{"id":"https://openalex.org/W3123411108","doi":"https://doi.org/10.1145/3517821","title":"Auto-weighted Robust Federated Learning with Corrupted Data Sources","display_name":"Auto-weighted Robust Federated Learning with Corrupted Data Sources","publication_year":2022,"publication_date":"2022-02-23","ids":{"openalex":"https://openalex.org/W3123411108","doi":"https://doi.org/10.1145/3517821","mag":"3123411108"},"language":"en","primary_location":{"id":"doi:10.1145/3517821","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3517821","pdf_url":null,"source":{"id":"https://openalex.org/S2492086750","display_name":"ACM Transactions on Intelligent Systems and Technology","issn_l":"2157-6904","issn":["2157-6904","2157-6912"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319798","host_organization_name":"Association for Computing Machinery","host_organization_lineage":["https://openalex.org/P4310319798"],"host_organization_lineage_names":["Association for Computing Machinery"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ACM Transactions on Intelligent Systems and Technology","raw_type":"journal-article"},"type":"article","indexed_in":["arxiv","crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2101.05880","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5100625222","display_name":"Shenghui Li","orcid":"https://orcid.org/0000-0003-0145-3127"},"institutions":[{"id":"https://openalex.org/I123387679","display_name":"Uppsala University","ror":"https://ror.org/048a87296","country_code":"SE","type":"education","lineage":["https://openalex.org/I123387679"]}],"countries":["SE"],"is_corresponding":true,"raw_author_name":"Shenghui Li","raw_affiliation_strings":["Uppsala University, Uppsala, Sweden"],"raw_orcid":"https://orcid.org/0000-0003-0145-3127","affiliations":[{"raw_affiliation_string":"Uppsala University, Uppsala, Sweden","institution_ids":["https://openalex.org/I123387679"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5077317339","display_name":"Edith C.\u2010H. Ngai","orcid":"https://orcid.org/0000-0002-3454-8731"},"institutions":[{"id":"https://openalex.org/I889458895","display_name":"University of Hong Kong","ror":"https://ror.org/02zhqgq86","country_code":"HK","type":"education","lineage":["https://openalex.org/I889458895"]}],"countries":["HK"],"is_corresponding":false,"raw_author_name":"Edith Ngai","raw_affiliation_strings":["The University of Hong Kong, Hong Kong, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"The University of Hong Kong, Hong Kong, China","institution_ids":["https://openalex.org/I889458895"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5078520300","display_name":"Fanghua Ye","orcid":"https://orcid.org/0000-0002-1063-6534"},"institutions":[{"id":"https://openalex.org/I45129253","display_name":"University College London","ror":"https://ror.org/02jx3x895","country_code":"GB","type":"education","lineage":["https://openalex.org/I124357947","https://openalex.org/I45129253"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Fanghua Ye","raw_affiliation_strings":["University College London, London, UK"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University College London, London, UK","institution_ids":["https://openalex.org/I45129253"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5071943253","display_name":"Thiemo Voigt","orcid":"https://orcid.org/0000-0002-2586-8573"},"institutions":[{"id":"https://openalex.org/I123387679","display_name":"Uppsala University","ror":"https://ror.org/048a87296","country_code":"SE","type":"education","lineage":["https://openalex.org/I123387679"]},{"id":"https://openalex.org/I2800664555","display_name":"RISE Research Institutes of Sweden","ror":"https://ror.org/03nnxqz81","country_code":"SE","type":"other","lineage":["https://openalex.org/I2800664555"]}],"countries":["SE"],"is_corresponding":false,"raw_author_name":"Thiemo Voigt","raw_affiliation_strings":["Uppsala University and Research Institutes of Sweden (RISE), Stockholm, Sweden"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Uppsala University and Research Institutes of Sweden (RISE), Stockholm, Sweden","institution_ids":["https://openalex.org/I2800664555","https://openalex.org/I123387679"]}]}],"institutions":[],"countries_distinct_count":3,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5100625222"],"corresponding_institution_ids":["https://openalex.org/I123387679"],"apc_list":null,"apc_paid":null,"fwci":4.7165,"has_fulltext":false,"cited_by_count":34,"citation_normalized_percentile":{"value":0.95337112,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":97,"max":99},"biblio":{"volume":"13","issue":"5","first_page":"1","last_page":"20"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10764","display_name":"Privacy-Preserving Technologies in Data","score":1.0,"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":1.0,"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/T11704","display_name":"Mobile Crowdsensing and Crowdsourcing","score":0.9825000166893005,"subfield":{"id":"https://openalex.org/subfields/1706","display_name":"Computer Science Applications"},"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/T11612","display_name":"Stochastic Gradient Optimization