{"id":"https://openalex.org/W4212890525","doi":"https://doi.org/10.1145/3488560.3498408","title":"Towards Robust Graph Neural Networks for Noisy Graphs with Sparse Labels","display_name":"Towards Robust Graph Neural Networks for Noisy Graphs with Sparse Labels","publication_year":2022,"publication_date":"2022-02-11","ids":{"openalex":"https://openalex.org/W4212890525","doi":"https://doi.org/10.1145/3488560.3498408"},"language":"en","primary_location":{"id":"doi:10.1145/3488560.3498408","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3488560.3498408","pdf_url":null,"source":{"id":"https://openalex.org/S4363608885","display_name":"Proceedings of the Fifteenth ACM International Conference on Web Search 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 Fifteenth ACM International Conference on Web Search and Data Mining","raw_type":"proceedings-article"},"type":"conference-paper","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/A5091395218","display_name":"Enyan Dai","orcid":"https://orcid.org/0000-0001-9715-0280"},"institutions":[{"id":"https://openalex.org/I130769515","display_name":"Pennsylvania State University","ror":"https://ror.org/04p491231","country_code":"US","type":"education","lineage":["https://openalex.org/I130769515"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Enyan Dai","raw_affiliation_strings":["The Pennsylvania State University, State College, PA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"The Pennsylvania State University, State College, PA, USA","institution_ids":["https://openalex.org/I130769515"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100758371","display_name":"Wei Jin","orcid":"https://orcid.org/0000-0002-5054-954X"},"institutions":[{"id":"https://openalex.org/I87216513","display_name":"Michigan State University","ror":"https://ror.org/05hs6h993","country_code":"US","type":"education","lineage":["https://openalex.org/I87216513"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Wei Jin","raw_affiliation_strings":["Michigan State University, East Lansing, MI, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Michigan State University, East Lansing, MI, USA","institution_ids":["https://openalex.org/I87216513"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101566727","display_name":"Hui Liu","orcid":"https://orcid.org/0000-0002-3555-3495"},"institutions":[{"id":"https://openalex.org/I87216513","display_name":"Michigan State University","ror":"https://ror.org/05hs6h993","country_code":"US","type":"education","lineage":["https://openalex.org/I87216513"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Hui Liu","raw_affiliation_strings":["Michigan State University, East Lansing, MI, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Michigan State University, East Lansing, MI, USA","institution_ids":["https://openalex.org/I87216513"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5011048500","display_name":"Suhang Wang","orcid":"https://orcid.org/0000-0003-3448-4878"},"institutions":[{"id":"https://openalex.org/I130769515","display_name":"Pennsylvania State University","ror":"https://ror.org/04p491231","country_code":"US","type":"education","lineage":["https://openalex.org/I130769515"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Suhang Wang","raw_affiliation_strings":["The Pennsylvania State University, State College, PA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"The Pennsylvania State University, State College, PA, USA","institution_ids":["https://openalex.org/I130769515"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":14.3278,"has_fulltext":false,"cited_by_count":101,"citation_normalized_percentile":{"value":0.99261365,"is_in_top_1_percent":true,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":97,"max":100},"biblio":{"volume":null,"issue":null,"first_page":"181","last_page":"191"},"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":0.9837999939918518,"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/T10203","display_name":"Recommender Systems and Techniques","score":0.9725000262260437,"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/computer-science","display_name":"Computer science","score":0.7848155498504639},{"id":"https://openalex.org/keywords/robustness","display_name":"Robustness (evolution)","score":0.5803050994873047},{"id":"https://openalex.org/keywords/graph","display_name":"Graph","score":0.48572617769241333},{"id":"https://openalex.org/keywords/message-passing","display_name":"Message passing","score":0.4806636571884155},{"id":"https://openalex.org/keywords/deep-neural-networks","display_name":"Deep neural networks","score":0.4655293822288513},{"id":"https://openalex.org/keywords/theoretical-computer-science","display_name":"Theoretical computer science","score":0.46492481231689453},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4237833321094513},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.4210949242115021},{"id":"https://openalex.org/keywords/dense-graph","display_name":"Dense graph","score":0.41857901215553284},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.3928489685058594},{"id":"https://openalex.org/keywords/distributed-computing","display_name":"Distributed computing","score":0.16737687587738037},{"id":"https://openalex.org/keywords/pathwidth","display_name":"Pathwidth","score":0.07957801222801208},{"id":"https://openalex.org/keywords/line-graph","display_name":"Line graph","score":0.07788491249084473}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7848155498504639},{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.5803050994873047},{"id":"https://openalex.org/C132525143","wikidata":"https://www.wikidata.org/wiki/Q141488","display_name":"Graph","level":2,"score":0.48572617769241333},{"id":"https://openalex.org/C854659","wikidata":"https://www.wikidata.org/wiki/Q1859284","display_name":"Message