{"id":"https://openalex.org/W4401857439","doi":"https://doi.org/10.1145/3637528.3671798","title":"Divide and Denoise: Empowering Simple Models for Robust Semi-Supervised Node Classification against Label Noise","display_name":"Divide and Denoise: Empowering Simple Models for Robust Semi-Supervised Node Classification against Label Noise","publication_year":2024,"publication_date":"2024-08-24","ids":{"openalex":"https://openalex.org/W4401857439","doi":"https://doi.org/10.1145/3637528.3671798"},"language":"en","primary_location":{"id":"doi:10.1145/3637528.3671798","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3637528.3671798","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3637528.3671798","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 30th ACM SIGKDD Conference on Knowledge Discovery and Data Mining","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/10.1145/3637528.3671798","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5044455276","display_name":"Kaize Ding","orcid":"https://orcid.org/0000-0001-6684-6752"},"institutions":[{"id":"https://openalex.org/I111979921","display_name":"Northwestern University","ror":"https://ror.org/000e0be47","country_code":"US","type":"education","lineage":["https://openalex.org/I111979921"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Kaize Ding","raw_affiliation_strings":["Northwestern University, Evanston, USA"],"affiliations":[{"raw_affiliation_string":"Northwestern University, Evanston, USA","institution_ids":["https://openalex.org/I111979921"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5085139646","display_name":"Xiaoxiao Ma","orcid":"https://orcid.org/0000-0003-1270-4155"},"institutions":[{"id":"https://openalex.org/I99043593","display_name":"Macquarie University","ror":"https://ror.org/01sf06y89","country_code":"AU","type":"education","lineage":["https://openalex.org/I99043593"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Xiaoxiao Ma","raw_affiliation_strings":["Macquarie University, Sydney, Australia"],"affiliations":[{"raw_affiliation_string":"Macquarie University, Sydney, Australia","institution_ids":["https://openalex.org/I99043593"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100386682","display_name":"Yixin Liu","orcid":"https://orcid.org/0000-0002-4309-5076"},"institutions":[{"id":"https://openalex.org/I56590836","display_name":"Monash University","ror":"https://ror.org/02bfwt286","country_code":"AU","type":"education","lineage":["https://openalex.org/I56590836"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Yixin Liu","raw_affiliation_strings":["Monash University, Melbourne, Australia"],"affiliations":[{"raw_affiliation_string":"Monash University, Melbourne, Australia","institution_ids":["https://openalex.org/I56590836"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5008056593","display_name":"Shirui Pan","orcid":"https://orcid.org/0000-0003-0794-527X"},"institutions":[{"id":"https://openalex.org/I11701301","display_name":"Griffith University","ror":"https://ror.org/02sc3r913","country_code":"AU","type":"education","lineage":["https://openalex.org/I11701301"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Shirui Pan","raw_affiliation_strings":["Griffith University, Gold Coast, Australia"],"affiliations":[{"raw_affiliation_string":"Griffith University, Gold Coast, Australia","institution_ids":["https://openalex.org/I11701301"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5044455276"],"corresponding_institution_ids":["https://openalex.org/I111979921"],"apc_list":null,"apc_paid":null,"fwci":2.4326,"has_fulltext":false,"cited_by_count":7,"citation_normalized_percentile":{"value":0.90359227,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":90,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"574","last_page":"584"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11273","display_name":"Advanced Graph Neural Networks","score":0.9998000264167786,"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":0.9998000264167786,"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/T12535","display_name":"Machine Learning and Data Classification","score":0.9944999814033508,"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/T12761","display_name":"Data