{"id":"https://openalex.org/W2978012698","doi":"https://doi.org/10.1109/ijcnn.2019.8851920","title":"Identifying Mislabeled Instances in Classification Datasets","display_name":"Identifying Mislabeled Instances in Classification Datasets","publication_year":2019,"publication_date":"2019-07-01","ids":{"openalex":"https://openalex.org/W2978012698","doi":"https://doi.org/10.1109/ijcnn.2019.8851920","mag":"2978012698"},"language":"en","primary_location":{"id":"doi:10.1109/ijcnn.2019.8851920","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ijcnn.2019.8851920","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2019 International Joint Conference on Neural Networks (IJCNN)","raw_type":"proceedings-article"},"type":"article","indexed_in":["arxiv","crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/1912.05283","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":null,"display_name":"Nicolas M. Muller","orcid":null},"institutions":[{"id":"https://openalex.org/I4210136922","display_name":"Fraunhofer Institute for Applied and Integrated Security","ror":"https://ror.org/03w0bbr97","country_code":"DE","type":"facility","lineage":["https://openalex.org/I4210136922","https://openalex.org/I4923324"]}],"countries":["DE"],"is_corresponding":true,"raw_author_name":"Nicolas M. Muller","raw_affiliation_strings":["Cognitive Security Technologies, Fraunhofer AISEC, Garching, 85748, Germany"],"affiliations":[{"raw_affiliation_string":"Cognitive Security Technologies, Fraunhofer AISEC, Garching, 85748, Germany","institution_ids":["https://openalex.org/I4210136922"]}]},{"author_position":"last","author":{"id":null,"display_name":"Karla Markert","orcid":null},"institutions":[{"id":"https://openalex.org/I4210136922","display_name":"Fraunhofer Institute for Applied and Integrated Security","ror":"https://ror.org/03w0bbr97","country_code":"DE","type":"facility","lineage":["https://openalex.org/I4210136922","https://openalex.org/I4923324"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Karla Markert","raw_affiliation_strings":["Cognitive Security Technologies, Fraunhofer AISEC, Garching, 85748, Germany"],"affiliations":[{"raw_affiliation_string":"Cognitive Security Technologies, Fraunhofer AISEC, Garching, 85748, Germany","institution_ids":["https://openalex.org/I4210136922"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I4210136922"],"apc_list":null,"apc_paid":null,"fwci":1.3007,"has_fulltext":false,"cited_by_count":27,"citation_normalized_percentile":{"value":0.85845826,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":94,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"8"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12535","display_name":"Machine Learning and Data Classification","score":0.9998999834060669,"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":0.9998999834060669,"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/T12072","display_name":"Machine Learning and Algorithms","score":0.9961000084877014,"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/T11652","display_name":"Imbalanced Data Classification Techniques","score":0.9901999831199646,"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/pipeline","display_name":"Pipeline (software)","score":0.5874000191688538},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.5303999781608582},{"id":"https://openalex.org/keywords/key","display_name":"Key (lock)","score":0.5189999938011169},{"id":"https://openalex.org/keywords/domain","display_name":"Domain (mathematical analysis)","score":0.4997999966144562},{"id":"https://openalex.org/keywords/labeled-data","display_name":"Labeled data","score":0.47909998893737793},{"id":"https://openalex.org/keywords/code","display_name":"Code (set theory)","score":0.4650999903678894},{"id":"https://openalex.org/keywords/noise","display_name":"Noise (video)","score":0.4571000039577484}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8149999976158142},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6144999861717224},{"id":"https://openalex.org/C43521106","wikidata":"https://www.wikidata.org/wiki/Q2165493","display_name":"Pipeline (software)","level":2,"score":0.5874000191688538},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.5467000007629395},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.5303999781608582},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.5189999938011169},{"id":"https://openalex.org/C36503486","wikidata":"https://www.wikidata.org/wiki/Q11235244","display_name":"Domain (mathematical analysis)","level":2,"score":0.4997999966144562},{"id":"https://openalex.org/C2776145971","wikidata":"https://www.wikidata.org/wiki/Q30673951","display_name":"Labeled data","level":2,"score":0.47909998893737793},{"id":"https://openalex.org/C2776760102","wikidata":"https://www.wikidata.org/wiki/Q5139990","display_name":"Code (set theory)","level":3,"score":0.4650999903678894},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.4571000039577484},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.4271000027656555},{"id":"https://openalex.org/C136389625","wikidata":"https://www.wikidata.org/wiki/Q334384","display_name":"Supervised learning","level":3,"score":0.4246000051498413},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.3955000042915344},{"id":"https://openalex.org/C207685749","wikidata":"https://www.wikidata.org/wiki/Q2088941","display_name":"Domain knowledge","level":2,"score":0.35690000653266907},{"id":"https://openalex.org/C2781170535","wikidata":"https://www.wikidata.org/wiki/Q30587856","display_name":"Noisy