ror":"https://ror.org/047s2c258","country_code":"US","type":"education","lineage":["https://openalex.org/I66946132"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Yuhang Zhou","raw_affiliation_strings":["University of Maryland, College Park, USA"],"affiliations":[{"raw_affiliation_string":"University of Maryland, College Park, USA","institution_ids":["https://openalex.org/I66946132"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5023028617","display_name":"Vassilis N. Ioannidis","orcid":"https://orcid.org/0000-0002-8367-0733"},"institutions":[{"id":"https://openalex.org/I1311688040","display_name":"Amazon (United States)","ror":"https://ror.org/04mv4n011","country_code":"US","type":"company","lineage":["https://openalex.org/I1311688040"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Vassilis N. Ioannidis","raw_affiliation_strings":["Amazon, Santa Clara, USA"],"affiliations":[{"raw_affiliation_string":"Amazon, Santa Clara, USA","institution_ids":["https://openalex.org/I1311688040"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5030632256","display_name":"Shengyi Qian","orcid":"https://orcid.org/0000-0003-0262-2412"},"institutions":[{"id":"https://openalex.org/I27837315","display_name":"University of Michigan","ror":"https://ror.org/00jmfr291","country_code":"US","type":"education","lineage":["https://openalex.org/I27837315"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Shengyi Qian","raw_affiliation_strings":["University of Michigan, Ann Arbor, USA"],"affiliations":[{"raw_affiliation_string":"University of Michigan, Ann Arbor, USA","institution_ids":["https://openalex.org/I27837315"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5062903694","display_name":"Wei Ai","orcid":"https://orcid.org/0000-0001-6271-9430"},"institutions":[{"id":"https://openalex.org/I66946132","display_name":"University of Maryland, College Park","ror":"https://ror.org/047s2c258","country_code":"US","type":"education","lineage":["https://openalex.org/I66946132"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Wei Ai","raw_affiliation_strings":["University of Maryland, College Park, USA"],"affiliations":[{"raw_affiliation_string":"University of Maryland, College Park, USA","institution_ids":["https://openalex.org/I66946132"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101675531","display_name":"Xiang Song","orcid":"https://orcid.org/0000-0001-5030-5054"},"institutions":[{"id":"https://openalex.org/I1311688040","display_name":"Amazon (United States)","ror":"https://ror.org/04mv4n011","country_code":"US","type":"company","lineage":["https://openalex.org/I1311688040"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Xiang Song","raw_affiliation_strings":["Amazon AWS, Santa Clara, USA"],"affiliations":[{"raw_affiliation_string":"Amazon AWS, Santa Clara, USA","institution_ids":["https://openalex.org/I1311688040"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5015996266","display_name":"Danai Koutra","orcid":"https://orcid.org/0000-0002-3206-8179"},"institutions":[{"id":"https://openalex.org/I27837315","display_name":"University of Michigan","ror":"https://ror.org/00jmfr291","country_code":"US","type":"education","lineage":["https://openalex.org/I27837315"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Danai Koutra","raw_affiliation_strings":["University of Michigan, Ann Arbor, USA"],"affiliations":[{"raw_affiliation_string":"University of Michigan, Ann Arbor, USA","institution_ids":["https://openalex.org/I27837315"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":7,"corresponding_author_ids":["https://openalex.org/A5100317533"],"corresponding_institution_ids":["https://openalex.org/I27837315"],"apc_list":null,"apc_paid":null,"fwci":3.4067,"has_fulltext":true,"cited_by_count":10,"citation_normalized_percentile":{"value":0.92776525,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":96,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"994","last_page":"1002"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11273","display_name":"Advanced Graph Neural Networks","score":1.0,"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":1.0,"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/T10064","display_name":"Complex Network Analysis Techniques","score":0.9983000159263611,"subfield":{"id":"https://openalex.org/subfields/3109","display_name":"Statistical and Nonlinear Physics"},"field":{"id":"https://openalex.org/fields/31","display_name":"Physics and Astronomy"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T10203","display_name":"Recommender Systems and Techniques","score":0.9912999868392944,"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/generalizability-theory","display_name":"Generalizability theory","score":0.7970576286315918},{"id":"https://openalex.org/keywords/overfitting","display_name":"Overfitting","score":0.7621553540229797},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7534865140914917},{"id":"https://openalex.org/keywords/graph","display_name":"Graph","score":0.5452741384506226},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.5006060600280762},{"id":"https://openalex.org/keywords/test-data","display_name":"Test