{"id":"https://openalex.org/W4312783952","doi":"https://doi.org/10.1109/icpr56361.2022.9956678","title":"Graph Data Augmentation for Node Classification","display_name":"Graph Data Augmentation for Node Classification","publication_year":2022,"publication_date":"2022-08-21","ids":{"openalex":"https://openalex.org/W4312783952","doi":"https://doi.org/10.1109/icpr56361.2022.9956678"},"language":"en","primary_location":{"id":"doi:10.1109/icpr56361.2022.9956678","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icpr56361.2022.9956678","pdf_url":null,"source":{"id":"https://openalex.org/S4363607731","display_name":"2022 26th International Conference on Pattern Recognition (ICPR)","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":"2022 26th International Conference on Pattern Recognition (ICPR)","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":false,"oa_status":"closed","oa_url":null,"any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5017416140","display_name":"Ziyu Wei","orcid":"https://orcid.org/0000-0001-6224-9336"},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Ziyu Wei","raw_affiliation_strings":["Tsinghua University,Shenzhen International Graduate School,Shenzhen,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tsinghua University,Shenzhen International Graduate School,Shenzhen,China","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101600503","display_name":"Xi Xiao","orcid":"https://orcid.org/0000-0003-1521-9542"},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xi Xiao","raw_affiliation_strings":["Tsinghua University,Shenzhen International Graduate School,Shenzhen,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tsinghua University,Shenzhen International Graduate School,Shenzhen,China","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100392792","display_name":"Bin Zhang","orcid":"https://orcid.org/0000-0001-8835-8370"},"institutions":[{"id":"https://openalex.org/I4210136793","display_name":"Peng Cheng Laboratory","ror":"https://ror.org/03qdqbt06","country_code":"CN","type":"facility","lineage":["https://openalex.org/I4210136793"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Bin Zhang","raw_affiliation_strings":["Peng Cheng Laboratory,Department of New Networks,Shenzhen,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Peng Cheng Laboratory,Department of New Networks,Shenzhen,China","institution_ids":["https://openalex.org/I4210136793"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5085450781","display_name":"Guangwu Hu","orcid":"https://orcid.org/0000-0003-3947-9998"},"institutions":[{"id":"https://openalex.org/I158809036","display_name":"Shenzhen Institute of Information Technology","ror":"https://ror.org/03wrf9427","country_code":"CN","type":"education","lineage":["https://openalex.org/I158809036"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Guangwu Hu","raw_affiliation_strings":["Shenzhen Institute of Information Technology,Shenzhen,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Shenzhen Institute of Information Technology,Shenzhen,China","institution_ids":["https://openalex.org/I158809036"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100404176","display_name":"Qing Li","orcid":"https://orcid.org/0000-0003-3370-471X"},"institutions":[{"id":"https://openalex.org/I4210136793","display_name":"Peng Cheng Laboratory","ror":"https://ror.org/03qdqbt06","country_code":"CN","type":"facility","lineage":["https://openalex.org/I4210136793"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Qing Li","raw_affiliation_strings":["Peng Cheng Laboratory,Department of New Networks,Shenzhen,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Peng Cheng Laboratory,Department of New Networks,Shenzhen,China","institution_ids":["https://openalex.org/I4210136793"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5034104790","display_name":"Shu\u2010Tao Xia","orcid":"https://orcid.org/0000-0002-8639-982X"},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Shutao Xia","raw_affiliation_strings":["Tsinghua University,Shenzhen International Graduate School,Shenzhen,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tsinghua University,Shenzhen International Graduate School,Shenzhen,China","institution_ids":["https://openalex.org/I99065089"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":6,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.3114,"has_fulltext":false,"cited_by_count":3,"citation_normalized_percentile":{"value":0.52949907,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":96},"biblio":{"volume":"80","issue":null,"first_page":"4899","last_page":"4905"},"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/T12292","display_name":"Graph Theory and Algorithms","score":0.9887999892234802,"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/T10064","display_name":"Complex Network Analysis Techniques","score":0.986299991607666,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7326964735984802},{"id":"https://openalex.org/keywords/graph","display_name":"Graph","score":0.6157464981079102},{"id":"https://openalex.org/keywords/smoothing","display_name":"Smoothing","score":0.4864620864391327},{"id":"https://openalex.org/keywords/theoretical-computer-science","display_name":"Theoretical computer science","score":0.4221940338611603},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.3435823917388916}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7326964735984802},{"id":"https://openalex.org/C132525143","wikidata":"https://www.wikidata.org/wiki/Q141488","display_name":"Graph","level":2,"score":0.6157464981079102},{"id":"https://openalex.org/C3770464","wikidata":"https://www.wikidata.org/wiki/Q775963","display_name":"Smoothing","level":2,"score":0.4864620864391327},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.4221940338611603},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.3435823917388916},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icpr56361.2022.9956678","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icpr56361.2022.9956678","pdf_url":null,"source":{"id":"https://openalex.org/S4363607731","display_name":"2022 