data","level":2,"score":0.35120001435279846},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3165000081062317},{"id":"https://openalex.org/C195324797","wikidata":"https://www.wikidata.org/wiki/Q33742","display_name":"Natural language","level":2,"score":0.2623000144958496},{"id":"https://openalex.org/C41458344","wikidata":"https://www.wikidata.org/wiki/Q732577","display_name":"Publication","level":2,"score":0.2567000091075897},{"id":"https://openalex.org/C43126263","wikidata":"https://www.wikidata.org/wiki/Q128751","display_name":"Source code","level":2,"score":0.2529999911785126}],"mesh":[],"locations_count":4,"locations":[{"id":"doi:10.1109/ijcnn.2019.8851920","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ijcnn.2019.8851920","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2019 International Joint Conference on Neural Networks (IJCNN)","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:1912.05283","is_oa":true,"landing_page_url":"http://arxiv.org/abs/1912.05283","pdf_url":"https://arxiv.org/pdf/1912.05283","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":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"pmh:oai:fraunhofer.de:N-568435","is_oa":false,"landing_page_url":"http://publica.fraunhofer.de/documents/N-568435.html","pdf_url":null,"source":{"id":"https://openalex.org/S4306400801","display_name":"Publikationsdatenbank der Fraunhofer-Gesellschaft (Fraunhofer-Gesellschaft)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I4923324","host_organization_name":"Fraunhofer-Gesellschaft","host_organization_lineage":["https://openalex.org/I4923324"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Fraunhofer AISEC","raw_type":"Conference Paper"},{"id":"pmh:oai:publica.fraunhofer.de:publica/405876","is_oa":false,"landing_page_url":"https://publica.fraunhofer.de/handle/publica/405876","pdf_url":null,"source":{"id":"https://openalex.org/S4306400318","display_name":"Fraunhofer-Publica (Fraunhofer-Gesellschaft)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I4923324","host_organization_name":"Fraunhofer-Gesellschaft","host_organization_lineage":["https://openalex.org/I4923324"],"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":"conference paper"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:1912.05283","is_oa":true,"landing_page_url":"http://arxiv.org/abs/1912.05283","pdf_url":"https://arxiv.org/pdf/1912.05283","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":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":25,"referenced_works":["https://openalex.org/W1666942233","https://openalex.org/W1670346950","https://openalex.org/W2007339694","https://openalex.org/W2015887370","https://openalex.org/W2036166268","https://openalex.org/W2068303084","https://openalex.org/W2085988980","https://openalex.org/W2102776287","https://openalex.org/W2167460663","https://openalex.org/W2285776716","https://openalex.org/W2592335154","https://openalex.org/W2767543837","https://openalex.org/W2772138765","https://openalex.org/W2902284233","https://openalex.org/W2947137296","https://openalex.org/W4300601563","https://openalex.org/W6675354045","https://openalex.org/W6676984168","https://openalex.org/W6682132143","https://openalex.org/W6682691769","https://openalex.org/W6703116779","https://openalex.org/W6743688258","https://openalex.org/W6747898760","https://openalex.org/W6751795773","https://openalex.org/W6787972765"],"related_works":[],"abstract_inverted_index":{"A":[0],"key":[1],"requirement":[2],"for":[3],"supervised":[4],"machine":[5],"learning":[6],"is":[7,12,55,66],"labeled":[8,63],"training":[9],"data,":[10],"which":[11],"created":[13],"by":[14,32,39,106],"annotating":[15],"unlabeled":[16],"data":[17],"with":[18,124],"the":[19,160],"appropriate":[20],"class.":[21],"Because":[22],"this":[23,79,84],"process":[24,44],"can":[25],"in":[26,50,83,94,152],"many":[27,71],"cases":[28],"not":[29],"be":[30,37,47],"done":[31],"machines,":[33],"labeling":[34],"needs":[35],"to":[36,46,57,90,114,144],"performed":[38],"human":[40],"domain":[41],"experts.":[42],"This":[43],"tends":[45],"expensive":[48],"both":[49],"time":[51],"and":[52,54,97,117,148,155,162],"money,":[53],"prone":[56],"errors.":[58],"Additionally,":[59],"reviewing":[60,133],"an":[61,125,163],"entire":[62],"dataset":[64],"manually":[65],"often":[67],"prohibitively":[68],"costly,":[69],"so":[70],"real":[72],"world":[73],"datasets":[74,147],"contain":[75],"mislabeled":[76,92,122,150],"instances.To":[77],"address":[78],"issue,":[80],"we":[81,120,158],"present":[82],"paper":[85],"a":[86,108],"non-parametric":[87],"end-to-end":[88],"pipeline":[89],"find":[91,121,149],"instances":[93,123,151],"numerical,":[95],"image":[96],"natural":[98],"language":[99],"datasets.":[100],"We":[101,139],"evaluate":[102],"our":[103,134,142,167],"system":[104,143],"quantitatively":[105],"adding":[107],"small":[109],"number":[110],"of":[111,128,166],"label":[112],"noise":[113],"29":[115],"datasets,":[116],"show":[118],"that":[119],"average":[126],"precision":[127],"more":[129],"than":[130],"0.84":[131],"when":[132],"system's":[135],"top":[136],"1%":[137],"recommendation.":[138],"then":[140],"apply":[141],"publicly":[145],"available":[146],"CIFAR-100,":[153],"Fashion-MNIST,":[154],"others.":[156],"Finally,":[157],"publish":[159],"code":[161],"applicable":[164],"implementation":[165],"approach.":[168]},"counts_by_year":[{"year":2025,"cited_by_count":7},{"year":2024,"cited_by_count":7},{"year":2023,"cited_by_count":4},{"year":2022,"cited_by_count":3},{"year":2021,"cited_by_count":4},{"year":2020,"cited_by_count":2}],"updated_date":"2026-03-10T16:38:18.471706","created_date":"2019-10-10T00:00:00"}