data","score":0.45958438515663147},{"id":"https://openalex.org/keywords/attention-network","display_name":"Attention network","score":0.4317304193973541},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.420812726020813},{"id":"https://openalex.org/keywords/dense-graph","display_name":"Dense graph","score":0.4164718985557556},{"id":"https://openalex.org/keywords/node","display_name":"Node (physics)","score":0.41597163677215576},{"id":"https://openalex.org/keywords/training-set","display_name":"Training set","score":0.41149580478668213},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.4075019657611847},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3899827301502228},{"id":"https://openalex.org/keywords/theoretical-computer-science","display_name":"Theoretical computer science","score":0.3215969204902649},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.10669839382171631},{"id":"https://openalex.org/keywords/statistics","display_name":"Statistics","score":0.09648025035858154}],"concepts":[{"id":"https://openalex.org/C27158222","wikidata":"https://www.wikidata.org/wiki/Q5532422","display_name":"Generalizability theory","level":2,"score":0.7970576286315918},{"id":"https://openalex.org/C22019652","wikidata":"https://www.wikidata.org/wiki/Q331309","display_name":"Overfitting","level":3,"score":0.7621553540229797},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7534865140914917},{"id":"https://openalex.org/C132525143","wikidata":"https://www.wikidata.org/wiki/Q141488","display_name":"Graph","level":2,"score":0.5452741384506226},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.5006060600280762},{"id":"https://openalex.org/C16910744","wikidata":"https://www.wikidata.org/wiki/Q7705759","display_name":"Test data","level":2,"score":0.45958438515663147},{"id":"https://openalex.org/C2993807640","wikidata":"https://www.wikidata.org/wiki/Q103709453","display_name":"Attention network","level":2,"score":0.4317304193973541},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.420812726020813},{"id":"https://openalex.org/C13251829","wikidata":"https://www.wikidata.org/wiki/Q3085841","display_name":"Dense graph","level":5,"score":0.4164718985557556},{"id":"https://openalex.org/C62611344","wikidata":"https://www.wikidata.org/wiki/Q1062658","display_name":"Node (physics)","level":2,"score":0.41597163677215576},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.41149580478668213},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.4075019657611847},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3899827301502228},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.3215969204902649},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.10669839382171631},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.09648025035858154},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0},{"id":"https://openalex.org/C66938386","wikidata":"https://www.wikidata.org/wiki/Q633538","display_name":"Structural engineering","level":1,"score":0.0},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.0},{"id":"https://openalex.org/C102192266","wikidata":"https://www.wikidata.org/wiki/Q4545823","display_name":"1-planar graph","level":4,"score":0.0},{"id":"https://openalex.org/C203776342","wikidata":"https://www.wikidata.org/wiki/Q1378376","display_name":"Line graph","level":3,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1145/3616855.3635786","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3616855.3635786","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 17th ACM International Conference on Web Search and Data Mining","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2306.00899","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2306.00899","pdf_url":"https://arxiv.org/pdf/2306.00899","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":"cc-by-nc-sa","license_id":"https://openalex.org/licenses/cc-by-nc-sa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2306.00899","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2306.00899","pdf_url":"https://arxiv.org/pdf/2306.00899","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":"cc-by-nc-sa","license_id":"https://openalex.org/licenses/cc-by-nc-sa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/9","score":0.41999998688697815,"display_name":"Industry, innovation and infrastructure"}],"awards":[{"id":"https://openalex.org/G4496747893","display_name":null,"funder_award_id":"IS 1845491","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G5962262462","display_name":"Collaborative Research: III: Medium: Graph Neural Networks for Heterophilous Data: Advancing the Theory, Models, and Applications","funder_award_id":"2212143","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G6595624021","display_name":null,"funder_award_id":"IIS 1845491","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/G7903790144","display_name":null,"funder_award_id":"1845491","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G8336002174","display_name":null,"funder_award_id":"2212143","funder_id":"https://openalex.org/F4320323817","funder_display_name":"Universitas Brawijaya"},{"id":"https://openalex.org/G848032724","display_name":null,"funder_award_id":"Science","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/F4320323817","display_name":"Universitas