{"id":"https://openalex.org/W4290875057","doi":"https://doi.org/10.1145/3534678.3539457","title":"Learning on Graphs with Out-of-Distribution Nodes","display_name":"Learning on Graphs with Out-of-Distribution Nodes","publication_year":2022,"publication_date":"2022-08-12","ids":{"openalex":"https://openalex.org/W4290875057","doi":"https://doi.org/10.1145/3534678.3539457"},"language":"en","primary_location":{"id":"doi:10.1145/3534678.3539457","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3534678.3539457","pdf_url":null,"source":{"id":"https://openalex.org/S4363608767","display_name":"Proceedings of the 28th ACM SIGKDD Conference on Knowledge Discovery and Data Mining","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 28th ACM SIGKDD Conference on Knowledge Discovery and Data Mining","raw_type":"proceedings-article"},"type":"article","indexed_in":["arxiv","crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2308.06714","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5033014552","display_name":"Yu Song","orcid":"https://orcid.org/0000-0002-0771-7499"},"institutions":[{"id":"https://openalex.org/I3133055985","display_name":"Westlake University","ror":"https://ror.org/05hfa4n20","country_code":"CN","type":"education","lineage":["https://openalex.org/I3133055985"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Yu Song","raw_affiliation_strings":["Westlake University, Hangzhou, China"],"affiliations":[{"raw_affiliation_string":"Westlake University, Hangzhou, China","institution_ids":["https://openalex.org/I3133055985"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100665181","display_name":"Donglin Wang","orcid":"https://orcid.org/0000-0002-8188-3735"},"institutions":[{"id":"https://openalex.org/I3133055985","display_name":"Westlake University","ror":"https://ror.org/05hfa4n20","country_code":"CN","type":"education","lineage":["https://openalex.org/I3133055985"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Donglin Wang","raw_affiliation_strings":["Westlake University, Hangzhou, China"],"affiliations":[{"raw_affiliation_string":"Westlake University, Hangzhou, China","institution_ids":["https://openalex.org/I3133055985"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5033014552"],"corresponding_institution_ids":["https://openalex.org/I3133055985"],"apc_list":null,"apc_paid":null,"fwci":2.5039,"has_fulltext":true,"cited_by_count":26,"citation_normalized_percentile":{"value":0.91197668,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":98,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"1635","last_page":"1645"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11273","display_name":"Advanced Graph Neural Networks","score":0.9973999857902527,"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":0.9973999857902527,"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/T11512","display_name":"Anomaly Detection Techniques and Applications","score":0.9930999875068665,"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/T11689","display_name":"Adversarial Robustness in Machine Learning","score":0.9894000291824341,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7456823587417603},{"id":"https://openalex.org/keywords/inference","display_name":"Inference","score":0.6396300792694092},{"id":"https://openalex.org/keywords/outlier","display_name":"Outlier","score":0.564351499080658},{"id":"https://openalex.org/keywords/margin","display_name":"Margin (machine learning)","score":0.5399366617202759},{"id":"https://openalex.org/keywords/graph","display_name":"Graph","score":0.5350882411003113},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5241805911064148},{"id":"https://openalex.org/keywords/theoretical-computer-science","display_name":"Theoretical computer science","score":0.44734594225883484},{"id":"https://openalex.org/keywords/anomaly-detection","display_name":"Anomaly detection","score":0.44616761803627014},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.44414493441581726},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.3962709903717041},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.3357456922531128}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7456823587417603},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.6396300792694092},{"id":"https://openalex.org/C79337645","wikidata":"https://www.wikidata.org/wiki/Q779824","display_name":"Outlier","level":2,"score":0.564351499080658},{"id":"https://openalex.org/C774472","wikidata":"https://www.wikidata.org/wiki/Q6760393","display_name":"Margin (machine learning)","level":2,"score":0.5399366617202759},{"id":"https://openalex.org/C132525143","wikidata":"https://www.wikidata.org/wiki/Q141488","display_name":"Graph","level":2,"score":0.5350882411003113},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5241805911064148},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.44734594225883484},{"id":"https://openalex.org/C739882","wikidata":"https://www.wikidata.org/wiki/Q3560506","display_name":"Anomaly detection","level":2,"score":0.44616761803627014},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.44414493441581726},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.3962709903717041},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3357456922531128}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1145/3534678.3539457","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3534678.3539457","pdf_url":null,"source":{"id":"https://openalex.org/S4363608767","display_name":"Proceedings of the 28th ACM SIGKDD Conference on Knowledge Discovery and Data Mining","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 28th ACM SIGKDD Conference on Knowledge Discovery