{"id":"https://openalex.org/W7143399400","doi":"https://doi.org/10.1109/tkde.2026.3678725","title":"GNN Defender: Overcoming Mixed Noise Through Cross-Correction Over Nodes and Edges","display_name":"GNN Defender: Overcoming Mixed Noise Through Cross-Correction Over Nodes and Edges","publication_year":2026,"publication_date":"2026-03-30","ids":{"openalex":"https://openalex.org/W7143399400","doi":"https://doi.org/10.1109/tkde.2026.3678725"},"language":"en","primary_location":{"id":"doi:10.1109/tkde.2026.3678725","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tkde.2026.3678725","pdf_url":null,"source":{"id":"https://openalex.org/S30698027","display_name":"IEEE Transactions on Knowledge and Data Engineering","issn_l":"1041-4347","issn":["1041-4347","1558-2191","2326-3865"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320439","host_organization_name":"IEEE Computer Society","host_organization_lineage":["https://openalex.org/P4310320439","https://openalex.org/P4310319808"],"host_organization_lineage_names":["IEEE Computer Society","Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Knowledge and Data Engineering","raw_type":"journal-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/A5100430876","display_name":"Xi Zhang","orcid":"https://orcid.org/0000-0003-3415-5345"},"institutions":[{"id":"https://openalex.org/I4800084","display_name":"Southwest Jiaotong University","ror":"https://ror.org/00hn7w693","country_code":"CN","type":"education","lineage":["https://openalex.org/I4800084"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xiaobo Zhang","raw_affiliation_strings":["School of Computing and Artificial Intelligence, the Institute of Artificial Intelligence, and the National Engineering Laboratory of Integrated Transportation Big Data Application Technology, Southwest Jiaotong University, Chengdu, China"],"raw_orcid":"https://orcid.org/0000-0002-6598-0519","affiliations":[{"raw_affiliation_string":"School of Computing and Artificial Intelligence, the Institute of Artificial Intelligence, and the National Engineering Laboratory of Integrated Transportation Big Data Application Technology, Southwest Jiaotong University, Chengdu, China","institution_ids":["https://openalex.org/I4800084"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5090143892","display_name":"Yutao Liu","orcid":"https://orcid.org/0009-0001-2001-7876"},"institutions":[{"id":"https://openalex.org/I4800084","display_name":"Southwest Jiaotong University","ror":"https://ror.org/00hn7w693","country_code":"CN","type":"education","lineage":["https://openalex.org/I4800084"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yutao Liu","raw_affiliation_strings":["School of Computing and Artificial Intelligence, the Institute of Artificial Intelligence, and the National Engineering Laboratory of Integrated Transportation Big Data Application Technology, Southwest Jiaotong University, Chengdu, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Computing and Artificial Intelligence, the Institute of Artificial Intelligence, and the National Engineering Laboratory of Integrated Transportation Big Data Application Technology, Southwest Jiaotong University, Chengdu, China","institution_ids":["https://openalex.org/I4800084"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5130985399","display_name":"Hao Wang","orcid":null},"institutions":[{"id":"https://openalex.org/I24185976","display_name":"Sichuan University","ror":"https://ror.org/011ashp19","country_code":"CN","type":"education","lineage":["https://openalex.org/I24185976"]},{"id":"https://openalex.org/I4210125143","display_name":"Chengdu University","ror":"https://ror.org/034z67559","country_code":"CN","type":"education","lineage":["https://openalex.org/I4210125143"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Hao Wang","raw_affiliation_strings":["College of Computer Science, Sichuan University, Chengdu, China"],"raw_orcid":"https://orcid.org/0000-0001-9492-3807","affiliations":[{"raw_affiliation_string":"College of Computer Science, Sichuan University, Chengdu, China","institution_ids":["https://openalex.org/I24185976","https://openalex.org/I4210125143"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102942589","display_name":"W. Xie","orcid":"https://orcid.org/0000-0001-7689-140X"},"institutions":[{"id":"https://openalex.org/I4800084","display_name":"Southwest