{"id":"https://openalex.org/W3170957236","doi":null,"title":"Fed+: A Unified Approach to Robust Personalized Federated Learning","display_name":"Fed+: A Unified Approach to Robust Personalized Federated Learning","publication_year":2020,"publication_date":"2020-09-14","ids":{"openalex":"https://openalex.org/W3170957236","mag":"3170957236"},"language":"en","primary_location":{"id":"mag:3170957236","doi":null,"is_oa":true,"landing_page_url":"http://export.arxiv.org/pdf/2009.06303","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":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"arXiv (Cornell University)","raw_type":null},"volume":null,"type":"preprint","is_traditional":true,"indexed_in":[],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"http://export.arxiv.org/pdf/2009.06303","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":null,"display_name":"P. L. Yu","orcid":"https://orcid.org/0000-0002-4660-6679","observed_orcids":["https://orcid.org/0000-0002-4660-6679"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"P. L. Yu","raw_affiliation_strings":[],"raw_orcid":"https://orcid.org/0000-0002-4660-6679","affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5069854798","display_name":"Achintya Kundu","orcid":"https://orcid.org/0000-0002-1231-7393","observed_orcids":["https://orcid.org/0000-0002-1231-7393"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Achintya Kundu","raw_affiliation_strings":[],"raw_orcid":"https://orcid.org/0000-0002-1231-7393","affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5070946273","display_name":"Laura Wynter","orcid":"https://orcid.org/0000-0001-5169-0214","observed_orcids":["https://orcid.org/0000-0001-5169-0214"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Laura Wynter","raw_affiliation_strings":["IBM"],"raw_orcid":"https://orcid.org/0000-0001-5169-0214","affiliations":[{"raw_affiliation_string":"IBM","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5081958802","display_name":"Shiau Hong Lim","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Shiau Hong Lim","raw_affiliation_strings":["IBM"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"IBM","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":8,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":null,"last_page":null},"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/T11612","display_name":"Stochastic Gradient Optimization Techniques","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"}},{"id":"https://openalex.org/T11307","display_name":"Domain Adaptation and Few-Shot Learning","score":0.0,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/personalized-federated-learning","display_name":"personalized federated learning","score":0.9879999756813049},{"id":"https://openalex.org/keywords/robust-federated-learning","display_name":"robust federated learning","score":0.8560000061988831},{"id":"https://openalex.org/keywords/fed","display_name":"FED","score":0.7710000276565552},{"id":"https://openalex.org/keywords/non-iid-data","display_name":"non-IID data","score":0.8619999885559082},{"id":"https://openalex.org/keywords/robust-aggregation","display_name":"robust aggregation","score":0.6069999933242798},{"id":"https://openalex.org/keywords/straggler-tolerance","display_name":"straggler tolerance","score":0.578000009059906},{"id":"https://openalex.org/keywords/convergence-guarantees","display_name":"convergence guarantees","score":0.6589999794960022},{"id":"https://openalex.org/keywords/non-convex-loss-functions","display_name":"non-convex loss functions","score":0.8029999732971191},{"id":"https://openalex.org/keywords/heterogeneous-computing-environments","display_name":"heterogeneous computing environments","score":0.625},{"id":"https://openalex.org/keywords/financial-portfolio-management","display_name":"financial portfolio management","score":0.8169999718666077}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8009433150291443},{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.7400826811790466},{"id":"https://openalex.org/C2992525071","wikidata":"https://www.wikidata.org/wiki/Q50818671","display_name":"Federated learning","level":2,"score":0.6562027335166931},{"id":"https://openalex.org/C79337645","wikidata":"https://www.wikidata.org/wiki/Q779824","display_name":"Outlier","level":2,"score":0.6445137858390808},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.4957974851131439},{"id":"https://openalex.org/C2777303404","wikidata":"https://www.wikidata.org/wiki/Q759757","display_name":"Convergence (economics)","level":2,"score":0.4532349109649658},{"id":"https://openalex.org/C45374587","wikidata":"https://www.wikidata.org/wiki/Q12525525","display_name":"Computation","level":2,"score":0.4213916063308716},{"id":"https://openalex.org/C2780821815","wikidata":"https://www.wikidata.org/wiki/Q5340806","display_name":"Portfolio","level":2,"score":0.4195190668106079},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.38600417971611023},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3681827187538147},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3127833604812622},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.13861075043678284},{"id":"https://openalex.org/C55493867","wikidata":"https://www.wikidata.org/wiki/Q7094","display_name":"Biochemistry","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},{"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/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"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/C50522688","wikidata":"https://www.wikidata.org/wiki/Q189833","display_name":"Economic growth","level":1,"score":0.0},{"id":"https://openalex.org/C106159729","wikidata":"https://www.wikidata.org/wiki/Q2294553","display_name":"Financial economics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"mag:3170957236","doi":null,"is_oa":true,"landing_page_url":"http://export.arxiv.org/pdf/2009.06303","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":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"arXiv (Cornell University)","raw_type":null}],"best_oa_location":{"id":"mag:3170957236","doi":null,"is_oa":true,"landing_page_url":"http://export.arxiv.org/pdf/2009.06303","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":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"arXiv (Cornell University)","raw_type":null},"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":24,"referenced_works":["https://openalex.org/W1845277745","https://openalex.org/W2087714402","https://openalex.org/W2112796928","https://openalex.org/W2116612304","https://openalex.org/W2165150801","https://openalex.org/W2250539671","https://openalex.org/W2535838896","https://openalex.org/W2541884796","https://openalex.org/W2731083990","https://openalex.org/W2734358244","https://openalex.org/W2902113386","https://openalex.org/W2914328083","https://openalex.org/W2949377959","https://openalex.org/W2981206218","https://openalex.org/W2996769125","https://openalex.org/W3005776401","https://openalex.org/W3007548213","https://openalex.org/W3012968339","https://openalex.org/W3035353486","https://openalex.org/W3039258010","https://openalex.org/W3100393648","https://openalex.org/W3111777903","https://openalex.org/W3132692395","https://openalex.org/W3169039555"],"related_works":["https://openalex.org/W4292973401","https://openalex.org/W4285276690","https://openalex.org/W3086066566","https://openalex.org/W4281708275","https://openalex.org/W3134581569","https://openalex.org/W4315629593","https://openalex.org/W3036814563","https://openalex.org/W7102416886","https://openalex.org/W4416466110","https://openalex.org/W6948387233"],"abstract_inverted_index":{"We":[0,64,158],"present":[1],"a":[2,68,175],"class":[3,24],"of":[4,22,25,42,80,89,101,103,150,162,186],"methods":[5,26],"for":[6,49,112,114],"robust,":[7],"personalized":[8],"federated":[9,16,36,196],"learning,":[10],"called":[11],"Fed+,":[12],"that":[13,71],"unifies":[14],"many":[15],"learning":[17,197],"algorithms.":[18],"The":[19,123],"principal":[20],"advantage":[21],"this":[23,66],"is":[27,126],"to":[28,51,58,76,129,191],"better":[29],"accommodate":[30],"the":[31,40,47,56,73,82,87,99,140,144,148,160,184],"real-world":[32,177],"characteristics":[33],"found":[34],"in":[35,179,194],"training,":[37],"such":[38],"as":[39,171,173],"lack":[41],"IID":[43],"data":[44,105,188],"across":[45,106,154,167],"parties,":[46,107],"need":[48],"robustness":[50],"outliers":[52],"or":[53],"stragglers,":[54],"and":[55,116,120],"requirement":[57],"perform":[59],"well":[60,172],"on":[61,98,174],"party-specific":[62],"datasets.":[63],"achieve":[65],"through":[67,164],"problem":[69,178],"formulation":[70],"allows":[72],"central":[74],"server":[75],"employ":[77],"robust":[78,121],"ways":[79],"aggregating":[81],"local":[83,90,104,151],"models":[84],"while":[85],"keeping":[86],"structure":[88],"computation":[91],"intact.":[92],"Without":[93],"making":[94],"any":[95],"statistical":[96],"assumption":[97],"degree":[100],"heterogeneity":[102,185],"we":[108],"provide":[109],"convergence":[110,141],"guarantees":[111],"Fed+":[113,124,163],"convex":[115],"non-convex":[117],"loss":[118],"functions":[119],"aggregation.":[122],"theory":[125],"also":[127],"equipped":[128],"handle":[130],"heterogeneous":[131],"computing":[132],"environments":[133],"including":[134],"stragglers":[135],"without":[136],"additional":[137],"assumptions;":[138],"specifically,":[139],"results":[142],"cover":[143],"general":[145],"setting":[146],"where":[147,183],"number":[149],"update":[152],"steps":[153],"parties":[155],"can":[156,189],"vary.":[157],"demonstrate":[159],"benefits":[161],"extensive":[165],"experiments":[166],"standard":[168,195],"benchmark":[169],"datasets":[170],"challenging":[176],"financial":[180],"portfolio":[181],"management":[182],"party-level":[187],"lead":[190],"training":[192],"failure":[193],"approaches.":[198]},"counts_by_year":[{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":4},{"year":2022,"cited_by_count":1},{"year":2021,"cited_by_count":2}],"updated_date":"2026-10-16T09:59:22.235173","created_date":"2021-06-22T00:00:00"}