{"id":"https://openalex.org/W3036468020","doi":"https://doi.org/10.1109/icpr48806.2021.9412599","title":"Overcoming Noisy and Irrelevant Data in Federated Learning","display_name":"Overcoming Noisy and Irrelevant Data in Federated Learning","publication_year":2021,"publication_date":"2021-01-10","ids":{"openalex":"https://openalex.org/W3036468020","doi":"https://doi.org/10.1109/icpr48806.2021.9412599","mag":"3036468020"},"language":"en","primary_location":{"id":"doi:10.1109/icpr48806.2021.9412599","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icpr48806.2021.9412599","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2020 25th International Conference on Pattern Recognition (ICPR)","raw_type":"proceedings-article"},"type":"preprint","indexed_in":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2001.08300","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5052314895","display_name":"Tiffany Tuor","orcid":null},"institutions":[{"id":"https://openalex.org/I47508984","display_name":"Imperial College London","ror":"https://ror.org/041kmwe10","country_code":"GB","type":"education","lineage":["https://openalex.org/I47508984"]}],"countries":["GB"],"is_corresponding":true,"raw_author_name":"Tiffany Tuor","raw_affiliation_strings":["Imperial College London, UK","Imperial College London Department of Electrical and Electronic Engineering UK"],"affiliations":[{"raw_affiliation_string":"Imperial College London, UK","institution_ids":["https://openalex.org/I47508984"]},{"raw_affiliation_string":"Imperial College London Department of Electrical and Electronic Engineering UK","institution_ids":["https://openalex.org/I47508984"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100443968","display_name":"Shiqiang Wang","orcid":"https://orcid.org/0000-0003-2090-5512"},"institutions":[{"id":"https://openalex.org/I4210114115","display_name":"IBM Research - Thomas J. Watson Research Center","ror":"https://ror.org/0265w5591","country_code":"US","type":"facility","lineage":["https://openalex.org/I1341412227","https://openalex.org/I4210114115"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Shiqiang Wang","raw_affiliation_strings":["IBM T. J. Watson Research Center, Yorktown Heights, NY, USA","IBM T.J. Watson Research Center, Yorktown Heights, NY, USA"],"affiliations":[{"raw_affiliation_string":"IBM T. J. Watson Research Center, Yorktown Heights, NY, USA","institution_ids":["https://openalex.org/I4210114115"]},{"raw_affiliation_string":"IBM T.J. Watson Research Center, Yorktown Heights, NY, USA","institution_ids":["https://openalex.org/I4210114115"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5110791651","display_name":"Bong Jun Ko","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Bong Jun Ko","raw_affiliation_strings":["Stanford Institute for Human-Centered Artificial Intelligence (HAI), Stanford, CA, USA","Stanford Institute for Human-Centered Artificial Intelligence (HAI),Stanford,CA,USA"],"affiliations":[{"raw_affiliation_string":"Stanford Institute for Human-Centered Artificial Intelligence (HAI), Stanford, CA, USA","institution_ids":[]},{"raw_affiliation_string":"Stanford Institute for Human-Centered Artificial Intelligence (HAI),Stanford,CA,USA","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5062732327","display_name":"Changchang Liu","orcid":"https://orcid.org/0000-0003-4594-4577"},"institutions":[{"id":"https://openalex.org/I4210114115","display_name":"IBM Research - Thomas J. Watson Research Center","ror":"https://ror.org/0265w5591","country_code":"US","type":"facility","lineage":["https://openalex.org/I1341412227","https://openalex.org/I4210114115"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Changchang Liu","raw_affiliation_strings":["IBM T. J. Watson Research Center, Yorktown Heights, NY, USA","IBM T.J. Watson Research Center, Yorktown Heights, NY, USA"],"affiliations":[{"raw_affiliation_string":"IBM T. J. Watson Research Center, Yorktown Heights, NY, USA","institution_ids":["https://openalex.org/I4210114115"]},{"raw_affiliation_string":"IBM T.J. Watson Research Center, Yorktown Heights, NY, USA","institution_ids":["https://openalex.org/I4210114115"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5020917506","display_name":"Kin K. Leung","orcid":"https://orcid.org/0000-0002-3860-6257"},"institutions":[{"id":"https://openalex.org/I47508984","display_name":"Imperial College London","ror":"https://ror.org/041kmwe10","country_code":"GB","type":"education","lineage":["https://openalex.org/I47508984"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Kin K. Leung","raw_affiliation_strings":["Imperial College London, UK","Imperial College London Department of Electrical and Electronic Engineering UK"],"affiliations":[{"raw_affiliation_string":"Imperial College London, UK","institution_ids":["https://openalex.org/I47508984"]},{"raw_affiliation_string":"Imperial College London Department of Electrical and Electronic Engineering UK","institution_ids":["https://openalex.org/I47508984"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5052314895"],"corresponding_institution_ids":["https://openalex.org/I47508984"],"apc_list":null,"apc_paid":null,"fwci":1.9595,"has_fulltext":true,"cited_by_count":17,"citation_normalized_percentile":{"value":0.8822357,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"5020","last_page":"5027"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10764","display_name":"Privacy-Preserving