{"id":"https://openalex.org/W3101293418","doi":"https://doi.org/10.48550/arxiv.2006.08907","title":"Robust Federated Learning: The Case of Affine Distribution Shifts","display_name":"Robust Federated Learning: The Case of Affine Distribution Shifts","alternate_titles":[],"publication_year":2020,"publication_date":"2020-06-16","ids":{"openalex":"https://openalex.org/W3101293418","doi":"https://doi.org/10.48550/arxiv.2006.08907","mag":"3101293418"},"language":"en","primary_location":{"id":"pmh:oai:arXiv.org:2006.08907","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2006.08907","pdf_url":"https://arxiv.org/pdf/2006.08907","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"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"},"parent_works":[],"lineage":["https://openalex.org/W3101293418"],"child_works_count":0,"type":"preprint","is_traditional":true,"indexed_in":["arxiv","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2006.08907","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5059780399","display_name":"Amirhossein Reisizadeh","orcid":"https://orcid.org/0000-0002-1730-8402","observed_orcids":["https://orcid.org/0000-0002-1730-8402"]},"institutions":[{"id":"https://openalex.org/I154570441","display_name":"University of California, Santa Barbara","ror":"https://ror.org/02t274463","country_code":"US","type":"education","lineage":["https://openalex.org/I154570441"]}],"countries":["US"],"is_corresponding":false,"contributor_roles":[],"raw_author_name":"Reisizadeh, Amirhossein","raw_affiliation_strings":["University of California, Santa Barbara, Santa Barbara, United States"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of California, Santa Barbara, Santa Barbara, United States","institution_ids":["https://openalex.org/I154570441"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5017160178","display_name":"Farzan Farnia","orcid":"https://orcid.org/0000-0002-6049-9232","observed_orcids":["https://orcid.org/0000-0002-6049-9232"]},"institutions":[{"id":"https://openalex.org/I63966007","display_name":"Massachusetts Institute of Technology","ror":"https://ror.org/042nb2s44","country_code":"US","type":"education","lineage":["https://openalex.org/I63966007"]}],"countries":["US"],"is_corresponding":false,"contributor_roles":[],"raw_author_name":"Farnia, Farzan","raw_affiliation_strings":["Massachusetts Institute of Technology, Cambridge, United States"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Massachusetts Institute of Technology, Cambridge, United States","institution_ids":["https://openalex.org/I63966007"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5040270189","display_name":"Ramtin Pedarsani","orcid":"https://orcid.org/0000-0002-1126-0292","observed_orcids":["https://orcid.org/0000-0002-1126-0292"]},"institutions":[{"id":"https://openalex.org/I154570441","display_name":"University of California, Santa Barbara","ror":"https://ror.org/02t274463","country_code":"US","type":"education","lineage":["https://openalex.org/I154570441"]}],"countries":["US"],"is_corresponding":false,"contributor_roles":[],"raw_author_name":"Pedarsani, Ramtin","raw_affiliation_strings":["University of California, Santa Barbara, Santa Barbara, United States"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of California, Santa Barbara, Santa Barbara, United States","institution_ids":["https://openalex.org/I154570441"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5078288116","display_name":"Ali Jadbabaie","orcid":"https://orcid.org/0000-0003-1122-3069","observed_orcids":["https://orcid.org/0000-0003-1122-3069"]},"institutions":[{"id":"https://openalex.org/I63966007","display_name":"Massachusetts Institute of Technology","ror":"https://ror.org/042nb2s44","country_code":"US","type":"education","lineage":["https://openalex.org/I63966007"]}],"countries":["US"],"is_corresponding":false,"contributor_roles":[],"raw_author_name":"Jadbabaie, Ali","raw_affiliation_strings":["Massachusetts Institute of Technology, Cambridge, United States"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Massachusetts Institute of Technology, Cambridge, United States","institution_ids":["https://openalex.org/I63966007"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"cited_by_count":210,"reviewed_by_count":0,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":"33","issue":null,"first_page":"21554","last_page":"21565"},"is_retracted":false,"is_pulled":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10764","display_name":"Privacy-Preserving Technologies in Data","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/T10764","display_name":"Privacy-Preserving Technologies in Data","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/T11612","display_name":"Stochastic Gradient Optimization Techniques","score":0.00019999999494757503,"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/T11307","display_name":"Domain Adaptation and Few-Shot Learning","score":9.999999747378752e-05,"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/federated-learning","display_name":"federated learning","score":0.8479999899864197},{"id":"https://openalex.org/keywords/device-heterogeneity","display_name":"heterogeneous devices","score":0.6790000200271606},{"id":"https://openalex.org/keywords/robustness","display_name":"robustness","score":0.5120000243186951},{"id":"https://openalex.org/keywords/gradient-descent-ascent","display_name":"gradient