{"id":"https://openalex.org/W4387760980","doi":"https://doi.org/10.1109/ipccc59175.2023.10253887","title":"Bi-level Sampling: Improved Clients Selection in Heterogeneous Settings for Federated Learning","display_name":"Bi-level Sampling: Improved Clients Selection in Heterogeneous Settings for Federated Learning","publication_year":2023,"publication_date":"2023-10-18","ids":{"openalex":"https://openalex.org/W4387760980","doi":"https://doi.org/10.1109/ipccc59175.2023.10253887"},"language":"en","primary_location":{"id":"doi:10.1109/ipccc59175.2023.10253887","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1109/ipccc59175.2023.10253887","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2023 IEEE International Performance, Computing, and Communications Conference (IPCCC)","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":false,"oa_status":"closed","oa_url":null,"any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5041031990","display_name":"Danyang Xiao","orcid":"https://orcid.org/0000-0001-6798-9683"},"institutions":[{"id":"https://openalex.org/I157773358","display_name":"Sun Yat-sen University","ror":"https://ror.org/0064kty71","country_code":"CN","type":"education","lineage":["https://openalex.org/I157773358"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Danyang Xiao","raw_affiliation_strings":["Sun Yat-sen University"],"affiliations":[{"raw_affiliation_string":"Sun Yat-sen University","institution_ids":["https://openalex.org/I157773358"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5077654624","display_name":"Congcong Zhan","orcid":null},"institutions":[{"id":"https://openalex.org/I157773358","display_name":"Sun Yat-sen University","ror":"https://ror.org/0064kty71","country_code":"CN","type":"education","lineage":["https://openalex.org/I157773358"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Congcong Zhan","raw_affiliation_strings":["Sun Yat-sen University"],"affiliations":[{"raw_affiliation_string":"Sun Yat-sen University","institution_ids":["https://openalex.org/I157773358"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100679362","display_name":"Jialun Li","orcid":"https://orcid.org/0000-0003-0941-9820"},"institutions":[{"id":"https://openalex.org/I157773358","display_name":"Sun Yat-sen University","ror":"https://ror.org/0064kty71","country_code":"CN","type":"education","lineage":["https://openalex.org/I157773358"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jialun Li","raw_affiliation_strings":["Sun Yat-sen University"],"affiliations":[{"raw_affiliation_string":"Sun Yat-sen University","institution_ids":["https://openalex.org/I157773358"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5084826798","display_name":"Weigang Wu","orcid":"https://orcid.org/0000-0002-4714-7021"},"institutions":[{"id":"https://openalex.org/I157773358","display_name":"Sun Yat-sen University","ror":"https://ror.org/0064kty71","country_code":"CN","type":"education","lineage":["https://openalex.org/I157773358"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Weigang Wu","raw_affiliation_strings":["Sun Yat-sen University"],"affiliations":[{"raw_affiliation_string":"Sun Yat-sen University","institution_ids":["https://openalex.org/I157773358"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5041031990"],"corresponding_institution_ids":["https://openalex.org/I157773358"],"apc_list":null,"apc_paid":null,"fwci":0.1746,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.56793969,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":94},"biblio":{"volume":"2022","issue":null,"first_page":"430","last_page":"435"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10764","display_name":"Privacy-Preserving Technologies in Data","score":0.9958000183105469,"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":0.9958000183105469,"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":0.7804646492004395},{"id":"https://openalex.org/keywords/cluster-analysis","display_name":"Cluster analysis","score":0.7584106922149658},{"id":"https://openalex.org/keywords/selection","display_name":"Selection (genetic algorithm)","score":0.6969395875930786},{"id":"https://openalex.org/keywords/sampling","display_name":"Sampling (signal processing)","score":0.625000536441803},{"id":"https://openalex.org/keywords/overhead","display_name":"Overhead (engineering)","score":0.566794216632843},{"id":"https://openalex.org/keywords/variance","display_name":"Variance (accounting)","score":0.5543519258499146},{"id":"https://openalex.org/keywords/sample","display_name":"Sample (material)","score":0.5048444867134094},{"id":"https://openalex.org/keywords/multinomial-distribution","display_name":"Multinomial