Technologies in Data","score":0.9997000098228455,"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":0.9997000098228455,"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":0.9965999722480774,"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"}},{"id":"https://openalex.org/T10862","display_name":"AI in cancer detection","score":0.9927999973297119,"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":0.8653138875961304},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.7190089821815491},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.6357795596122742},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.6265504360198975},{"id":"https://openalex.org/keywords/raw-data","display_name":"Raw data","score":0.62247633934021},{"id":"https://openalex.org/keywords/relevance","display_name":"Relevance (law)","score":0.5974718928337097},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.5898420810699463},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5099245309829712},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.4386414885520935},{"id":"https://openalex.org/keywords/variety","display_name":"Variety (cybernetics)","score":0.4371452331542969},{"id":"https://openalex.org/keywords/data-modeling","display_name":"Data modeling","score":0.41598784923553467},{"id":"https://openalex.org/keywords/information-privacy","display_name":"Information privacy","score":0.4152612090110779},{"id":"https://openalex.org/keywords/training-set","display_name":"Training set","score":0.4117972254753113},{"id":"https://openalex.org/keywords/database","display_name":"Database","score":0.16009488701820374}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8653138875961304},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.7190089821815491},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.6357795596122742},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.6265504360198975},{"id":"https://openalex.org/C132964779","wikidata":"https://www.wikidata.org/wiki/Q2110223","display_name":"Raw data","level":2,"score":0.62247633934021},{"id":"https://openalex.org/C158154518","wikidata":"https://www.wikidata.org/wiki/Q7310970","display_name":"Relevance (law)","level":2,"score":0.5974718928337097},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.5898420810699463},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5099245309829712},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.4386414885520935},{"id":"https://openalex.org/C136197465","wikidata":"https://www.wikidata.org/wiki/Q1729295","display_name":"Variety (cybernetics)","level":2,"score":0.4371452331542969},{"id":"https://openalex.org/C67186912","wikidata":"https://www.wikidata.org/wiki/Q367664","display_name":"Data modeling","level":2,"score":0.41598784923553467},{"id":"https://openalex.org/C123201435","wikidata":"https://www.wikidata.org/wiki/Q456632","display_name":"Information privacy","level":2,"score":0.4152612090110779},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.4117972254753113},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.16009488701820374},{"id":"https://openalex.org/C13280743","wikidata":"https://www.wikidata.org/wiki/Q131089","display_name":"Geodesy","level":1,"score":0.0},{"id":"https://openalex.org/C17744445","wikidata":"https://www.wikidata.org/wiki/Q36442","display_name":"Political science","level":0,"score":0.0},{"id":"https://openalex.org/C187736073","wikidata":"https://www.wikidata.org/wiki/Q2920921","display_name":"Management","level":1,"score":0.0},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0},{"id":"https://openalex.org/C199539241","wikidata":"https://www.wikidata.org/wiki/Q7748","display_name":"Law","level":1,"score":0.0},{"id":"https://openalex.org/C108827166","wikidata":"https://www.wikidata.org/wiki/Q175975","display_name":"Internet privacy","level":1,"score":0.0},{"id":"https://openalex.org/C205649164","wikidata":"https://www.wikidata.org/wiki/Q1071","display_name":"Geography","level":0,"score":0.0},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0}],"mesh":[],"locations_count":4,"locations":[{"id":"doi:10.1109/icpr48806.2021.9412599","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icpr48806.2021.9412599","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2020 25th International Conference on Pattern Recognition (ICPR)","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2001.08300","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2001.08300","pdf_url":"https://arxiv.org/pdf/2001.08300","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":"","raw_type":"text"},{"id":"mag:3036468020","is_oa":true,"landing_page_url":"https://arxiv.org/pdf/2001.08300","pdf_url":null,"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":"arXiv (Cornell University)","raw_type":null},{"id":"doi:10.48550/arxiv.2001.08300","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2001.08300","pdf_url":null,"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":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"article"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2001.08300","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2001.08300","pdf_url":"https://arxiv.org/pdf/2001.08300","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":"","raw_type":"text"},"sustainable_development_goals":[{"display_name":"Partnerships