{"id":"https://openalex.org/W3137213853","doi":"https://doi.org/10.1109/bigdata50022.2020.9378234","title":"Towards Training Robust Private Aggregation of Teacher Ensembles Under Noisy Labels","display_name":"Towards Training Robust Private Aggregation of Teacher Ensembles Under Noisy Labels","publication_year":2020,"publication_date":"2020-12-10","ids":{"openalex":"https://openalex.org/W3137213853","doi":"https://doi.org/10.1109/bigdata50022.2020.9378234","mag":"3137213853"},"language":"en","primary_location":{"id":"doi:10.1109/bigdata50022.2020.9378234","is_oa":false,"landing_page_url":"https://doi.org/10.1109/bigdata50022.2020.9378234","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2020 IEEE International Conference on Big Data (Big Data)","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/A5027539408","display_name":"Qiuchen Zhang","orcid":"https://orcid.org/0000-0002-7054-1983"},"institutions":[{"id":"https://openalex.org/I150468666","display_name":"Emory University","ror":"https://ror.org/03czfpz43","country_code":"US","type":"education","lineage":["https://openalex.org/I150468666"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Qiuchen Zhang","raw_affiliation_strings":["Emory University,Department of Computer Science,Atlanta,GA"],"affiliations":[{"raw_affiliation_string":"Emory University,Department of Computer Science,Atlanta,GA","institution_ids":["https://openalex.org/I150468666"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5034823980","display_name":"Jing Ma","orcid":"https://orcid.org/0000-0002-7464-8331"},"institutions":[{"id":"https://openalex.org/I150468666","display_name":"Emory University","ror":"https://ror.org/03czfpz43","country_code":"US","type":"education","lineage":["https://openalex.org/I150468666"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Jing Ma","raw_affiliation_strings":["Emory University,Department of Computer Science,Atlanta,GA"],"affiliations":[{"raw_affiliation_string":"Emory University,Department of Computer Science,Atlanta,GA","institution_ids":["https://openalex.org/I150468666"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5041918034","display_name":"Jian Lou","orcid":"https://orcid.org/0000-0002-4110-2068"},"institutions":[{"id":"https://openalex.org/I150468666","display_name":"Emory University","ror":"https://ror.org/03czfpz43","country_code":"US","type":"education","lineage":["https://openalex.org/I150468666"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Jian Lou","raw_affiliation_strings":["Emory University,Department of Computer Science,Atlanta,GA"],"affiliations":[{"raw_affiliation_string":"Emory University,Department of Computer Science,Atlanta,GA","institution_ids":["https://openalex.org/I150468666"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5078394535","display_name":"Li Xiong","orcid":"https://orcid.org/0000-0001-7354-0428"},"institutions":[{"id":"https://openalex.org/I150468666","display_name":"Emory University","ror":"https://ror.org/03czfpz43","country_code":"US","type":"education","lineage":["https://openalex.org/I150468666"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Li Xiong","raw_affiliation_strings":["Emory University,Department of Computer Science,Atlanta,GA"],"affiliations":[{"raw_affiliation_string":"Emory University,Department of Computer Science,Atlanta,GA","institution_ids":["https://openalex.org/I150468666"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5055458864","display_name":"Xiaoqian Jiang","orcid":"https://orcid.org/0000-0001-9933-2205"},"institutions":[{"id":"https://openalex.org/I919571938","display_name":"The University of Texas Health Science Center at Houston","ror":"https://ror.org/03gds6c39","country_code":"US","type":"education","lineage":["https://openalex.org/I919571938"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Xiaoqian Jiang","raw_affiliation_strings":["University of Texas Health Science Center at Houston,Houston,TX"],"affiliations":[{"raw_affiliation_string":"University of Texas Health Science Center at Houston,Houston,TX","institution_ids":["https://openalex.org/I919571938"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5027539408"],"corresponding_institution_ids":["https://openalex.org/I150468666"],"apc_list":null,"apc_paid":null,"fwci":0.7954,"has_fulltext":false,"cited_by_count":8,"citation_normalized_percentile":{"value":0.79362496,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":94,"max":97},"biblio":{"volume":"9","issue":null,"first_page":"1103","last_page":"1110"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10764","display_name":"Privacy-Preserving