Jiaotong University","ror":"https://ror.org/00hn7w693","country_code":"CN","type":"education","lineage":["https://openalex.org/I4800084"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Wei Xie","raw_affiliation_strings":["School of Computing and Artificial Intelligence, the Institute of Artificial Intelligence, and the National Engineering Laboratory of Integrated Transportation Big Data Application Technology, Southwest Jiaotong University, Chengdu, China"],"raw_orcid":"https://orcid.org/0009-0002-0400-268X","affiliations":[{"raw_affiliation_string":"School of Computing and Artificial Intelligence, the Institute of Artificial Intelligence, and the National Engineering Laboratory of Integrated Transportation Big Data Application Technology, Southwest Jiaotong University, Chengdu, China","institution_ids":["https://openalex.org/I4800084"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100391700","display_name":"Wei Wang","orcid":"https://orcid.org/0000-0001-6853-7785"},"institutions":[{"id":"https://openalex.org/I139024713","display_name":"Guangdong University of Technology","ror":"https://ror.org/04azbjn80","country_code":"CN","type":"education","lineage":["https://openalex.org/I139024713"]},{"id":"https://openalex.org/I4210122146","display_name":"Guangzhou Municipal Engineering Design and Research Institute","ror":"https://ror.org/02rgkd872","country_code":"CN","type":"facility","lineage":["https://openalex.org/I4210122146"]},{"id":"https://openalex.org/I889458895","display_name":"University of Hong Kong","ror":"https://ror.org/02zhqgq86","country_code":"HK","type":"education","lineage":["https://openalex.org/I889458895"]},{"id":"https://openalex.org/I90610280","display_name":"South China University of Technology","ror":"https://ror.org/0530pts50","country_code":"CN","type":"education","lineage":["https://openalex.org/I90610280"]}],"countries":["CN","HK"],"is_corresponding":false,"raw_author_name":"Wei Wang","raw_affiliation_strings":["Guangzhou Municipal Key Laboratory of Materials Informatics, Hong Kong University of Science and Technology, Guangzhou, Guangdong, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Guangzhou Municipal Key Laboratory of Materials Informatics, Hong Kong University of Science and Technology, Guangzhou, Guangdong, China","institution_ids":["https://openalex.org/I139024713","https://openalex.org/I4210122146","https://openalex.org/I889458895","https://openalex.org/I90610280"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":7,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.37628549,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"38","issue":"6","first_page":"3655","last_page":"3668"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10036","display_name":"Advanced Neural Network Applications","score":0.24889999628067017,"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"}},"topics":[{"id":"https://openalex.org/T10036","display_name":"Advanced Neural Network Applications","score":0.24889999628067017,"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/T11689","display_name":"Adversarial Robustness in Machine Learning","score":0.11909999698400497,"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/T12611","display_name":"Neural Networks and Reservoir Computing","score":0.061799999326467514,"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/noise","display_name":"Noise (video)","score":0.5716999769210815},{"id":"https://openalex.org/keywords/noise-measurement","display_name":"Noise measurement","score":0.36039999127388},{"id":"https://openalex.org/keywords/signal-to-noise-ratio","display_name":"Signal-to-noise ratio (imaging)","score":0.3084999918937683},{"id":"https://openalex.org/keywords/radar-tracker","display_name":"Radar tracker","score":0.30329999327659607},{"id":"https://openalex.org/keywords/signal-processing","display_name":"Signal processing","score":0.29429998993873596},{"id":"https://openalex.org/keywords/gaussian-noise","display_name":"Gaussian noise","score":0.27889999747276306}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7192000150680542},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.5716999769210815},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.43529999256134033},{"id":"https://openalex.org/C29265498","wikidata":"https://www.wikidata.org/wiki/Q7047719","display_name":"Noise