passing","level":2,"score":0.4806636571884155},{"id":"https://openalex.org/C2984842247","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep neural networks","level":3,"score":0.4655293822288513},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.46492481231689453},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4237833321094513},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.4210949242115021},{"id":"https://openalex.org/C13251829","wikidata":"https://www.wikidata.org/wiki/Q3085841","display_name":"Dense graph","level":5,"score":0.41857901215553284},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3928489685058594},{"id":"https://openalex.org/C120314980","wikidata":"https://www.wikidata.org/wiki/Q180634","display_name":"Distributed computing","level":1,"score":0.16737687587738037},{"id":"https://openalex.org/C43517604","wikidata":"https://www.wikidata.org/wiki/Q7144893","display_name":"Pathwidth","level":4,"score":0.07957801222801208},{"id":"https://openalex.org/C203776342","wikidata":"https://www.wikidata.org/wiki/Q1378376","display_name":"Line graph","level":3,"score":0.07788491249084473},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0},{"id":"https://openalex.org/C55493867","wikidata":"https://www.wikidata.org/wiki/Q7094","display_name":"Biochemistry","level":1,"score":0.0},{"id":"https://openalex.org/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3488560.3498408","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3488560.3498408","pdf_url":null,"source":{"id":"https://openalex.org/S4363608885","display_name":"Proceedings of the Fifteenth ACM International Conference on Web Search 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 Fifteenth ACM International Conference on Web Search and Data Mining","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G125128811","display_name":null,"funder_award_id":"W911NF-2110198","funder_id":"https://openalex.org/F4320338281","funder_display_name":"Army Research Office"},{"id":"https://openalex.org/G1950507725","display_name":"III: Medium: Collaborative Research: Towards Scalable and Interpretable Graph Neural Networks","funder_award_id":"1955851","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/F4320338281","display_name":"Army Research Office","ror":"https://ror.org/05epdh915"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":27,"referenced_works":["https://openalex.org/W1837843568","https://openalex.org/W2099352187","https://openalex.org/W2162630660","https://openalex.org/W2605350416","https://openalex.org/W2803831897","https://openalex.org/W2890187992","https://openalex.org/W2932399282","https://openalex.org/W2945827377","https://openalex.org/W2948729509","https://openalex.org/W2963084622","https://openalex.org/W2963911286","https://openalex.org/W2994598354","https://openalex.org/W2998122931","https://openalex.org/W2999817249","https://openalex.org/W3081203761","https://openalex.org/W3093551363","https://openalex.org/W3098276446","https://openalex.org/W3099064659","https://openalex.org/W3101553402","https://openalex.org/W3104667978","https://openalex.org/W3117178429","https://openalex.org/W3125182500","https://openalex.org/W3134509497","https://openalex.org/W3166215705","https://openalex.org/W3207981989","https://openalex.org/W6602452458","https://openalex.org/W6733130978"],"related_works":["https://openalex.org/W2978729728","https://openalex.org/W4288966080","https://openalex.org/W2770593030","https://openalex.org/W3154990682","https://openalex.org/W2551042189","https://openalex.org/W3210882018","https://openalex.org/W2970990331","https://openalex.org/W4379116102","https://openalex.org/W3207178610","https://openalex.org/W3211782752"],"abstract_inverted_index":{"Graph":[0],"Neural":[1],"Networks":[2],"(GNNs)":[3],"have":[4,22],"shown":[5],"their":[6],"great":[7],"ability":[8],"in":[9],"modeling":[10],"graph":[11],"structured":[12],"data.":[13],"However,":[14,59],"real-world":[15,170],"graphs":[16,79,181],"usually":[17],"contain":[18],"structure":[19],"noises":[20],"and":[21,92,123,133],"limited":[23,56,81,93,144,183],"labeled":[24,57,82,94,145,184],"nodes.":[25,58,83,146,185],"The":[26,147],"performance":[27],"of":[28,42,73,101,137,143,157,175],"GNNs":[29,43,54,76,138],"would":[30],"drop":[31],"significantly":[32],"when":[33],"trained":[34],"on":[35,44,62,77,169,179],"such":[36],"graphs,":[37],"which":[38,112,126],"hinders":[39],"the":[40,60,89,98,114,141,155,173,176],"adoption":[41],"many":[45],"applications.":[46],"Thus,":[47],"it":[48],"is":[49,64],"important":[50],"to":[51,119,139,153,163],"develop":[52],"noise-resistant":[53],"with":[55,80,160,182],"work":[61],"this":[63],"rather":[65],"limited.":[66],"Therefore,":[67],"we":[68,107],"study":[69],"a":[70,109,121],"novel":[71,110],"problem":[72],"developing":[74],"robust":[75],"noisy":[78,90,115,131,180],"Our":[84],"analysis":[85],"shows":[86],"that":[87],"both":[88],"edges":[91,116,132,149],"nodes":[95,159],"could":[96],"harm":[97],"message-passing":[99],"mechanism":[100],"GNNs.":[102,166],"To":[103],"mitigate":[104],"these":[105],"issues,":[106],"propose":[108],"framework":[111,178],"adopts":[113],"as":[117],"supervision":[118],"learn":[120],"denoised":[122],"dense":[124],"graph,":[125],"can":[127],"down-weight":[128],"or":[129],"eliminate":[130],"facilitate":[134],"message":[135],"passing":[136],"alleviate":[140],"issue":[142],"generated":[148],"are":[150],"further":[151],"used":[152],"regularize":[154],"predictions":[156],"unlabeled":[158],"label":[161],"smoothness":[162],"better":[164],"train":[165],"Experimental":[167],"results":[168],"datasets":[171],"demonstrate":[172],"robustness":[174],"proposed":[177]},"counts_by_year":[{"year":2026,"cited_by_count":16},{"year":2025,"cited_by_count":30},{"year":2024,"cited_by_count":28},{"year":2023,"cited_by_count":23},{"year":2022,"cited_by_count":4}],"updated_date":"2026-08-08T01:25:22.217667","created_date":"2025-10-10T00:00:00"}