and Data Mining","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2308.06714","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2308.06714","pdf_url":"https://arxiv.org/pdf/2308.06714","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":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2308.06714","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2308.06714","pdf_url":"https://arxiv.org/pdf/2308.06714","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":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G1121271761","display_name":null,"funder_award_id":"Program","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G3317480652","display_name":null,"funder_award_id":"Science","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/G5265214819","display_name":null,"funder_award_id":"62176215","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G5939423041","display_name":null,"funder_award_id":"Technology","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G8018449572","display_name":null,"funder_award_id":"2022ZD0208800","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G8955107213","display_name":null,"funder_award_id":"Major","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4290875057.pdf","grobid_xml":"https://content.openalex.org/works/W4290875057.grobid-xml"},"referenced_works_count":40,"referenced_works":["https://openalex.org/W2145494108","https://openalex.org/W2293363371","https://openalex.org/W2531327146","https://openalex.org/W2867167548","https://openalex.org/W2889625178","https://openalex.org/W2900470550","https://openalex.org/W2912083425","https://openalex.org/W2951883849","https://openalex.org/W2963312446","https://openalex.org/W2963384319","https://openalex.org/W2963956526","https://openalex.org/W2963995504","https://openalex.org/W2964015378","https://openalex.org/W2964051675","https://openalex.org/W2964159205","https://openalex.org/W2970946347","https://openalex.org/W2998269939","https://openalex.org/W3005644236","https://openalex.org/W3006853338","https://openalex.org/W3034792991","https://openalex.org/W3043138801","https://openalex.org/W3094146654","https://openalex.org/W3094397005","https://openalex.org/W3094504436","https://openalex.org/W3106636111","https://openalex.org/W3165919849","https://openalex.org/W3166215705","https://openalex.org/W3166500992","https://openalex.org/W3171723757","https://openalex.org/W3198218876","https://openalex.org/W3199390827","https://openalex.org/W3212603644","https://openalex.org/W4285723986","https://openalex.org/W4286795917","https://openalex.org/W4286953199","https://openalex.org/W4287262235","https://openalex.org/W4287280056","https://openalex.org/W4287638145","https://openalex.org/W4287726895","https://openalex.org/W4294558607"],"related_works":["https://openalex.org/W3125011624","https://openalex.org/W1508631387","https://openalex.org/W2370917603","https://openalex.org/W2952760143","https://openalex.org/W2499612753","https://openalex.org/W3111802945","https://openalex.org/W2946096271","https://openalex.org/W2295423552","https://openalex.org/W1598471830","https://openalex.org/W3107369729"],"abstract_inverted_index":{"Graph":[0,148],"Neural":[1],"Networks":[2],"(GNNs)":[3],"are":[4,71,78,140],"state-of-the-art":[5],"models":[6,158],"for":[7,142],"performing":[8],"prediction":[9],"tasks":[10,22],"on":[11,20],"graphs.":[12],"While":[13],"existing":[14,180],"GNNs":[15],"have":[16],"shown":[17],"great":[18],"performance":[19],"various":[21],"related":[23],"to":[24,31,104,115,125],"graphs,":[25],"little":[26],"attention":[27],"has":[28],"been":[29],"paid":[30],"the":[32,40,47,63,93,116,122,129,135,159],"scenario":[33],"where":[34],"out-of-distribution":[35,99],"(OOD)":[36],"nodes":[37,56,58,84,110,124,165],"exist":[38],"in":[39,138,193],"graph":[41,96],"during":[42,171],"training":[43,64],"and":[44,51,81,119,145,166],"inference.":[45],"Borrowing":[46],"concept":[48],"from":[49,62,85,169],"CV":[50],"NLP,":[52],"we":[53,91,102],"define":[54,92],"OOD":[55],"as":[57],"with":[59,98],"labels":[60],"unseen":[61],"set.":[65],"Since":[66],"a":[67,152,185],"lot":[68],"of":[69,95,128,164,195],"networks":[70],"automatically":[72],"constructed":[73],"by":[74,184],"programs,":[75],"real-world":[76],"graphs":[77,139],"often":[79],"noisy":[80],"may":[82],"contain":[83],"unknown":[86],"distributions.":[87],"In":[88],"this":[89],"work,":[90],"problem":[94],"learning":[97],"nodes.":[100],"Specifically,":[101],"aim":[103],"accomplish":[105],"two":[106],"tasks:":[107],"1)":[108],"detect":[109],"which":[111,156],"do":[112],"not":[113],"belong":[114],"known":[117,130],"distribution":[118],"2)":[120],"classify":[121],"remaining":[123],"be":[126],"one":[127],"classes.":[131],"We":[132],"demonstrate":[133],"that":[134,177],"connection":[136],"patterns":[137],"informative":[141],"outlier":[143,181],"detection,":[144],"propose":[146],"Out-of-Distribution":[147],"Attention":[149],"Network":[150],"(OODGAT),":[151],"novel":[153],"GNN":[154],"model":[155],"explicitly":[157],"interaction":[160],"between":[161],"different":[162],"kinds":[163],"separate":[167],"inliers":[168],"outliers":[170],"feature":[172],"propagation.":[173],"Extensive":[174],"experiments":[175],"show":[176],"OODGAT":[178],"outperforms":[179],"detection":[182],"methods":[183],"large":[186],"margin,":[187],"while":[188],"being":[189],"better":[190],"or":[191],"comparable":[192],"terms":[194],"in-distribution":[196],"classification.":[197]},"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2025,"cited_by_count":10},{"year":2024,"cited_by_count":7},{"year":2023,"cited_by_count":7}],"updated_date":"2026-04-18T07:56:08.524223","created_date":"2025-10-10T00:00:00"}