measurement","level":3,"score":0.36039999127388},{"id":"https://openalex.org/C13944312","wikidata":"https://www.wikidata.org/wiki/Q7512748","display_name":"Signal-to-noise ratio (imaging)","level":2,"score":0.3084999918937683},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3075999915599823},{"id":"https://openalex.org/C32283439","wikidata":"https://www.wikidata.org/wiki/Q1407014","display_name":"Radar tracker","level":3,"score":0.30329999327659607},{"id":"https://openalex.org/C104267543","wikidata":"https://www.wikidata.org/wiki/Q208163","display_name":"Signal processing","level":3,"score":0.29429998993873596},{"id":"https://openalex.org/C4199805","wikidata":"https://www.wikidata.org/wiki/Q2725903","display_name":"Gaussian noise","level":2,"score":0.27889999747276306},{"id":"https://openalex.org/C100675267","wikidata":"https://www.wikidata.org/wiki/Q1371624","display_name":"Background noise","level":2,"score":0.2768999934196472},{"id":"https://openalex.org/C106516650","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm design","level":2,"score":0.27070000767707825},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.2639999985694885},{"id":"https://openalex.org/C50151734","wikidata":"https://www.wikidata.org/wiki/Q1759577","display_name":"Matched filter","level":3,"score":0.26179999113082886},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.25360000133514404},{"id":"https://openalex.org/C2986577269","wikidata":"https://www.wikidata.org/wiki/Q11306265","display_name":"Random noise","level":2,"score":0.2522999942302704}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/tkde.2026.3678725","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tkde.2026.3678725","pdf_url":null,"source":{"id":"https://openalex.org/S30698027","display_name":"IEEE Transactions on Knowledge and Data Engineering","issn_l":"1041-4347","issn":["1041-4347","1558-2191","2326-3865"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320439","host_organization_name":"IEEE Computer Society","host_organization_lineage":["https://openalex.org/P4310320439","https://openalex.org/P4310319808"],"host_organization_lineage_names":["IEEE Computer Society","Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Knowledge and Data Engineering","raw_type":"journal-article"},{"id":"pmh:oai:repository.hkust.edu.hk:1783.1-172218","is_oa":false,"landing_page_url":"http://repository.hkust.edu.hk/ir/Record/1783.1-172218","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":"Article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G4999280892","display_name":null,"funder_award_id":"62406209","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G5839130649","display_name":null,"funder_award_id":"YT202421","funder_id":"https://openalex.org/F4320335787","funder_display_name":"Fundamental Research Funds for the Central Universities"},{"id":"https://openalex.org/G7020882947","display_name":null,"funder_award_id":"2023A03J0003","funder_id":"https://openalex.org/F4320335480","funder_display_name":"Guangzhou Municipal Science and Technology Project"},{"id":"https://openalex.org/G8792811732","display_name":null,"funder_award_id":"U24B20174","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"},{"id":"https://openalex.org/F4320335480","display_name":"Guangzhou Municipal Science and Technology Project","ror":null},{"id":"https://openalex.org/F4320335787","display_name":"Fundamental Research Funds for the Central Universities","ror":null}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":36,"referenced_works":["https://openalex.org/W1994940238","https://openalex.org/W2106568252","https://openalex.org/W2162630660","https://openalex.org/W2566079294","https://openalex.org/W2907492528","https://openalex.org/W2943605315","https://openalex.org/W2964274690","https://openalex.org/W2964583308","https://openalex.org/W3042609801","https://openalex.org/W3042770487","https://openalex.org/W3081203761","https://openalex.org/W3097300053","https://openalex.org/W3112076981","https://openalex.org/W3116239416","https://openalex.org/W3127659116","https://openalex.org/W3130869292","https://openalex.org/W3134509497","https://openalex.org/W3160381762","https://