{"id":"https://openalex.org/W3135959773","doi":null,"title":"FedGP: Correlation-Based Active Client Selection for Heterogeneous Federated Learning","display_name":"FedGP: Correlation-Based Active Client Selection for Heterogeneous Federated Learning","publication_year":2021,"publication_date":"2021-03-24","ids":{"openalex":"https://openalex.org/W3135959773","mag":"3135959773"},"language":"en","primary_location":{"id":"mag:3135959773","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/pdf/2103.13822v1","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":"https://arxiv.org/pdf/2103.13822v1","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5109442652","display_name":"Minxue Tang","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I170897317","display_name":"Duke University","ror":"https://ror.org/00py81415","country_code":"US","type":"education","lineage":["https://openalex.org/I170897317"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Minxue Tang","raw_affiliation_strings":["Duke University#TAB#"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Duke University#TAB#","institution_ids":["https://openalex.org/I170897317"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5086217226","display_name":"Xuefei Ning","orcid":"https://orcid.org/0000-0003-2209-8312","observed_orcids":["https://orcid.org/0000-0003-2209-8312"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Xuefei Ning","raw_affiliation_strings":[],"raw_orcid":"https://orcid.org/0000-0003-2209-8312","affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5011262125","display_name":"Yitu Wang","orcid":"https://orcid.org/0000-0003-4453-5966","observed_orcids":["https://orcid.org/0000-0003-4453-5966"]},"institutions":[{"id":"https://openalex.org/I170897317","display_name":"Duke University","ror":"https://ror.org/00py81415","country_code":"US","type":"education","lineage":["https://openalex.org/I170897317"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Yitu Wang","raw_affiliation_strings":["Duke University#TAB#"],"raw_orcid":"https://orcid.org/0000-0003-4453-5966","affiliations":[{"raw_affiliation_string":"Duke University#TAB#","institution_ids":["https://openalex.org/I170897317"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Yu Wang","orcid":"https://orcid.org/0000-0003-3511-0288","observed_orcids":["https://orcid.org/0000-0003-3511-0288"]},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yu Wang","raw_affiliation_strings":["Tsinghua University"],"raw_orcid":"https://orcid.org/0000-0003-3511-0288","affiliations":[{"raw_affiliation_string":"Tsinghua University","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5058073627","display_name":"Yiran Chen","orcid":"https://orcid.org/0000-0002-1486-8412","observed_orcids":["https://orcid.org/0000-0002-1486-8412","https://orcid.org/0009-0007-6890-2018","https://orcid.org/0009-0001-2437-3763"]},"institutions":[{"id":"https://openalex.org/I170897317","display_name":"Duke University","ror":"https://ror.org/00py81415","country_code":"US","type":"education","lineage":["https://openalex.org/I170897317"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Yiran Chen","raw_affiliation_strings":["Duke University#TAB#"],"raw_orcid":"https://orcid.org/0000-0002-1486-8412","affiliations":[{"raw_affiliation_string":"Duke University#TAB#","institution_ids":["https://openalex.org/I170897317"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":13,"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":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":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/federated-learning","display_name":"federated learning","score":0.8479999899864197},{"id":"https://openalex.org/keywords/loss-correlations","display_name":"loss correlations","score":0.8619999885559082},{"id":"https://openalex.org/keywords/gaussian-processes","display_name":"Gaussian processes","score":0.9520000219345093},{"id":"https://openalex.org/keywords/convergence-rate","display_name":"convergence rate","score":0.8610000014305115},{"id":"https://openalex.org/keywords/communication-overhead-reduction","display_name":"communication cost reduction","score":0.8100000023841858},{"id":"https://openalex.org/keywords/heterogeneous-data-distributions","display_name":"heterogeneous data distributions","score":0.5720000267028809}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7450479865074158},{"id":"https://openalex.org/C81917197","wikidata":"https://www.wikidata.org/wiki/Q628760","display_name":"Selection (genetic algorithm)","level":2,"score":0.7369832992553711},{"id":"https://openalex.org/C2777303404","wikidata":"https://www.wikidata.org/wiki/Q759757","display_name":"Convergence (economics)","level":2,"score":0.5880985856056213},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.5440664887428284},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.4918487071990967},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4352806806564331},{"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/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"mag:3135959773","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/pdf/2103.13822v1","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:3135959773","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/pdf/2103.13822v1","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":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":27,"referenced_works":["https://openalex.org/W1522301498","https://openalex.org/W1591699755","https://openalex.org/W1746819321","https://openalex.org/W2116612304","https://openalex.org/W2140539195","https://openalex.org/W2187089797","https://openalex.org/W2192203593","https://openalex.org/W2535838896","https://openalex.org/W2541884796","https://openalex.org/W2750384547","https://openalex.org/W2914328083","https://openalex.org/W2963300197","https://openalex.org/W2964286272","https://openalex.org/W2968239693","https://openalex.org/W2972570881","https://openalex.org/W2975985894","https://openalex.org/W2981206218","https://openalex.org/W2995022099","https://openalex.org/W2996442797","https://openalex.org/W3006555759","https://openalex.org/W3021654819","https://openalex.org/W3046178819","https://openalex.org/W3048121440","https://openalex.org/W3089426191","https://openalex.org/W3101293418","https://openalex.org/W3118608800","https://openalex.org/W3194243671"],"related_works":["https://openalex.org/W4312429505","https://openalex.org/W4408145113","https://openalex.org/W4320521973","https://openalex.org/W7162013894","https://openalex.org/W4404738223","https://openalex.org/W4391661602","https://openalex.org/W4386260702","https://openalex.org/W4312052117","https://openalex.org/W7124899512","https://openalex.org/W7160383820"],"abstract_inverted_index":{"Client-wise":[0],"heterogeneity":[1],"is":[2],"one":[3],"of":[4,36,90,150],"the":[5,17,26,33,37,51,55,63,87,96,100,109,114,125,131,137,143,164,173],"major":[6],"issues":[7],"that":[8,161],"hinder":[9],"effective":[10],"training":[11,111,122],"in":[12,113,154],"federated":[13,75],"learning":[14,76],"(FL).":[15],"Since":[16],"data":[18],"distribution":[19],"on":[20,79,136,180],"each":[21,155],"client":[22,27,45,82,144,167],"may":[23],"differ":[24],"dramatically,":[25],"selection":[28,46,65,83,145,168],"strategy":[29],"can":[30,171],"largely":[31],"influence":[32],"convergence":[34,88,174],"rate":[35,89],"FL":[38,116],"process.":[39],"Several":[40],"recent":[41],"studies":[42],"adopt":[43],"active":[44,166],"strategies.":[47],"However,":[48],"they":[49],"neglect":[50],"loss":[52,97,153],"correlations":[53,98,138],"between":[54,99],"clients":[56,101],"and":[57,178,182],"achieve":[58],"marginal":[59],"improvement":[60],"compared":[61,162],"to":[62,85,129,163],"uniform":[64],"strategy.":[66],"In":[67],"this":[68],"work,":[69],"we":[70,93,118,139,141],"propose":[71],"FedGP":[72,170],"--":[73],"a":[74,80,103,120],"framework":[77],"built":[78],"correlation-based":[81],"strategy,":[84,169],"boost":[86],"FL.":[91],"Specifically,":[92],"first":[94],"model":[95],"with":[102,146],"Gaussian":[104],"Process":[105],"(GP).":[106],"To":[107],"make":[108],"GP":[110,121],"feasible":[112],"communication-bounded":[115],"process,":[117],"develop":[119],"method":[123],"utilizing":[124],"historical":[126],"samples":[127],"efficiently":[128],"reduce":[130],"communication":[132],"cost.":[133],"Finally,":[134],"based":[135],"learned,":[140],"derive":[142],"an":[147],"enlarged":[148],"reduction":[149],"expected":[151],"global":[152],"round.":[156],"Our":[157],"experimental":[158],"results":[159],"show":[160],"latest":[165],"improve":[172],"rates":[175],"by":[176],"$1.3\\sim2.3\\times$":[177],"$1.2\\sim1.4\\times$":[179],"FMNIST":[181],"CIFAR-10,":[183],"respectively.":[184]},"counts_by_year":[{"year":2024,"cited_by_count":2},{"year":2023,"cited_by_count":5},{"year":2022,"cited_by_count":5},{"year":2021,"cited_by_count":1}],"updated_date":"2026-11-04T10:54:05.112534","created_date":"2021-03-29T00:00:00"}