{"id":"https://openalex.org/W4399455308","doi":"https://doi.org/10.48550/arxiv.2406.04299","title":"NoisyGL: A Comprehensive Benchmark for Graph Neural Networks under Label\n Noise","display_name":"NoisyGL: A Comprehensive Benchmark for Graph Neural Networks under Label\n Noise","publication_year":2024,"publication_date":"2024-06-06","ids":{"openalex":"https://openalex.org/W4399455308","doi":"https://doi.org/10.48550/arxiv.2406.04299"},"language":"en","primary_location":{"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2406.04299","pdf_url":"https://arxiv.org/pdf/2406.04299","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":["Cornell University"],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false},"type":"preprint","type_crossref":"posted-content","indexed_in":["arxiv"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2406.04299","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5101635344","display_name":"Zhonghao Wang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Wang, Zhonghao","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100889203","display_name":"Danyu Sun","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Sun, Danyu","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5082049699","display_name":"Sheng Zhou","orcid":"https://orcid.org/0000-0002-6675-3991"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zhou, Sheng","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5049707744","display_name":"Haobo Wang","orcid":"https://orcid.org/0000-0001-8586-3048"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Wang, Haobo","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5000936207","display_name":"Jiapei Fan","orcid":"https://orcid.org/0000-0003-3194-025X"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Fan, Jiapei","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5058197951","display_name":"Longtao Huang","orcid":"https://orcid.org/0000-0002-0517-1592"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Huang, Longtao","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5052757755","display_name":"Jiajun Bu","orcid":"https://orcid.org/0000-0002-1097-2044"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Bu, Jiajun","raw_affiliation_strings":[],"affiliations":[]}],"institution_assertions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.0,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":0,"max":84},"biblio":{"volume":null,"issue":null,"first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"primary_topic":{"id":"https://openalex.org/T12535","display_name":"Machine Learning and Data Classification","score":0.9604,"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/T12535","display_name":"Machine Learning and Data Classification","score":0.9604,"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/T11273","display_name":"Advanced Graph Neural Networks","score":0.931,"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/benchmark","display_name":"Benchmark (surveying)","score":0.6751475}],"concepts":[{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.6751475},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.53630435},{"id":"https://openalex.org/C132525143","wikidata":"https://www.wikidata.org/wiki/Q141488","display_name":"Graph","level":2,"score":0.5007918},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.48057938},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.45394284},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.38467038},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.257121},{"id":"https://openalex.org/C205649164","wikidata":"https://www.wikidata.org/wiki/Q1071","display_name":"Geography","level":0,"score":0.087887704},{"id":"https://openalex.org/C58640448","wikidata":"https://www.wikidata.org/wiki/Q42515","display_name":"Cartography","level":1,"score":0.05739528},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2406.04299","pdf_url":"https://arxiv.org/pdf/2406.04299","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":["Cornell University"],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false}],"best_oa_location":{"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2406.04299","pdf_url":"https://arxiv.org/pdf/2406.04299","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":["Cornell University"],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false},"sustainable_development_goals":[],"grants":[],"datasets":[],"versions":[],"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W972276598","https://openalex.org/W4321353415","https://openalex.org/W4246352526","https://openalex.org/W2745001401","https://openalex.org/W2378211422","https://openalex.org/W2130974462","https://openalex.org/W2121910908","https://openalex.org/W2087343574","https://openalex.org/W2086519370","https://openalex.org/W2028665553"],"abstract_inverted_index":{"Graph":[0,64],"Neural":[1,65],"Networks":[2,66],"(GNNs)":[3],"exhibit":[4],"strong":[5],"potential":[6],"in":[7,29,44,79,110,158,183,194],"node":[8,22],"classification":[9],"task":[10],"through":[11],"a":[12,91],"message-passing":[13],"mechanism.":[14],"However,":[15,75],"their":[16],"performance":[17],"often":[18],"hinges":[19],"on":[20,134],"high-quality":[21],"labels,":[23],"which":[24,94],"are":[25],"challenging":[26],"to":[27,33,77],"obtain":[28],"real-world":[30,45],"scenarios":[31],"due":[32,76],"unreliable":[34],"sources":[35],"or":[36],"adversarial":[37],"attacks.":[38],"Consequently,":[39],"label":[40,122],"noise":[41],"is":[42],"common":[43],"graph":[46,118,137],"data,":[47],"negatively":[48],"impacting":[49],"GNNs":[50],"by":[51],"propagating":[52],"incorrect":[53],"information":[54],"during":[55],"training.":[56],"To":[57,103],"address":[58],"this":[59,105,111,184],"issue,":[60],"the":[61,87,113,189],"study":[62],"of":[63,101,131,188],"under":[67,121],"Label":[68],"Noise":[69],"(GLN)":[70],"has":[71,150],"recently":[72],"gained":[73],"traction.":[74],"variations":[78],"dataset":[80],"selection,":[81],"data":[82,138],"splitting,":[83],"and":[84,98,128,146,161],"preprocessing":[85],"techniques,":[86],"community":[88],"currently":[89],"lacks":[90],"comprehensive":[92,115],"benchmark,":[93],"impedes":[95],"deeper":[96],"understanding":[97],"further":[99,181],"development":[100],"GLN.":[102],"fill":[104],"gap,":[106],"we":[107,162],"introduce":[108],"NoisyGL":[109,124],"paper,":[112],"first":[114],"benchmark":[116,149,177,190],"for":[117,170],"neural":[119],"networks":[120],"noise.":[123],"enables":[125],"fair":[126],"comparisons":[127],"detailed":[129],"analyses":[130],"GLN":[132],"methods":[133],"noisy":[135],"labeled":[136],"across":[139],"various":[140],"datasets,":[141],"with":[142],"unified":[143],"experimental":[144],"settings":[145],"interface.":[147],"Our":[148],"uncovered":[151],"several":[152],"important":[153],"insights":[154],"that":[155],"were":[156],"missed":[157],"previous":[159],"research,":[160],"believe":[163],"these":[164],"findings":[165],"will":[166,179],"be":[167,192],"highly":[168],"beneficial":[169],"future":[171],"studies.":[172],"We":[173],"hope":[174],"our":[175],"open-source":[176],"library":[178],"foster":[180],"advancements":[182],"field.":[185],"The":[186],"code":[187],"can":[191],"found":[193],"https://github.com/eaglelab-zju/NoisyGL.":[195]},"cited_by_api_url":"https://api.openalex.org/works?filter=cites:W4399455308","counts_by_year":[],"updated_date":"2024-12-24T02:16:00.610117","created_date":"2024-06-08"}