{"id":"https://openalex.org/W4392904009","doi":"https://doi.org/10.1109/icassp48485.2024.10447823","title":"Federated Learning with Instance-Dependent Noisy Label","display_name":"Federated Learning with Instance-Dependent Noisy Label","publication_year":2024,"publication_date":"2024-03-18","ids":{"openalex":"https://openalex.org/W4392904009","doi":"https://doi.org/10.1109/icassp48485.2024.10447823"},"language":"en","primary_location":{"id":"doi:10.1109/icassp48485.2024.10447823","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp48485.2024.10447823","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2024 - 2024 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","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/A5100436173","display_name":"Lei Wang","orcid":"https://orcid.org/0009-0003-1939-5532"},"institutions":[{"id":"https://openalex.org/I145608581","display_name":"University of Miami","ror":"https://ror.org/02dgjyy92","country_code":"US","type":"education","lineage":["https://openalex.org/I145608581"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Lei Wang","raw_affiliation_strings":["University of Miami,Electrical and Computer Engineering,Coral Gables,FL,USA,33146"],"affiliations":[{"raw_affiliation_string":"University of Miami,Electrical and Computer Engineering,Coral Gables,FL,USA,33146","institution_ids":["https://openalex.org/I145608581"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5012540094","display_name":"Jieming Bian","orcid":"https://orcid.org/0000-0002-6372-6357"},"institutions":[{"id":"https://openalex.org/I145608581","display_name":"University of Miami","ror":"https://ror.org/02dgjyy92","country_code":"US","type":"education","lineage":["https://openalex.org/I145608581"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Jieming Bian","raw_affiliation_strings":["University of Miami,Electrical and Computer Engineering,Coral Gables,FL,USA,33146"],"affiliations":[{"raw_affiliation_string":"University of Miami,Electrical and Computer Engineering,Coral Gables,FL,USA,33146","institution_ids":["https://openalex.org/I145608581"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5044771462","display_name":"Jie Xu","orcid":"https://orcid.org/0000-0002-0515-1647"},"institutions":[{"id":"https://openalex.org/I145608581","display_name":"University of Miami","ror":"https://ror.org/02dgjyy92","country_code":"US","type":"education","lineage":["https://openalex.org/I145608581"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Jie Xu","raw_affiliation_strings":["University of Miami,Electrical and Computer Engineering,Coral Gables,FL,USA,33146"],"affiliations":[{"raw_affiliation_string":"University of Miami,Electrical and Computer Engineering,Coral Gables,FL,USA,33146","institution_ids":["https://openalex.org/I145608581"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5100436173"],"corresponding_institution_ids":["https://openalex.org/I145608581"],"apc_list":null,"apc_paid":null,"fwci":2.044,"has_fulltext":false,"cited_by_count":6,"citation_normalized_percentile":{"value":0.87886955,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"8916","last_page":"8920"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12535","display_name":"Machine Learning and Data Classification","score":0.9994999766349792,"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":0.9994999766349792,"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":0.9932000041007996,"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/T10764","display_name":"Privacy-Preserving Technologies in Data","score":0.9887999892234802,"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/computer-science","display_name":"Computer science","score":0.8460395336151123},{"id":"https://openalex.org/keywords/classifier","display_name":"Classifier (UML)","score":0.6582207679748535},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.6313586235046387},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5891989469528198},{"id":"https://openalex.org/keywords/noisy-data","display_name":"Noisy data","score":0.5701929926872253},{"id":"https://openalex.org/keywords/federated-learning","display_name":"Federated learning","score":0.4968922436237335},{"id":"https://openalex.org/keywords/bayesian-probability","display_name":"Bayesian probability","score":0.4465769827365875},{"id":"https://openalex.org/keywords/noise","display_name":"Noise (video)","score":0.42401039600372314},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.42313557863235474}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8460395336151123},{"id":"https://openalex.org/C95623464","wikidata":"https://www.wikidata.org/wiki/Q1096149","display_name":"Classifier (UML)","level":2,"score":0.6582207679748535},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.6313586235046387},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5891989469528198},{"id":"https://openalex.org/C2781170535","wikidata":"https://www.wikidata.org/wiki/Q30587856","display_name":"Noisy