{"id":"https://openalex.org/W4391420198","doi":"https://doi.org/10.1109/camsap58249.2023.10403492","title":"Deep Learning from Noisy Labels via Robust Nonnegative Matrix Factorization-Based Design","display_name":"Deep Learning from Noisy Labels via Robust Nonnegative Matrix Factorization-Based Design","publication_year":2023,"publication_date":"2023-12-10","ids":{"openalex":"https://openalex.org/W4391420198","doi":"https://doi.org/10.1109/camsap58249.2023.10403492"},"language":"en","primary_location":{"id":"doi:10.1109/camsap58249.2023.10403492","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1109/camsap58249.2023.10403492","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2023 IEEE 9th International Workshop on Computational Advances in Multi-Sensor Adaptive Processing (CAMSAP)","raw_type":"proceedings-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/A5093836017","display_name":"Daniel Grey Wolnick","orcid":null},"institutions":[{"id":"https://openalex.org/I131249849","display_name":"Oregon State University","ror":"https://ror.org/00ysfqy60","country_code":"US","type":"education","lineage":["https://openalex.org/I131249849"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Daniel Grey Wolnick","raw_affiliation_strings":["School of EECS, Oregon State University,Corvallis,OR,USA","School of EECS, Oregon State University, Corvallis, OR, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of EECS, Oregon State University,Corvallis,OR,USA","institution_ids":["https://openalex.org/I131249849"]},{"raw_affiliation_string":"School of EECS, Oregon State University, Corvallis, OR, USA","institution_ids":["https://openalex.org/I131249849"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5005841750","display_name":"Shahana Ibrahim","orcid":"https://orcid.org/0000-0003-1951-5234"},"institutions":[{"id":"https://openalex.org/I131249849","display_name":"Oregon State University","ror":"https://ror.org/00ysfqy60","country_code":"US","type":"education","lineage":["https://openalex.org/I131249849"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Shahana Ibrahim","raw_affiliation_strings":["School of EECS, Oregon State University,Corvallis,OR,USA","School of EECS, Oregon State University, Corvallis, OR, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of EECS, Oregon State University,Corvallis,OR,USA","institution_ids":["https://openalex.org/I131249849"]},{"raw_affiliation_string":"School of EECS, Oregon State University, Corvallis, OR, USA","institution_ids":["https://openalex.org/I131249849"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5024418285","display_name":"Tim Marrinan","orcid":"https://orcid.org/0000-0001-5240-3053"},"institutions":[{"id":"https://openalex.org/I142606810","display_name":"Pacific Northwest National Laboratory","ror":"https://ror.org/05h992307","country_code":"US","type":"facility","lineage":["https://openalex.org/I1325736334","https://openalex.org/I1330989302","https://openalex.org/I142606810","https://openalex.org/I39565521"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Tim Marrinan","raw_affiliation_strings":["Pacific Northwest National Lab,Seattle,WA,USA","Pacific Northwest National Lab, Seattle, WA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Pacific Northwest National Lab,Seattle,WA,USA","institution_ids":["https://openalex.org/I142606810"]},{"raw_affiliation_string":"Pacific Northwest National Lab, Seattle, WA, USA","institution_ids":["https://openalex.org/I142606810"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5015075381","display_name":"Xiao Fu","orcid":"https://orcid.org/0000-0003-4847-9586"},"institutions":[{"id":"https://openalex.org/I131249849","display_name":"Oregon State University","ror":"https://ror.org/00ysfqy60","country_code":"US","type":"education","lineage":["https://openalex.org/I131249849"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Xiao Fu","raw_affiliation_strings":["School of EECS, Oregon State University,Corvallis,OR,USA","School of EECS, Oregon State University, Corvallis, OR, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of EECS, Oregon State University,Corvallis,OR,USA","institution_ids":["https://openalex.org/I131249849"]},{"raw_affiliation_string":"School