Stream Mining Techniques","score":0.9735999703407288,"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/overfitting","display_name":"Overfitting","score":0.8162951469421387},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7891215085983276},{"id":"https://openalex.org/keywords/leverage","display_name":"Leverage (statistics)","score":0.5544631481170654},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5209125876426697},{"id":"https://openalex.org/keywords/graph","display_name":"Graph","score":0.5021085739135742},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.4945513904094696},{"id":"https://openalex.org/keywords/noise","display_name":"Noise (video)","score":0.4793891906738281},{"id":"https://openalex.org/keywords/node","display_name":"Node (physics)","score":0.47751158475875854},{"id":"https://openalex.org/keywords/message-passing","display_name":"Message passing","score":0.4677194654941559},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.4244208335876465},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.30799245834350586},{"id":"https://openalex.org/keywords/theoretical-computer-science","display_name":"Theoretical computer science","score":0.27318286895751953},{"id":"https://openalex.org/keywords/distributed-computing","display_name":"Distributed computing","score":0.08105248212814331}],"concepts":[{"id":"https://openalex.org/C22019652","wikidata":"https://www.wikidata.org/wiki/Q331309","display_name":"Overfitting","level":3,"score":0.8162951469421387},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7891215085983276},{"id":"https://openalex.org/C153083717","wikidata":"https://www.wikidata.org/wiki/Q6535263","display_name":"Leverage (statistics)","level":2,"score":0.5544631481170654},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5209125876426697},{"id":"https://openalex.org/C132525143","wikidata":"https://www.wikidata.org/wiki/Q141488","display_name":"Graph","level":2,"score":0.5021085739135742},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.4945513904094696},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.4793891906738281},{"id":"https://openalex.org/C62611344","wikidata":"https://www.wikidata.org/wiki/Q1062658","display_name":"Node (physics)","level":2,"score":0.47751158475875854},{"id":"https://openalex.org/C854659","wikidata":"https://www.wikidata.org/wiki/Q1859284","display_name":"Message passing","level":2,"score":0.4677194654941559},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.4244208335876465},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.30799245834350586},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.27318286895751953},{"id":"https://openalex.org/C120314980","wikidata":"https://www.wikidata.org/wiki/Q180634","display_name":"Distributed computing","level":1,"score":0.08105248212814331},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.0},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.0},{"id":"https://openalex.org/C13280743","wikidata":"https://www.wikidata.org/wiki/Q131089","display_name":"Geodesy","level":1,"score":0.0},{"id":"https://openalex.org/C205649164","wikidata":"https://www.wikidata.org/wiki/Q1071","display_name":"Geography","level":0,"score":0.0},{"id":"https://openalex.org/C66938386","wikidata":"https://www.wikidata.org/wiki/Q633538","display_name":"Structural engineering","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1145/3637528.3671798","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3637528.3671798","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3637528.3671798","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 30th ACM SIGKDD Conference on Knowledge Discovery and Data Mining","raw_type":"proceedings-article"},{"id":"pmh:oai:research-repository.griffith.edu.au:10072/432600","is_oa":true,"landing_page_url":"https://hdl.handle.net/10072/432600","pdf_url":null,"source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"Conference output"}],"best_oa_location":{"id":"doi:10.1145/3637528.3671798","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3637528.3671798","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3637528.3671798","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 30th ACM SIGKDD Conference on Knowledge Discovery and