for the goals","id":"https://metadata.un.org/sdg/17","score":0.5}],"awards":[{"id":"https://openalex.org/G3056544016","display_name":null,"funder_award_id":"W911NF-16-3-0001","funder_id":"https://openalex.org/F4320338295","funder_display_name":"Army Research Laboratory"},{"id":"https://openalex.org/G5259331294","display_name":null,"funder_award_id":"W911NF","funder_id":"https://openalex.org/F4320338295","funder_display_name":"Army Research Laboratory"}],"funders":[{"id":"https://openalex.org/F4320338295","display_name":"Army Research Laboratory","ror":"https://ror.org/011hc8f90"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W3036468020.pdf","grobid_xml":"https://content.openalex.org/works/W3036468020.grobid-xml"},"referenced_works_count":36,"referenced_works":["https://openalex.org/W1579279110","https://openalex.org/W2112796928","https://openalex.org/W2166481425","https://openalex.org/W2335728318","https://openalex.org/W2541884796","https://openalex.org/W2577784528","https://openalex.org/W2750384547","https://openalex.org/W2752689052","https://openalex.org/W2886444620","https://openalex.org/W2889939668","https://openalex.org/W2902113386","https://openalex.org/W2912213068","https://openalex.org/W2950720894","https://openalex.org/W2963160702","https://openalex.org/W2963318081","https://openalex.org/W2963697299","https://openalex.org/W2963735582","https://openalex.org/W2964096266","https://openalex.org/W2964155802","https://openalex.org/W2964162474","https://openalex.org/W2964292098","https://openalex.org/W2964309657","https://openalex.org/W2979359324","https://openalex.org/W2996179709","https://openalex.org/W3103802018","https://openalex.org/W3118608800","https://openalex.org/W4255375128","https://openalex.org/W4294106961","https://openalex.org/W6728757088","https://openalex.org/W6736098614","https://openalex.org/W6738763127","https://openalex.org/W6743821447","https://openalex.org/W6747898760","https://openalex.org/W6751647823","https://openalex.org/W6758632346","https://openalex.org/W6771795890"],"related_works":["https://openalex.org/W3001250740","https://openalex.org/W2541884796","https://openalex.org/W2995022099","https://openalex.org/W2913570153","https://openalex.org/W3041101125","https://openalex.org/W3081349436","https://openalex.org/W2535838896","https://openalex.org/W2907887012","https://openalex.org/W156260471","https://openalex.org/W1991944675","https://openalex.org/W2338189341","https://openalex.org/W2045114813","https://openalex.org/W2113536712","https://openalex.org/W284401865","https://openalex.org/W3032098059","https://openalex.org/W2400712033","https://openalex.org/W2398009937","https://openalex.org/W2406733485","https://openalex.org/W3091102523","https://openalex.org/W2620641980"],"abstract_inverted_index":{"Many":[0],"image":[1,202],"and":[2,29,167],"vision":[3],"applications":[4],"require":[5,59],"a":[6,19,41,46,85,90,99,134,144,149,205,209],"large":[7,72,210],"amount":[8],"of":[9,39,74,96,118,160,183,193,212],"data":[10,17,27,51,63,75,97,119,162,170,185],"for":[11,89,136],"model":[12,44,103,146,220],"training.":[13,104],"Collecting":[14],"all":[15,226],"such":[16],"at":[18,77,164],"central":[20],"location":[21],"can":[22],"be":[23],"challenging":[24],"due":[25],"to":[26,114,123,156,216,223],"privacy":[28],"communication":[30],"bandwidth":[31],"restrictions.":[32],"Federated":[33],"learning":[34,43,91,109,127,189],"is":[35,68,81,87,112,121,154,197],"an":[36],"effective":[37],"way":[38],"training":[40,224],"machine":[42],"in":[45,186,204,219],"distributed":[47],"manner":[48],"from":[49],"local":[50],"collected":[52,76],"by":[53],"client":[54,166,177],"devices,":[55],"which":[56],"does":[57],"not":[58],"exchanging":[60],"the":[61,71,94,108,116,124,158,169,180,187],"raw":[62],"among":[64,70],"clients.":[65],"A":[66],"challenge":[67],"that":[69,83,120,153],"variety":[73],"each":[78,165,176],"client,":[79],"it":[80,111],"likely":[82],"only":[84,178],"subset":[86,117,182],"relevant":[88,122,139],"task":[92],"while":[93],"rest":[95],"has":[98],"negative":[100],"impact":[101],"on":[102,148,199],"Therefore,":[105],"before":[106],"starting":[107],"process,":[110],"important":[113],"select":[115,168],"given":[125],"federated":[126,188],"task.":[128],"In":[129],"this":[130],"paper,":[131],"we":[132,142],"propose":[133],"method":[135],"distributedly":[137],"selecting":[138],"data,":[140],"where":[141],"use":[143],"benchmark":[145,151],"trained":[147],"small":[150],"dataset":[152],"task-specific,":[155],"evaluate":[157],"relevance":[159],"individual":[161],"samples":[163],"with":[171,208,225],"sufficiently":[172],"high":[173],"relevance.":[174],"Then,":[175],"uses":[179],"selected":[181],"its":[184],"process.":[190],"The":[191],"effectiveness":[192],"our":[194],"proposed":[195],"approach":[196],"evaluated":[198],"multiple":[200],"real-world":[201],"datasets":[203],"simulated":[206],"system":[207],"number":[211],"clients,":[213],"showing":[214],"up":[215],"25%":[217],"improvement":[218],"accuracy":[221],"compared":[222],"data.":[227]},"counts_by_year":[{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":2},{"year":2023,"cited_by_count":3},{"year":2022,"cited_by_count":2},{"year":2021,"cited_by_count":7},{"year":2020,"cited_by_count":1}],"updated_date":"2026-04-10T15:06:20.359241","created_date":"2025-10-10T00:00:00"}