Technologies in Data","score":0.9991999864578247,"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/T10764","display_name":"Privacy-Preserving Technologies in Data","score":0.9991999864578247,"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/T11689","display_name":"Adversarial Robustness in Machine Learning","score":0.9986000061035156,"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/T10036","display_name":"Advanced Neural Network Applications","score":0.9968000054359436,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7592184543609619},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.644978404045105},{"id":"https://openalex.org/keywords/generator","display_name":"Generator (circuit theory)","score":0.6154689192771912},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.5282710790634155},{"id":"https://openalex.org/keywords/training-set","display_name":"Training set","score":0.492541640996933},{"id":"https://openalex.org/keywords/generative-model","display_name":"Generative model","score":0.45415961742401123},{"id":"https://openalex.org/keywords/noisy-data","display_name":"Noisy data","score":0.4380127191543579},{"id":"https://openalex.org/keywords/data-modeling","display_name":"Data modeling","score":0.4121440052986145},{"id":"https://openalex.org/keywords/generative-grammar","display_name":"Generative grammar","score":0.393576443195343},{"id":"https://openalex.org/keywords/database","display_name":"Database","score":0.13401690125465393}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7592184543609619},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.644978404045105},{"id":"https://openalex.org/C2780992000","wikidata":"https://www.wikidata.org/wiki/Q17016113","display_name":"Generator (circuit theory)","level":3,"score":0.6154689192771912},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.5282710790634155},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.492541640996933},{"id":"https://openalex.org/C167966045","wikidata":"https://www.wikidata.org/wiki/Q5532625","display_name":"Generative model","level":3,"score":0.45415961742401123},{"id":"https://openalex.org/C2781170535","wikidata":"https://www.wikidata.org/wiki/Q30587856","display_name":"Noisy data","level":2,"score":0.4380127191543579},{"id":"https://openalex.org/C67186912","wikidata":"https://www.wikidata.org/wiki/Q367664","display_name":"Data modeling","level":2,"score":0.4121440052986145},{"id":"https://openalex.org/C39890363","wikidata":"https://www.wikidata.org/wiki/Q36108","display_name":"Generative grammar","level":2,"score":0.393576443195343},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.13401690125465393},{"id":"https://openalex.org/C163258240","wikidata":"https://www.wikidata.org/wiki/Q25342","display_name":"Power (physics)","level":2,"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/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/bigdata50022.2020.9378234","is_oa":false,"landing_page_url":"https://doi.org/10.1109/bigdata50022.2020.9378234","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2020 IEEE International Conference on Big Data (Big Data)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Reduced inequalities","score":0.5400000214576721,"id":"https://metadata.un.org/sdg/10"}],"awards":[],"funders":[{"id":"https://openalex.org/F4320306076","display_name":"National Science Foundation","ror":"https://ror.org/021nxhr62"},{"id":"https://openalex.org/F4320332161","display_name":"National Institutes of Health","ror":"https://ror.org/01cwqze88"},{"id":"https://openalex.org/F4320338279","display_name":"Air Force Office of Scientific Research","ror":"https://ror.org/011e9bt93"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":50,"referenced_works":["https://openalex.org/W1821462560","https://openalex.org/W1869752048","https://openalex.org/W1873763122","https://openalex.org/W2027595342","https://openalex.org/W2051267297","https://openalex.org/W2099471712","https://openalex.org/W2325939864","https://openalex.org/W2404901863","https://openalex.org/W2473418344","https://openalex.org/W2520442116","https://openalex.org/W2532781556","https://openalex.org/W2535690855","https://openalex.org/W2594311007","https://openalex.org/W2750384547","https://openalex.org/W2751384916","https://openalex.org/W2785361959","https://openalex.org/W2885593519","https://openalex.org/W2941564988","https://openalex.org/W2948705111","https://openalex.org/W2963069010","https://openalex.org/W2963081269","https://openalex.org/W2963096987","https://openalex.org/W2963373786","https://openalex.org/W2963374540","https://openalex.org/W2963735582","https://openalex.org/W2964234160","https://openalex.org/W2978426779","https://openalex.org/W2996108195","https://openalex.org/W2996364607","https://openalex.org/W3036586801","https://openalex.org/W3125630184","https://openalex.org/W3137695714","https://openalex.org/W4205228770","https://openalex.org/W4297799122","https://openalex.org/W4320013936","https://openalex.org/W6638523607","https://openalex.org/W6639082767","https://openalex.org/W6639246211","https://openalex.org/W6718379498","https://openalex.org/W6728897251","https://openalex.org/W6740005241","https://openalex.org/W6743688258","https://openalex.org/W6747732332","https://openalex.org/W6751647823","https://openalex.org/W6753772092","https://openalex.org/W6762913911","https://openalex.org/W6763485134","https://openalex.org/W6763865062","https://openalex.org/W6771630921","https://openalex.org/W6772389601"],"related_works":["https://openalex.org/W4365211920","https://openalex.org/W3014948380","https://openalex.org/W4380551139","https://openalex.org/W4317695495","https://openalex.org/W4287117424","https://openalex.org/W4387506531","https://openalex.org/W4238433571","https://openalex.org/W2967848559","https://openalex.org/W4299831724","https://openalex.org/W4283803360"],"abstract_inverted_index":{"Deep":[0],"learning":[1],"models":[2,18],"trained":[3,19,74,104],"on":[4,20,75,231,239,243],"large-scale":[5],"data":[6,77,97],"have":[7],"achieved":[8,51],"encouraging":[9],"performance":[10,221],"in":[11,54,181,197],"many":[12],"real-world":[13],"tasks.":[14],"Meanwhile,":[15],"publishing":[16],"those":[17],"sensitive":[21,76],"datasets,":[22],"such":[23],"as":[24],"medical":[25],"records,":[26],"could":[27],"pose":[28],"serious":[29],"privacy":[30,65],"concerns.":[31],"To":[32],"counter":[33],"these":[34],"issues,":[35],"one":[36,174],"of":[37,45,58,71,90,132,169,193],"the":[38,56,59,80,87,99,107,114,130,133,141,149,158,190,194,198,237,240],"current":[39,150],"state-of-the-art":[40],"approaches":[41],"is":[42,179],"Private":[43],"Aggregation":[44],"Teacher":[46],"Ensembles,":[47],"or":[48,109],"PATE,":[49],"which":[50,98,147],"promising":[52],"results":[53],"preserving":[55],"utility":[57],"model":[60,85,101,214,220],"while":[61],"providing":[62],"a":[63,83,206],"strong":[64],"guarantee.":[66],"PATE":[67,142,160,242],"combines":[68,148],"an":[69],"ensemble":[70],"\"teacher":[72],"models\"":[73],"and":[78,176,204,233],"transfers":[79],"knowledge":[81,108],"to":[82,119,162,183,216,235],"\"student\"":[84],"through":[86],"noisy":[88,117,125,152,208,225],"aggregation":[89],"teachers'":[91],"votes":[92],"for":[93,212],"labeling":[94],"unlabeled":[95],"public":[96],"student":[100,115,134,219],"will":[102],"be":[103],"on.":[105],"However,":[106],"voted":[110],"labels":[111,126],"learned":[112],"by":[113],"are":[116],"due":[118],"private":[120],"aggregation.":[121],"Learning":[122],"directly":[123],"from":[124],"can":[127],"significantly":[128],"impact":[129],"accuracy":[131],"model.":[135],"In":[136],"this":[137],"paper,":[138],"we":[139,188],"propose":[140],"<sub":[143,200],"xmlns:mml=\"http://www.w3.org/1998/Math/MathML\"":[144,201],"xmlns:xlink=\"http://www.w3.org/1999/xlink\">++</sub>":[145],"mechanism,":[146],"advanced":[151],"label":[153,209],"training":[154,215,223],"mechanisms":[155],"co-teaching(+)":[156],"with":[157,173,224],"original":[159,241],"framework":[161],"enhance":[163],"its":[164],"accuracy.":[165],"A":[166],"novel":[167,207],"structure":[168],"Generative":[170],"Adversarial":[171],"Nets":[172],"generator":[175],"two":[177],"discriminators":[178],"developed":[180],"order":[182],"integrate":[184],"them":[185],"effectively.":[186],"Furthermore,":[187],"discuss":[189],"intrinsic":[191],"limitations":[192],"\"update-by-disagreement\"":[195],"method":[196,230],"co-teaching":[199],"xmlns:xlink=\"http://www.w3.org/1999/xlink\">+</sub>":[202],"mechanism":[203,211],"develop":[205],"detection":[210],"semi-supervised":[213],"further":[217],"improve":[218],"when":[222],"labels.":[226],"We":[227],"evaluate":[228],"our":[229],"Fashion-MNIST":[232],"SVHN":[234],"show":[236],"improvements":[238],"all":[244],"measures.":[245]},"counts_by_year":[{"year":2024,"cited_by_count":2},{"year":2023,"cited_by_count":2},{"year":2022,"cited_by_count":4}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}