Brawijaya","ror":"https://ror.org/01wk3d929"}],"has_content":{"pdf":true,"grobid_xml":false},"content_urls":{"pdf":"https://content.openalex.org/works/W4379261299.pdf"},"referenced_works_count":50,"referenced_works":["https://openalex.org/W1736726159","https://openalex.org/W2054141820","https://openalex.org/W2111708605","https://openalex.org/W2127795553","https://openalex.org/W2154454189","https://openalex.org/W2420733993","https://openalex.org/W2564084673","https://openalex.org/W2607500032","https://openalex.org/W2804057010","https://openalex.org/W2896457183","https://openalex.org/W2899771611","https://openalex.org/W2952575904","https://openalex.org/W2963757395","https://openalex.org/W2964015378","https://openalex.org/W2995448904","https://openalex.org/W2997545008","https://openalex.org/W3005552578","https://openalex.org/W3034239155","https://openalex.org/W3037208489","https://openalex.org/W3041467169","https://openalex.org/W3048692209","https://openalex.org/W3080555959","https://openalex.org/W3080997787","https://openalex.org/W3100078588","https://openalex.org/W3101444938","https://openalex.org/W3103409210","https://openalex.org/W3159953606","https://openalex.org/W3169463543","https://openalex.org/W3172525852","https://openalex.org/W3210188290","https://openalex.org/W4229641819","https://openalex.org/W4242291765","https://openalex.org/W4282961889","https://openalex.org/W4283075104","https://openalex.org/W4283391386","https://openalex.org/W4286795917","https://openalex.org/W4287643204","https://openalex.org/W4288364260","https://openalex.org/W4288419263","https://openalex.org/W4294558607","https://openalex.org/W4297940714","https://openalex.org/W4310510663","https://openalex.org/W4319165818","https://openalex.org/W4322614756","https://openalex.org/W4385965989","https://openalex.org/W4387076000","https://openalex.org/W4388444775","https://openalex.org/W4388747884","https://openalex.org/W4389518953","https://openalex.org/W6601700763"],"related_works":["https://openalex.org/W4362597605","https://openalex.org/W1574414179","https://openalex.org/W3009056573","https://openalex.org/W4297676672","https://openalex.org/W2922073769","https://openalex.org/W4281702477","https://openalex.org/W4220972140","https://openalex.org/W3161120485","https://openalex.org/W2791137381","https://openalex.org/W2973011565"],"abstract_inverted_index":{"While":[0],"Graph":[1],"Neural":[2],"Networks":[3],"(GNNs)":[4],"are":[5,197],"remarkably":[6],"successful":[7],"in":[8,17,29,109,179,222,233],"a":[9,110,136],"variety":[10],"of":[11,23,42,94,103,169],"high-impact":[12],"applications,":[13],"we":[14,60,113],"demonstrate":[15],"that,":[16],"link":[18],"prediction,":[19],"the":[20,25,30,40,85,89,95,101,173,180,202],"common":[21],"practices":[22,52,190],"including":[24],"edges":[26,161],"being":[27],"predicted":[28,141,164],"graph":[31,194],"at":[32,131,147,154],"training":[33,120,132],"and/or":[34],"test":[35,74,86,155,160,174],"have":[36],"outsized":[37],"impact":[38,53],"on":[39,127,208],"performance":[41,55,97,229],"low-degree":[43,128,150,231],"nodes.":[44],"We":[45],"theoretically":[46],"and":[47,71,98,117,152,185,225],"empirically":[48],"investigate":[49],"how":[50],"these":[51,107],"node-level":[54],"across":[56],"different":[57],"degrees.":[58],"Specifically,":[59],"explore":[61],"three":[62],"issues":[63,79,108],"that":[64,213],"arise:":[65],"(I1)":[66],"overfitting;":[67],"(I2)":[68],"distribution":[69],"shift;":[70],"(I3)":[72],"implicit":[73],"leakage.":[75],"The":[76],"former":[77],"two":[78],"lead":[80],"to":[81,84,92,139,146,162,188,218],"poor":[82],"generalizability":[83],"data,":[87,195],"while":[88],"latter":[90],"leads":[91],"overestimation":[93],"model's":[96],"directly":[99],"impacts":[100],"deployment":[102],"GNNs.":[104],"To":[105],"address":[106],"systematic":[111],"way,":[112],"introduce":[114],"an":[115],"effective":[116],"efficient":[118],"GNN":[119],"framework,":[121],"SpotTarget,":[122],"which":[123,196],"leverages":[124],"our":[125],"insight":[126],"nodes:":[129],"(1)":[130],"time,":[133,156],"it":[134,143,157],"excludes":[135,158],"(training)":[137],"edge":[138],"be":[140,163],"if":[142],"is":[144,176],"incident":[145],"least":[148],"one":[149],"node;":[151],"(2)":[153],"all":[159],"(thus,":[165],"mimicking":[166],"real":[167],"scenarios":[168],"using":[170],"GNNs,":[171],"where":[172],"data":[175],"not":[177],"included":[178],"graph).":[181],"SpotTarget":[182,214],"helps":[183],"researchers":[184],"practitioners":[186],"adhere":[187],"best":[189],"for":[191,230],"learning":[192],"from":[193],"frequently":[198],"overlooked":[199],"even":[200],"by":[201],"most":[203],"widely-used":[204],"frameworks.":[205],"Our":[206],"experiments":[207],"various":[209],"real-world":[210],"datasets":[211],"show":[212],"makes":[215],"GNNs":[216],"up":[217],"15\u00d7":[219],"more":[220],"accurate":[221],"sparse":[223],"graphs,":[224],"significantly":[226],"improves":[227],"their":[228],"nodes":[232],"dense":[234],"graphs.":[235]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":6},{"year":2024,"cited_by_count":3}],"updated_date":"2026-04-10T15:06:20.359241","created_date":"2023-06-04T00:00:00"}