data","level":2,"score":0.5701929926872253},{"id":"https://openalex.org/C2992525071","wikidata":"https://www.wikidata.org/wiki/Q50818671","display_name":"Federated learning","level":2,"score":0.4968922436237335},{"id":"https://openalex.org/C107673813","wikidata":"https://www.wikidata.org/wiki/Q812534","display_name":"Bayesian probability","level":2,"score":0.4465769827365875},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.42401039600372314},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.42313557863235474},{"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":[{"id":"doi:10.1109/icassp48485.2024.10447823","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp48485.2024.10447823","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2024 - 2024 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G1946296","display_name":null,"funder_award_id":"2319780","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G3136170333","display_name":null,"funder_award_id":"2006630","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G6070057448","display_name":null,"funder_award_id":"2044991","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":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":25,"referenced_works":["https://openalex.org/W2194775991","https://openalex.org/W2767094803","https://openalex.org/W2807006176","https://openalex.org/W2963819344","https://openalex.org/W2978625989","https://openalex.org/W2989289980","https://openalex.org/W3034185248","https://openalex.org/W3104255659","https://openalex.org/W3122967774","https://openalex.org/W3175272368","https://openalex.org/W4212881588","https://openalex.org/W4281744550","https://openalex.org/W4287647398","https://openalex.org/W4312403682","https://openalex.org/W4312440249","https://openalex.org/W4387460392","https://openalex.org/W6728757088","https://openalex.org/W6752029299","https://openalex.org/W6759238902","https://openalex.org/W6773817997","https://openalex.org/W6782317661","https://openalex.org/W6784048413","https://openalex.org/W6785821353","https://openalex.org/W6838048988","https://openalex.org/W6849777976"],"related_works":["https://openalex.org/W4298221930","https://openalex.org/W2777914285","https://openalex.org/W4378677776","https://openalex.org/W2770533869","https://openalex.org/W2888188966","https://openalex.org/W3208786872","https://openalex.org/W2990812465","https://openalex.org/W3164866731","https://openalex.org/W2165396616","https://openalex.org/W3038785057"],"abstract_inverted_index":{"Federated":[0],"learning":[1,19],"(FL)":[2],"with":[3,51,88],"noisy":[4,15,52,178],"labels":[5,16],"poses":[6],"a":[7,81,98,122,131,173],"significant":[8],"challenge.":[9],"Existing":[10],"methods":[11],"designed":[12],"for":[13,177],"handling":[14],"in":[17,25,77,143],"centralized":[18],"tend":[20],"to":[21,31,48,96],"lose":[22],"their":[23],"effectiveness":[24],"the":[26,32,37,67,104,154,165,181,191],"FL":[27,50],"setting,":[28],"mainly":[29],"due":[30],"small":[33],"dataset":[34],"size":[35],"and":[36,70,126,187],"heterogeneity":[38],"of":[39,73],"client":[40],"data.":[41,156],"While":[42],"some":[43],"attempts":[44],"have":[45],"been":[46],"made":[47],"tackle":[49],"labels,":[53,179],"they":[54],"primarily":[55],"focused":[56],"on":[57,153,185],"scenarios":[58],"involving":[59],"class-conditional":[60],"noise.":[61],"In":[62],"this":[63],"paper,":[64],"we":[65],"study":[66],"more":[68],"challenging":[69],"practical":[71],"issue":[72],"instance-dependent":[74],"noise":[75],"(IDN)":[76],"FL.":[78],"We":[79],"introduce":[80],"novel":[82],"algorithm":[83],"called":[84],"FedBeat":[85,94],"(Federated":[86],"Learning":[87],"Bayesian":[89,132],"Ensemble-Assisted":[90],"Transition":[91],"Matrix":[92],"Estimation).":[93],"aims":[95],"build":[97],"global":[99,124,166],"statistically":[100],"consistent":[101],"classifier":[102,160],"using":[103,130,172],"IDN":[105],"transition":[106,139],"matrix":[107,140],"(IDNTM),":[108],"which":[109,144],"encompasses":[110],"three":[111],"synergistic":[112],"steps:":[113],"(1)":[114],"A":[115,137,158],"federated":[116,138,159],"data":[117,129],"extraction":[118],"step":[119,142,162],"that":[120,163,190],"constructs":[121],"weak":[123],"model":[125,133],"extracts":[127],"high-confidence":[128],"ensemble":[134],"method.":[135],"(2)":[136],"estimation":[141,150],"clients":[145],"collaboratively":[146],"train":[147],"an":[148],"IDNTM":[149],"network":[151],"based":[152],"extracted":[155],"(3)":[157],"correction":[161],"enhances":[164],"model\u2019s":[167],"performance":[168],"by":[169],"training":[170],"it":[171],"loss":[174],"function":[175],"tailored":[176],"leveraging":[180],"IDNTM.":[182],"Experiments":[183],"conducted":[184],"CIFAR-10":[186],"SVHN":[188],"verify":[189],"proposed":[192],"method":[193],"significantly":[194],"outperforms":[195],"state-of-the-art":[196],"methods.":[197]},"counts_by_year":[{"year":2025,"cited_by_count":5},{"year":2024,"cited_by_count":1}],"updated_date":"2026-04-10T15:06:20.359241","created_date":"2025-10-10T00:00:00"}