of EECS, Oregon State University, Corvallis, OR, USA","institution_ids":["https://openalex.org/I131249849"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"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":0.33505214,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"97","issue":null,"first_page":"446","last_page":"450"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12111","display_name":"Industrial Vision Systems and Defect Detection","score":0.9962999820709229,"subfield":{"id":"https://openalex.org/subfields/2209","display_name":"Industrial and Manufacturing Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},"topics":[{"id":"https://openalex.org/T12111","display_name":"Industrial Vision Systems and Defect Detection","score":0.9962999820709229,"subfield":{"id":"https://openalex.org/subfields/2209","display_name":"Industrial and Manufacturing Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T12535","display_name":"Machine Learning and Data Classification","score":0.9958000183105469,"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/T10848","display_name":"Advanced Multi-Objective Optimization Algorithms","score":0.9950000047683716,"subfield":{"id":"https://openalex.org/subfields/1703","display_name":"Computational Theory and Mathematics"},"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/matrix-decomposition","display_name":"Matrix decomposition","score":0.6674184799194336},{"id":"https://openalex.org/keywords/non-negative-matrix-factorization","display_name":"Non-negative matrix factorization","score":0.6614064574241638},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6366090774536133},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5312670469284058},{"id":"https://openalex.org/keywords/deep-learning","display_name":"Deep learning","score":0.4714711010456085},{"id":"https://openalex.org/keywords/factorization","display_name":"Factorization","score":0.4646690785884857},{"id":"https://openalex.org/keywords/matrix","display_name":"Matrix (chemical analysis)","score":0.4515470862388611},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.3340098261833191},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.30431556701660156}],"concepts":[{"id":"https://openalex.org/C42355184","wikidata":"https://www.wikidata.org/wiki/Q1361088","display_name":"Matrix decomposition","level":3,"score":0.6674184799194336},{"id":"https://openalex.org/C152671427","wikidata":"https://www.wikidata.org/wiki/Q10843505","display_name":"Non-negative matrix factorization","level":4,"score":0.6614064574241638},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6366090774536133},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5312670469284058},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.4714711010456085},{"id":"https://openalex.org/C187834632","wikidata":"https://www.wikidata.org/wiki/Q188804","display_name":"Factorization","level":2,"score":0.4646690785884857},{"id":"https://openalex.org/C106487976","wikidata":"https://www.wikidata.org/wiki/Q685816","display_name":"Matrix (chemical analysis)","level":2,"score":0.4515470862388611},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3340098261833191},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.30431556701660156},{"id":"https://openalex.org/C159985019","wikidata":"https://www.wikidata.org/wiki/Q181790","display_name":"Composite material","level":1,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0},{"id":"https://openalex.org/C192562407","wikidata":"https://www.wikidata.org/wiki/Q228736","display_name":"Materials science","level":0,"score":0.0},{"id":"https://openalex.org/C158693339","wikidata":"https://www.wikidata.org/wiki/Q190524","display_name":"Eigenvalues and eigenvectors","level":2,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/camsap58249.2023.10403492","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1109/camsap58249.2023.10403492","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2023 IEEE 9th International Workshop on Computational Advances in Multi-Sensor Adaptive Processing (CAMSAP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G3599886496","display_name":null,"funder_award_id":"IIS-2007836","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"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":45,"referenced_works":["https://openalex.org/W9014458","https://openalex.org/W1514928307","https://openalex.org/W1976615758","https://openalex.org/W2050041778","https://openalex.org/W2063790512","https://openalex.org/W2118943995","https://openalex.org/W2129062845","https://openalex.org/W2140318696","https://openalex.org/W2156458885","https://openalex.org/W2170078675","https://openalex.org/W2194775991","https://openalex.org/W2513096609","https://openalex.org/W2566079294","https://openalex.org/W2752365628","https://openalex.org/W2791154158","https://openalex.org/W2803187616","https://openalex.org/W2804378530","https://openalex.org/W2947049994","https://openalex.org/W2963697299","https://openalex.org/W2963735582","https://openalex.org/W2964257934","https://openalex.org/W2964292098","https://openalex.org/W2976088223","https://openalex.org/W2981873476","https://openalex.org/W3100202987","https://openalex.org/W3104255659","https://openalex.org/W3104256134","https://openalex.org/W3114089334","https://openalex.org/W3118608800","https://openalex.org/W6680770193","https://openalex.org/W6740005241","https://openalex.org/W6751420435","https://openalex.org/W6751647823","https://openalex.org/W6751883947","https://openalex.org/W6758632346","https://openalex.org/W6763576130","https://openalex.org/W6767394681","https://openalex.org/W6779709574","https://openalex.org/W6785821353","https://openalex.org/W6787972765","https://openalex.org/W6790117478","https://openalex.org/W6790529964","https://openalex.org/W6796467477","https://openalex.org/W6853085414","https://openalex.org/W6853511276"],"related_works":["https://openalex.org/W4390394189","https://openalex.org/W2037504162","https://openalex.org/W2539013788","https://openalex.org/W2792706544","https://openalex.org/W1568451138","https://openalex.org/W2156699640","https://openalex.org/W2045265907","https://openalex.org/W2972997031","https://openalex.org/W2146544734","https://openalex.org/W2075222291"],"abstract_inverted_index":{"Deep":[0],"neural":[1],"networks":[2],"(DNN)":[3],"heavily":[4],"rely":[5],"on":[6],"labeled":[7],"data":[8,135],"for":[9,71,164],"supervised":[10],"training.":[11],"However,":[12,95],"acquiring":[13],"accurate":[14],"labels":[15],"is":[16,40,59,69,97],"often":[17],"a":[18,37,41,56],"challenging":[19],"task.":[20],"Moreover,":[21],"DNNs":[22],"easily":[23],"overfit":[24],"to":[25,100,103,122],"noisy":[26,128],"labels,":[27],"hindering":[28],"the":[29,33,75,84,115,120,139,142,155,165,168],"generalization":[30],"ability.":[31],"Modeling":[32],"label":[34,129],"noise":[35],"using":[36,55],"\u201cconfusion":[38],"matrix\u201d":[39],"widely":[42],"adopted":[43],"strategy":[44],"under":[45],"such":[46,147],"circumstances.":[47],"A":[48],"recent":[49],"work":[50],"dealt":[51],"with":[52,125],"this":[53,109],"problem":[54],"regularizer":[57],"that":[58],"reminiscent":[60],"of":[61,74,117,167],"minimum-volume":[62],"enclosing":[63],"simplex":[64],"(MVES)-based":[65],"matrix":[66,86],"factorization.":[67],"MVES":[68,96,118],"known":[70],"its":[72,89,104],"identifiability":[73],"latent":[76],"factors,":[77],"which":[78],"in":[79,119],"turn":[80],"helps":[81],"accurately":[82],"estimate":[83],"confusion":[85],"and":[87],"rectify":[88],"negative":[90],"effects":[91],"when":[92,133],"training":[93],"DNNs.":[94],"highly":[98],"sensitive":[99],"outliers":[101],"due":[102],"geometric":[105],"nature.":[106],"To":[107],"overcome":[108],"limitation,":[110],"we":[111],"take":[112],"insight":[113],"from":[114,138],"robustification":[116],"literature":[121],"come":[123],"up":[124],"an":[126],"outlier-resilient":[127],"learning":[130],"criterion.":[131,170],"Consequently,":[132],"some":[134],"samples":[136],"deviate":[137],"model":[140,157],"assumptions,":[141],"proposed":[143,169],"criterion":[144],"automatically":[145],"downweights":[146],"outlying":[148],"data,":[149],"thereby":[150],"steering":[151],"DNN":[152],"towards":[153],"identifying":[154],"correct":[156],"parameters.":[158],"Our":[159],"experiment":[160],"results":[161],"provide":[162],"support":[163],"effectiveness":[166]},"counts_by_year":[],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}