26th International Conference on Pattern Recognition (ICPR)","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":"2022 26th International Conference on Pattern Recognition (ICPR)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"},{"id":"https://openalex.org/F4320321408","display_name":"Ministry of Education","ror":"https://ror.org/01p262204"},{"id":"https://openalex.org/F4320335777","display_name":"National Key Research and Development Program of China","ror":null},{"id":"https://openalex.org/F4320337504","display_name":"Research and Development","ror":"https://ror.org/027s68j25"},{"id":"https://openalex.org/F4320337986","display_name":"Tsinghua Shenzhen International Graduate School","ror":null}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":62,"referenced_works":["https://openalex.org/W637153065","https://openalex.org/W1662382123","https://openalex.org/W2103018059","https://openalex.org/W2170240176","https://openalex.org/W2487365028","https://openalex.org/W2558460151","https://openalex.org/W2583803680","https://openalex.org/W2624407581","https://openalex.org/W2786103815","https://openalex.org/W2786273134","https://openalex.org/W2790814121","https://openalex.org/W2804057010","https://openalex.org/W2806351858","https://openalex.org/W2807021761","https://openalex.org/W2809418595","https://openalex.org/W2889833989","https://openalex.org/W2945827377","https://openalex.org/W2954996726","https://openalex.org/W2962711740","https://openalex.org/W2963241951","https://openalex.org/W2963456618","https://openalex.org/W2963555845","https://openalex.org/W2963695795","https://openalex.org/W2963757395","https://openalex.org/W2964015378","https://openalex.org/W2964051675","https://openalex.org/W2964145825","https://openalex.org/W2964321699","https://openalex.org/W2971933740","https://openalex.org/W2990045899","https://openalex.org/W2996268457","https://openalex.org/W2998496395","https://openalex.org/W3035739162","https://openalex.org/W3100848837","https://openalex.org/W3101553402","https://openalex.org/W3103720336","https://openalex.org/W3105202247","https://openalex.org/W3117136530","https://openalex.org/W3133537878","https://openalex.org/W4289389616","https://openalex.org/W4294558607","https://openalex.org/W4297733535","https://openalex.org/W4297951436","https://openalex.org/W6620673361","https://openalex.org/W6637178625","https://openalex.org/W6685053522","https://openalex.org/W6713582119","https://openalex.org/W6720006811","https://openalex.org/W6726873649","https://openalex.org/W6738964360","https://openalex.org/W6748556633","https://openalex.org/W6748799445","https://openalex.org/W6748848838","https://openalex.org/W6748856961","https://openalex.org/W6749077313","https://openalex.org/W6752110883","https://openalex.org/W6754929296","https://openalex.org/W6755863455","https://openalex.org/W6767710714","https://openalex.org/W6771932116","https://openalex.org/W6779474503","https://openalex.org/W6785773631"],"related_works":["https://openalex.org/W2748952813","https://openalex.org/W2383807498","https://openalex.org/W1978572805","https://openalex.org/W1997992934","https://openalex.org/W1987225439","https://openalex.org/W4238188170","https://openalex.org/W2125114371","https://openalex.org/W2149980199","https://openalex.org/W2019977573","https://openalex.org/W4226363941"],"abstract_inverted_index":{"In":[0,85],"recent":[1],"years,":[2],"Graph":[3,91],"Neural":[4],"Networks":[5],"(GNNs)":[6],"have":[7],"emerged":[8],"as":[9],"powerful":[10],"techniques":[11],"for":[12,18,101],"graph-structure":[13],"data,":[14],"which":[15],"are":[16,35],"essential":[17],"a":[19,48,72,90],"wide":[20],"range":[21],"of":[22,76,109,117,158,167,172,198],"graph-based":[23],"tasks":[24],"like":[25],"link":[26],"prediction":[27],"and":[28,33,55,65,121,137,162,191,201],"node":[29,102,118],"classification.":[30],"However,":[31],"over-smoothing":[32],"over-fitting":[34],"two":[36,53,110],"main":[37],"challenges":[38],"that":[39,179],"impact":[40],"negatively":[41],"on":[42,115,174],"model":[43],"performance.":[44],"Data":[45,92],"augmentation":[46],"is":[47,57,71,131,143],"good":[49],"solution":[50],"to":[51,81,96,125,133,145,164],"these":[52],"problems,":[54],"it":[56,79],"also":[58],"proven":[59],"very":[60],"effective":[61],"in":[62],"computer":[63],"vision":[64],"nature":[66],"language":[67],"processing.":[68],"But":[69],"there":[70],"relatively":[73],"small":[74],"body":[75],"literature":[77],"when":[78],"comes":[80],"graph":[82,99,161],"data":[83],"augmentation.":[84],"this":[86],"paper,":[87],"we":[88],"propose":[89],"Augmentation":[93],"(GDA)":[94],"strategy":[95],"optimize":[97],"the":[98,155,159,192,196],"topology":[100],"classification":[103],"tasks.":[104],"Our":[105],"GDA":[106,181],"approach":[107,182],"consists":[108],"operations:":[111],"edge":[112],"manipulation":[113],"based":[114],"similarities":[116],"pairs":[119],"(GDA-E)":[120],"new":[122],"nodes":[123,128,147],"addition":[124],"under-informed":[126],"old":[127],"(GDA-N).":[129],"GDA-E":[130,200],"designed":[132],"add":[134],"missing":[135],"edges":[136],"remove":[138],"noisy":[139],"edges,":[140],"while":[141],"GDA-N":[142],"established":[144],"help":[146],"with":[148],"low":[149],"degree.":[150],"Both":[151],"operations":[152],"can":[153],"improve":[154],"information-to-noise":[156],"ratio":[157],"whole":[160],"lead":[163],"better":[165],"performance":[166],"GNNs.":[168],"The":[169],"comparative":[170],"results":[171],"experiments":[173],"three":[175],"different":[176],"datasets":[177],"show":[178],"our":[180],"achieves":[183],"considerable":[184],"improvement":[185],"(11.0%":[186],"average)":[187],"over":[188],"origin":[189],"graphs,":[190],"ablation":[193],"study":[194],"verifies":[195],"effectiveness":[197],"both":[199],"GDA-N.":[202]},"counts_by_year":[{"year":2024,"cited_by_count":2},{"year":2023,"cited_by_count":1}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}