Techniques","score":0.9693999886512756,"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":0.8904598951339722},{"id":"https://openalex.org/keywords/outlier","display_name":"Outlier","score":0.7528595924377441},{"id":"https://openalex.org/keywords/robustness","display_name":"Robustness (evolution)","score":0.7436779141426086},{"id":"https://openalex.org/keywords/empirical-risk-minimization","display_name":"Empirical risk minimization","score":0.7170687913894653},{"id":"https://openalex.org/keywords/federated-learning","display_name":"Federated learning","score":0.6802118420600891},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.5546513795852661},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.550180196762085},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5233970284461975},{"id":"https://openalex.org/keywords/minification","display_name":"Minification","score":0.4967854619026184},{"id":"https://openalex.org/keywords/regularization","display_name":"Regularization (linguistics)","score":0.4641745090484619},{"id":"https://openalex.org/keywords/deep-neural-networks","display_name":"Deep neural networks","score":0.4552724063396454},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.40864062309265137},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.395550012588501}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8904598951339722},{"id":"https://openalex.org/C79337645","wikidata":"https://www.wikidata.org/wiki/Q779824","display_name":"Outlier","level":2,"score":0.7528595924377441},{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.7436779141426086},{"id":"https://openalex.org/C107321475","wikidata":"https://www.wikidata.org/wiki/Q5374254","display_name":"Empirical risk minimization","level":2,"score":0.7170687913894653},{"id":"https://openalex.org/C2992525071","wikidata":"https://www.wikidata.org/wiki/Q50818671","display_name":"Federated learning","level":2,"score":0.6802118420600891},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.5546513795852661},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.550180196762085},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5233970284461975},{"id":"https://openalex.org/C147764199","wikidata":"https://www.wikidata.org/wiki/Q6865248","display_name":"Minification","level":2,"score":0.4967854619026184},{"id":"https://openalex.org/C2776135515","wikidata":"https://www.wikidata.org/wiki/Q17143721","display_name":"Regularization (linguistics)","level":2,"score":0.4641745090484619},{"id":"https://openalex.org/C2984842247","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep neural networks","level":3,"score":0.4552724063396454},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.40864062309265137},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.395550012588501},{"id":"https://openalex.org/C55493867","wikidata":"https://www.wikidata.org/wiki/Q7094","display_name":"Biochemistry","level":1,"score":0.0},{"id":"https://openalex.org/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"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/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"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/C13280743","wikidata":"https://www.wikidata.org/wiki/Q131089","display_name":"Geodesy","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1145/3517821","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3517821","pdf_url":null,"source":{"id":"https://openalex.org/S2492086750","display_name":"ACM Transactions on Intelligent Systems and Technology","issn_l":"2157-6904","issn":["2157-6904","2157-6912"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319798","host_organization_name":"Association for Computing Machinery","host_organization_lineage":["https://openalex.org/P4310319798"],"host_organization_lineage_names":["Association for Computing Machinery"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ACM Transactions on Intelligent Systems and Technology","raw_type":"journal-article"},{"id":"pmh:oai:arXiv.org:2101.05880","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2101.05880","pdf_url":"https://arxiv.org/pdf/2101.05880","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"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2101.05880","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2101.05880","pdf_url":"https://arxiv.org/pdf/2101.05880","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":[{"display_name":"Peace, Justice and strong institutions","id":"https://metadata.un.org/sdg/16","score":0.8199999928474426}],"awards":[{"id":"https://openalex.org/G3483627843","display_name":null,"funder_award_id":"2017-04543","funder_id":"https://openalex.org/F4320322581","funder_display_name":"Vetenskapsr\u00e5det"}],"funders":[{"id":"https://openalex.org/F4320322581","display_name":"Vetenskapsr\u00e5det","ror":"https://ror.org/03zttf063"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":66,"referenced_works":["https://openalex.org/W607505555","https://openalex.org/W2025183033","https://openalex.org/W2082639035","https://openalex.org/W2111296615","https://openalex.org/W2165533158","https://openalex.org/W2271840356","https://openalex.org/W2296319761","https://openalex.org/W2312507444","https://openalex.org/W2530417694","https://openalex.org/W2535838896","https://openalex.org/W2541884796","https://openalex.org/W2614254310","https://openalex.org/W2734358244","https://openalex.org/W2752689052","https://