descent ascent","score":0.9710000157356262},{"id":"https://openalex.org/keywords/generalization-bounds","display_name":"generalization bounds","score":0.8190000057220459},{"id":"https://openalex.org/keywords/image-classification","display_name":"image classification","score":0.652999997138977},{"id":"https://openalex.org/keywords/privacy-preserving-machine-learning","display_name":"privacy-preserving machine learning","score":0.574999988079071}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7776689529418945},{"id":"https://openalex.org/C92757383","wikidata":"https://www.wikidata.org/wiki/Q382497","display_name":"Affine transformation","level":2,"score":0.7736872434616089},{"id":"https://openalex.org/C149728462","wikidata":"https://www.wikidata.org/wiki/Q751319","display_name":"Minimax","level":2,"score":0.7180088758468628},{"id":"https://openalex.org/C153258448","wikidata":"https://www.wikidata.org/wiki/Q1199743","display_name":"Gradient descent","level":3,"score":0.6054412126541138},{"id":"https://openalex.org/C95623464","wikidata":"https://www.wikidata.org/wiki/Q1096149","display_name":"Classifier (UML)","level":2,"score":0.5828713178634644},{"id":"https://openalex.org/C2992525071","wikidata":"https://www.wikidata.org/wiki/Q50818671","display_name":"Federated learning","level":2,"score":0.5233078002929688},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4837365448474884},{"id":"https://openalex.org/C177148314","wikidata":"https://www.wikidata.org/wiki/Q170084","display_name":"Generalization","level":2,"score":0.4770504832267761},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.4142771363258362},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.34919416904449463},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.30766570568084717},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.19034218788146973},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.15214350819587708},{"id":"https://openalex.org/C202444582","wikidata":"https://www.wikidata.org/wiki/Q837863","display_name":"Pure mathematics","level":1,"score":0.0},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.0}],"mesh":[],"locations_count":4,"locations":[{"id":"pmh:oai:arXiv.org:2006.08907","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2006.08907","pdf_url":"https://arxiv.org/pdf/2006.08907","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"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"},{"id":"pmh:oai:escholarship.org/ark:/13030/qt2cb061m3","doi":null,"is_oa":true,"landing_page_url":"https://escholarship.org/uc/item/2cb061m3","pdf_url":null,"source":{"id":"https://openalex.org/S4306400115","display_name":"eScholarship (California Digital Library)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I2801248553","host_organization_name":"California Digital Library","host_organization_lineage":["https://openalex.org/I2801248553"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"article"},{"id":"doi:10.48550/arxiv.2006.08907","doi":"https://doi.org/10.48550/arxiv.2006.08907","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2006.08907","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"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":false,"raw_source_name":null,"raw_type":"Preprint"},{"id":"mag:3101293418","doi":null,"is_oa":false,"landing_page_url":"https://proceedings.neurips.cc/paper/2020/file/f5e536083a438cec5b64a4954abc17f1-Paper.pdf","pdf_url":null,"source":{"id":"https://openalex.org/S4363606243","display_name":"neural information processing systems","issn_l":"1049-5258","issn":["1049-5258"],"is_oa":false,"is_in_doaj":false,"is_core":true,"listed_in":["cwts-core","norway-2"],"host_organization":"https://openalex.org/P4404678063","host_organization_name":"Neural Information Processing Systems Foundation","host_organization_lineage":["https://openalex.org/P4404678063"],"host_organization_lineage_names":["Neural Information Processing Systems Foundation"],"type":"conference"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false,"raw_source_name":"Neural Information Processing Systems","raw_type":null}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2006.08907","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2006.08907","pdf_url":"https://arxiv.org/pdf/2006.08907","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"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":[],"study_designs":[],"awards":[{"id":"https://openalex.org/G2407286371","display_name":null,"funder_award_id":"N00014-20-1-2394","funder_id":"https://openalex.org/F4320337345","funder_display_name":"Office of Naval Research"},{"id":"https://openalex.org/G5580501993","display_name":"CIF: Small: A Systematic Approach to Adversarial Machine Learning: Sparsity-based Defenses and Locally Linear Attacks","funder_award_id":"1909320","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G8805048880","display_name":"MLWiNS: Optimization and Coding Theory for Fast and Robust Wireless Distributed Learning","funder_award_id":"2003035","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"},{"id":"https://openalex.org/F4320337345","display_name":"Office of Naval