openalex.org/W3166215705","https://openalex.org/W3173874704","https://openalex.org/W3190486510","https://openalex.org/W3200504467","https://openalex.org/W3208506679","https://openalex.org/W3210378911","https://openalex.org/W4212890525","https://openalex.org/W4287947470","https://openalex.org/W4306830375","https://openalex.org/W4319586442","https://openalex.org/W4321480019","https://openalex.org/W4328008037","https://openalex.org/W4378506766","https://openalex.org/W4380091476","https://openalex.org/W4381327774","https://openalex.org/W4382239899","https://openalex.org/W4387237425","https://openalex.org/W4387848879"],"related_works":[],"abstract_inverted_index":{"Graph":[0],"Neural":[1],"Networks":[2],"(GNNs)":[3],"have":[4],"achieved":[5],"remarkable":[6],"success":[7],"in":[8],"processing":[9],"graph":[10,14,22,65,277],"data.":[11],"However,":[12],"when":[13],"contains":[15],"node":[16,61,134,156,160,172,244,255,271],"label":[17,47,62,162,251],"noise":[18,24,75,245,305,308],"(label":[19],"error)":[20],"and":[21,46,115,126,136,159,290,306],"structural":[23],"(edge":[25],"error),":[26],"the":[27,35,40,77,142,151,166,178,189,206,210,225,241,250,258,267,280,296],"performance":[28],"of":[29,54,74,108,111,122,145,193,209,243,270,298],"GNNs":[30],"will":[31],"severely":[32],"decrease.":[33],"In":[34,91],"learning":[36],"with":[37,174,188,320],"noisy":[38,259],"label,":[39],"methods":[41,56,82],"based":[42],"on":[43,59,224,303],"sample":[44,149],"selection":[45],"generation":[48],"reveal":[49],"promising":[50],"outlook.":[51],"Unfortunately,":[52],"most":[53],"these":[55,81],"only":[57],"focus":[58],"single":[60,304],"nosie":[63],"or":[64],"edge":[66,199,232,260,281],"noise,":[67],"which":[68,128],"cannot":[69],"handle":[70],"both":[71,109],"two":[72,116,123,146],"types":[73,110],"at":[76],"same":[78],"time.":[79],"Furthermore,":[80],"also":[83],"lack":[84],"measures":[85],"for":[86,221],"error":[87,299],"accumulation":[88],"during":[89],"training.":[90],"this":[92],"work,":[93],"we":[94,170,204,248,285],"propose":[95,286],"a":[96],"simple":[97],"yet":[98],"efficient":[99],"method,":[100],"named":[101],"GNN":[102],"Defender":[103],"(GDF),":[104],"to":[105,132,140,184,195,217,256,275,294,325],"address":[106],"challenges":[107],"noises":[112],"through":[113],"cross-correction":[114],"regularization":[117,289,293],"technologies.":[118],"Specifically,":[119],"GDF":[120],"consists":[121],"networks":[124],"(Nnet":[125],"Enet),":[127],"Nnet":[129],"is":[130,138,163,263],"responsible":[131],"predict":[133,141],"category":[135,157,287],"Enet":[137],"used":[139,274],"connected":[143,194,213,254],"probability":[144],"nodes.":[147],"For":[148,201],"selection,":[150],"mean":[152,179,190],"distribution":[153],"distance":[154],"between":[155,212,253],"prediction":[158],"original":[161],"regard":[164],"as":[165,180,215],"selecting":[167],"indicator.":[168],"Then,":[169],"consider":[171],"labels":[173,220,229,272],"distances":[175],"less":[176],"than":[177],"clean":[181,198,207,268],"labels.":[182,246],"Similar":[183],"node,":[185],"replacing":[186],"indicator":[187],"cosine":[191],"similarity":[192],"Adaptively":[196],"complete":[197],"selection.":[200],"cross":[202],"correction,":[203],"use":[205],"probabilities":[208,269],"edges":[211],"nodes":[214,223],"weights":[216],"generate":[218],"pseudo":[219,228],"target":[222],"subgraph.":[226],"The":[227],"generated":[230],"by":[231],"information":[233],"carry":[234],"more":[235],"credible":[236],"supervision":[237],"information,":[238],"thereby":[239],"completing":[240],"correction":[242,282],"Next,":[247],"compare":[249],"consistency":[252,288],"achieve":[257],"correction.":[261],"It":[262],"worth":[264],"noting":[265],"that":[266,311],"are":[273],"smooth":[276],"structure,":[278],"improving":[279],"quality.":[283],"Finally,":[284],"subgraph":[291],"clustering":[292],"weaken":[295],"impact":[297],"accumulation.":[300],"Extensive":[301],"experiments":[302],"mixed":[307],"datasets":[309],"show":[310],"our":[312],"proposed":[313],"framework":[314],"far":[315],"outperforms":[316],"current":[317],"baseline":[318],"methods,":[319],"improvements":[321],"ranging":[322],"from":[323],"1.43%":[324],"14.72%.":[326]},"counts_by_year":[],"updated_date":"2026-07-22T07:51:19.307946","created_date":"2026-03-31T00:00:00"}