Data Mining","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4401857439.pdf"},"referenced_works_count":18,"referenced_works":["https://openalex.org/W2906836970","https://openalex.org/W2998269939","https://openalex.org/W2998496395","https://openalex.org/W3021975806","https://openalex.org/W3035666843","https://openalex.org/W3042770487","https://openalex.org/W3094624443","https://openalex.org/W3099375322","https://openalex.org/W3100078588","https://openalex.org/W3156441686","https://openalex.org/W3156449551","https://openalex.org/W3166215705","https://openalex.org/W4225657277","https://openalex.org/W4311079930","https://openalex.org/W4315588234","https://openalex.org/W4321480019","https://openalex.org/W4378942422","https://openalex.org/W4382239158"],"related_works":["https://openalex.org/W4362597605","https://openalex.org/W1574414179","https://openalex.org/W4297676672","https://openalex.org/W3009056573","https://openalex.org/W2922073769","https://openalex.org/W4281702477","https://openalex.org/W2490526372","https://openalex.org/W4376166922","https://openalex.org/W4378510483","https://openalex.org/W4221142204"],"abstract_inverted_index":{"Graph":[0],"neural":[1],"networks":[2],"(GNNs)":[3],"based":[4],"on":[5,32,207,227],"message":[6,119],"passing":[7,120],"have":[8],"achieved":[9],"remarkable":[10],"performance":[11,31],"in":[12,60,125,218],"graph":[13,88,184],"machine":[14],"learning.":[15],"By":[16],"combining":[17],"it":[18],"with":[19,234],"the":[20,30,33,45,65,70,83,87,91,96,104,115,126,137,154,174,192,199,220],"power":[21],"of":[22,35,73,117,194,202,237],"pseudo":[23,98,123,185,204],"labeling,":[24],"one":[25],"can":[26,76,189,212],"further":[27],"push":[28],"forward":[29],"task":[34],"semi-supervised":[36,231],"node":[37,47,232],"classification.":[38],"However,":[39],"most":[40],"existing":[41],"works":[42],"assume":[43],"that":[44,152,188],"training":[46,67],"labels":[48,68,99,124,169],"are":[49],"purely":[50],"noise-free,":[51],"while":[52,197],"this":[53,111,162],"strong":[54],"assumption":[55],"usually":[56],"does":[57],"not":[58],"hold":[59],"practice.":[61],"GNNs":[62],"will":[63],"overfit":[64],"noisy":[66,97,168,203],"and":[69,121,129,140,170,216,240],"adverse":[71,200],"effects":[72,201],"mislabeled":[74],"nodes":[75,85,196],"be":[77],"exaggerated":[78],"by":[79],"being":[80],"propagated":[81],"to":[82,131,167],"remaining":[84],"through":[86],"structure,":[89],"exacerbating":[90],"model":[92,138],"failure.":[93],"Worse":[94],"still,":[95],"could":[100],"also":[101,171],"largely":[102],"undermine":[103],"model's":[105],"reliability":[106],"without":[107],"special":[108],"treatment.":[109],"In":[110],"paper,":[112],"we":[113,145,179,211],"revisit":[114],"role":[116],"(1)":[118],"(2)":[122],"studied":[127,221],"problem":[128],"try":[130],"address":[132],"two":[133],"denoising":[134],"subproblems":[135],"from":[136],"architecture":[139],"algorithm":[141,187],"perspective,":[142],"respectively.":[143],"Specifically,":[144],"first":[146],"develop":[147],"a":[148,181],"label-noise":[149],"robust":[150],"GNN":[151],"discards":[153],"coupled":[155],"message-passing":[156],"scheme.":[157],"Despite":[158],"its":[159],"simple":[160],"architecture,":[161],"learning":[163],"backbone":[164],"prevents":[165],"overfitting":[166],"inherently":[172],"avoids":[173],"noise":[175,239],"propagation":[176],"issue.":[177],"Moreover,":[178],"propose":[180],"novel":[182,209],"reliable":[183],"labeling":[186],"effectively":[190],"leverage":[191],"knowledge":[193],"unlabeled":[195],"mitigating":[198],"labels.":[205],"Based":[206],"those":[208],"designs,":[210],"attain":[213],"exceptional":[214],"effectiveness":[215],"efficiency":[217],"solving":[219],"problem.":[222],"We":[223],"conduct":[224],"extensive":[225],"experiments":[226],"benchmark":[228],"datasets":[229],"for":[230],"classification":[233],"different":[235],"levels":[236],"label":[238],"show":[241],"new":[242],"state-of-the-art":[243],"performance.":[244],"The":[245],"code":[246],"is":[247],"available":[248],"at":[249],"https://github.com/DND-NET/DND-NET.":[250]},"counts_by_year":[{"year":2025,"cited_by_count":6},{"year":2024,"cited_by_count":1}],"updated_date":"2026-03-27T05:58:40.876381","created_date":"2025-10-10T00:00:00"}