Research","ror":"https://ror.org/00rk2pe57"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W3101293418.pdf","grobid_xml":"https://content.openalex.org/works/W3101293418.grobid-xml"},"referenced_works_count":47,"referenced_works":["https://openalex.org/W1836465849","https://openalex.org/W1945616565","https://openalex.org/W2029029543","https://openalex.org/W2097117768","https://openalex.org/W2125417745","https://openalex.org/W2163605009","https://openalex.org/W2194775991","https://openalex.org/W2271840356","https://openalex.org/W2535838896","https://openalex.org/W2541884796","https://openalex.org/W2543927648","https://openalex.org/W2616028256","https://openalex.org/W2640329709","https://openalex.org/W2709553318","https://openalex.org/W2741952635","https://openalex.org/W2777914285","https://openalex.org/W2803867449","https://openalex.org/W2896404430","https://openalex.org/W2900578291","https://openalex.org/W2902114605","https://openalex.org/W2903272733","https://openalex.org/W2905444686","https://openalex.org/W2905631704","https://openalex.org/W2911327153","https://openalex.org/W2912592113","https://openalex.org/W2944525415","https://openalex.org/W2944542720","https://openalex.org/W2947996939","https://openalex.org/W2955213239","https://openalex.org/W2964110122","https://openalex.org/W2964121744","https://openalex.org/W2970416783","https://openalex.org/W2972652285","https://openalex.org/W2975043678","https://openalex.org/W2981206218","https://openalex.org/W2982654255","https://openalex.org/W2995022099","https://openalex.org/W2995653155","https://openalex.org/W2996564870","https://openalex.org/W2997502936","https://openalex.org/W3001825675","https://openalex.org/W3006555759","https://openalex.org/W3007136572","https://openalex.org/W3021654819","https://openalex.org/W3028483575","https://openalex.org/W3147600416","https://openalex.org/W7014838995"],"related_works":["https://openalex.org/W4320459812","https://openalex.org/W4281970528","https://openalex.org/W6926661418","https://openalex.org/W7128541908","https://openalex.org/W4393159856","https://openalex.org/W7133359158","https://openalex.org/W3193589553","https://openalex.org/W4415336602","https://openalex.org/W7124959514","https://openalex.org/W3217639405"],"abstract_inverted_index":{"Federated":[0,145],"learning":[1,73,117,263],"is":[2,42,67,112,155],"a":[3,18,70,92,144,177,188,246,255],"distributed":[4,13,172],"paradigm":[5],"that":[6,75,100,154,229],"aims":[7],"at":[8],"training":[9,40,266],"models":[10],"using":[11],"samples":[12,23,212],"across":[14,51,140],"multiple":[15],"users":[16,34],"in":[17,82,97,106,245,258],"network":[19],"while":[20],"keeping":[21],"the":[22,28,39,55,58,102,124,163,170,201,214,239,242],"on":[24],"users'":[25,83,98],"devices":[26],"with":[27],"aim":[29],"of":[30,57,64,165,211,241],"efficiency":[31],"and":[32,46,133,179,183,250,264],"protecting":[33],"privacy.":[35],"In":[36],"such":[37,119],"settings,":[38],"data":[41,99,104],"often":[43],"statistically":[44],"heterogeneous":[45],"manifests":[47],"various":[48,115],"distribution":[49,80,95,138,151,164,210,232],"shifts":[50,81,139,152,161],"users,":[52,141],"which":[53],"degrades":[54],"performance":[56,78,240],"learnt":[59,202,243],"model.":[60],"The":[61],"primary":[62],"goal":[63],"this":[65,87],"paper":[66],"to":[68,114,149,162,204,213,223,236,260],"develop":[69],"robust":[71,157],"federated":[72,107,116,262],"algorithm":[74,253],"achieves":[76,254],"satisfactory":[77],"against":[79,158],"samples.":[84,167],"To":[85,135,168],"achieve":[86],"goal,":[88],"we":[89,142,175],"first":[90],"consider":[91],"structured":[93],"affine":[94,137,159,231],"shift":[96,233],"captures":[101],"device-dependent":[103,127],"heterogeneity":[105],"settings.":[108],"This":[109],"perturbation":[110],"model":[111],"applicable":[113],"problems":[118],"as":[120],"image":[121],"classification":[122],"where":[123],"images":[125],"undergo":[126],"imperfections,":[128],"e.g.":[129],"different":[130],"intensity,":[131],"contrast,":[132],"brightness.":[134],"address":[136],"propose":[143,176],"Learning":[146],"framework":[147],"Robust":[148],"Affine":[150],"(FLRA)":[153],"provably":[156],"Wasserstein":[160],"observed":[166],"solve":[169],"FLRA's":[171],"minimax":[173],"problem,":[174],"fast":[178],"efficient":[180],"optimization":[181],"method":[182],"provide":[184],"convergence":[185],"guarantees":[186],"via":[187],"gradient":[189],"Descent":[190],"Ascent":[191],"(GDA)":[192],"method.":[193],"We":[194,218,227],"further":[195],"prove":[196],"generalization":[197,207],"error":[198],"bounds":[199],"for":[200],"classifier":[203,244],"show":[205,228],"proper":[206],"from":[208],"empirical":[209],"true":[215],"underlying":[216],"distribution.":[217],"perform":[219],"several":[220],"numerical":[221],"experiments":[222],"empirically":[224],"support":[225],"FLRA.":[226],"an":[230],"indeed":[234],"suffices":[235],"significantly":[237],"decrease":[238],"new":[247],"test":[248],"user,":[249],"our":[251],"proposed":[252],"significant":[256],"gain":[257],"comparison":[259],"standard":[261],"adversarial":[265],"methods.":[267]},"cited_by_api_url":"https://api.openalex.org/works?filter=cites:W3101293418","counts_by_year":[{"year":2026,"cited_by_count":29},{"year":2025,"cited_by_count":32},{"year":2024,"cited_by_count":47},{"year":2023,"cited_by_count":37},{"year":2022,"cited_by_count":43},{"year":2021,"cited_by_count":21},{"year":2020,"cited_by_count":1}],"updated_date":"2026-11-21T10:27:49.728292","created_date":"2020-11-23T00:00:00"}