openalex.org/W2900182564","https://openalex.org/W2902113386","https://openalex.org/W2904190483","https://openalex.org/W2911736639","https://openalex.org/W2912213068","https://openalex.org/W2944232152","https://openalex.org/W2952782294","https://openalex.org/W2962688627","https://openalex.org/W2963165390","https://openalex.org/W2963179579","https://openalex.org/W2963289726","https://openalex.org/W2963422767","https://openalex.org/W2963819344","https://openalex.org/W2964279249","https://openalex.org/W2971342441","https://openalex.org/W2972570881","https://openalex.org/W2981337066","https://openalex.org/W2985986882","https://openalex.org/W2995735216","https://openalex.org/W2996644705","https://openalex.org/W2996736801","https://openalex.org/W2996769125","https://openalex.org/W2997547170","https://openalex.org/W2997676382","https://openalex.org/W3003426262","https://openalex.org/W3010262580","https://openalex.org/W3016169665","https://openalex.org/W3035046187","https://openalex.org/W3046219242","https://openalex.org/W3082656638","https://openalex.org/W3097714942","https://openalex.org/W3102031770","https://openalex.org/W3103802018","https://openalex.org/W3107632872","https://openalex.org/W3112076925","https://openalex.org/W3129362180","https://openalex.org/W3209546151","https://openalex.org/W3212066104","https://openalex.org/W3217759167","https://openalex.org/W4210968720","https://openalex.org/W4236362309","https://openalex.org/W4252654521","https://openalex.org/W4287977550","https://openalex.org/W4289147229","https://openalex.org/W4297687186","https://openalex.org/W6694517276","https://openalex.org/W6756756286","https://openalex.org/W6769363519","https://openalex.org/W6772265129","https://openalex.org/W6774857738","https://openalex.org/W6781730173","https://openalex.org/W6830701505"],"related_works":["https://openalex.org/W4298221930","https://openalex.org/W2777914285","https://openalex.org/W4378677776","https://openalex.org/W3006513224","https://openalex.org/W3013363440","https://openalex.org/W2046456988","https://openalex.org/W4220659530","https://openalex.org/W4286971788","https://openalex.org/W3199340467","https://openalex.org/W2785875001"],"abstract_inverted_index":{"Federated":[0,56],"learning":[1,11,24,86],"provides":[2],"a":[3,61,85,128,202],"communication-efficient":[4,203],"and":[5,70,97,222,245,248],"privacy-preserving":[6],"training":[7],"process":[8],"by":[9,52,137],"enabling":[10],"statistical":[12],"models":[13],"with":[14,92,127,145,163],"massive":[15],"participants":[16],"without":[17],"accessing":[18],"their":[19,169],"local":[20,74],"data.":[21],"Standard":[22],"federated":[23,111],"techniques":[25],"that":[26,64,117,177,232],"naively":[27],"minimize":[28],"an":[29,115],"average":[30,147],"loss":[31,91],"function":[32],"are":[33],"vulnerable":[34],"to":[35,76,94,171],"data":[36,81,184],"corruptions":[37],"from":[38,191],"outliers,":[39],"systematic":[40],"mislabeling,":[41],"or":[42],"even":[43],"adversaries.":[44],"In":[45],"this":[46,50,178],"article,":[47],"we":[48,200],"address":[49],"challenge":[51],"proposing":[53],"Auto-weighted":[54],"Robust":[55],"Learning":[57],"(":[58],"ARFL":[59],"),":[60],"novel":[62],"approach":[63,179],"jointly":[65],"learns":[66],"the":[67,71,89,95,98,104,107,119,132,139,146,151,161,172,183,192,197,207,250],"global":[68,173],"model":[69],"weights":[72,99,133],"of":[73,100,106,122,125,142,150,185],"updates":[75],"provide":[77],"robustness":[78,181],"against":[79,237],"corrupted":[80,186],"sources.":[82],"We":[83,113,175,211],"prove":[84],"bound":[87],"on":[88,206,215],"expected":[90],"respect":[93],"predictor":[96],"clients,":[101],"which":[102],"guides":[103],"definition":[105],"objective":[108,116,198],"for":[109],"robust":[110,236],"learning.":[112],"present":[114],"minimizes":[118],"weighted":[120],"sum":[121],"empirical":[123,140,148],"risk":[124,141,149],"clients":[126,162,187],"regularization":[129],"term,":[130],"where":[131],"can":[134,159],"be":[135],"allocated":[136],"comparing":[138],"each":[143],"client":[144],"best":[152],"\\(":[153],"p":[154],"\\)":[155],"clients.":[156],"This":[157],"method":[158],"downweight":[160],"significantly":[164],"higher":[165],"losses,":[166],"thereby":[167],"lowering":[168],"contributions":[170],"model.":[174],"show":[176,231],"achieves":[180],"when":[182],"is":[188,235],"distributed":[189],"differently":[190],"benign":[193],"ones.":[194],"To":[195],"optimize":[196],"function,":[199],"propose":[201],"algorithm":[204],"based":[205],"blockwise":[208],"minimization":[209],"paradigm.":[210],"conduct":[212],"extensive":[213],"experiments":[214],"multiple":[216],"benchmark":[217],"datasets,":[218],"including":[219,240],"CIFAR-10,":[220],"FEMNIST,":[221],"Shakespeare,":[223],"considering":[224],"different":[225,238],"neural":[226],"network":[227],"models.":[228],"The":[229],"results":[230],"our":[233],"solution":[234],"scenarios,":[239],"label":[241,243],"shuffling,":[242],"flipping,":[244],"noisy":[246],"features,":[247],"outperforms":[249],"state-of-the-art":[251],"methods":[252],"in":[253],"most":[254],"scenarios.":[255]},"counts_by_year":[{"year":2025,"cited_by_count":10},{"year":2024,"cited_by_count":6},{"year":2023,"cited_by_count":13},{"year":2022,"cited_by_count":5}],"updated_date":"2026-05-21T06:26:12.895304","created_date":"2025-10-10T00:00:00"}