distribution","score":0.48927661776542664},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.45870885252952576},{"id":"https://openalex.org/keywords/convergence","display_name":"Convergence (economics)","score":0.42577287554740906},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.375215619802475},{"id":"https://openalex.org/keywords/statistics","display_name":"Statistics","score":0.14034578204154968}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7804646492004395},{"id":"https://openalex.org/C73555534","wikidata":"https://www.wikidata.org/wiki/Q622825","display_name":"Cluster analysis","level":2,"score":0.7584106922149658},{"id":"https://openalex.org/C81917197","wikidata":"https://www.wikidata.org/wiki/Q628760","display_name":"Selection (genetic algorithm)","level":2,"score":0.6969395875930786},{"id":"https://openalex.org/C140779682","wikidata":"https://www.wikidata.org/wiki/Q210868","display_name":"Sampling (signal processing)","level":3,"score":0.625000536441803},{"id":"https://openalex.org/C2779960059","wikidata":"https://www.wikidata.org/wiki/Q7113681","display_name":"Overhead (engineering)","level":2,"score":0.566794216632843},{"id":"https://openalex.org/C196083921","wikidata":"https://www.wikidata.org/wiki/Q7915758","display_name":"Variance (accounting)","level":2,"score":0.5543519258499146},{"id":"https://openalex.org/C198531522","wikidata":"https://www.wikidata.org/wiki/Q485146","display_name":"Sample (material)","level":2,"score":0.5048444867134094},{"id":"https://openalex.org/C192065140","wikidata":"https://www.wikidata.org/wiki/Q1147928","display_name":"Multinomial distribution","level":2,"score":0.48927661776542664},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.45870885252952576},{"id":"https://openalex.org/C2777303404","wikidata":"https://www.wikidata.org/wiki/Q759757","display_name":"Convergence (economics)","level":2,"score":0.42577287554740906},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.375215619802475},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.14034578204154968},{"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},{"id":"https://openalex.org/C43617362","wikidata":"https://www.wikidata.org/wiki/Q170050","display_name":"Chromatography","level":1,"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/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.0},{"id":"https://openalex.org/C121955636","wikidata":"https://www.wikidata.org/wiki/Q4116214","display_name":"Accounting","level":1,"score":0.0},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"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/C106131492","wikidata":"https://www.wikidata.org/wiki/Q3072260","display_name":"Filter (signal processing)","level":2,"score":0.0},{"id":"https://openalex.org/C144133560","wikidata":"https://www.wikidata.org/wiki/Q4830453","display_name":"Business","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/ipccc59175.2023.10253887","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1109/ipccc59175.2023.10253887","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2023 IEEE International Performance, Computing, and Communications Conference (IPCCC)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":22,"referenced_works":["https://openalex.org/W2560674852","https://openalex.org/W2605800822","https://openalex.org/W2747329762","https://openalex.org/W2798720628","https://openalex.org/W2972570881","https://openalex.org/W2995022099","https://openalex.org/W3092359860","https://openalex.org/W3095276777","https://openalex.org/W3105122387","https://openalex.org/W3217610115","https://openalex.org/W4205597275","https://openalex.org/W4220719396","https://openalex.org/W4328105406","https://openalex.org/W4375928838","https://openalex.org/W4377079730","https://openalex.org/W6728757088","https://openalex.org/W6759238902","https://openalex.org/W6765541894","https://openalex.org/W6767676916","https://openalex.org/W6773520829","https://openalex.org/W6784343361","https://openalex.org/W6795281715"],"related_works":["https://openalex.org/W2955220190","https://openalex.org/W2305090462","https://openalex.org/W2052791731","https://openalex.org/W2055203911","https://openalex.org/W2117588607","https://openalex.org/W1976212024","https://openalex.org/W2073599813","https://openalex.org/W2058461761","https://openalex.org/W2068420970","https://openalex.org/W2115188409"],"abstract_inverted_index":{"Client":[0],"selection":[1,59],"(a.k.a.,":[2],"client":[3,58,98,132],"sampling)":[4],"is":[5],"one":[6],"of":[7,51,138],"the":[8,29,49,135,139],"hot":[9],"topics":[10],"in":[11,24,42,123,144,181],"Federated":[12],"Learning":[13],"(FL).":[14],"In":[15,87],"each":[16,70,124],"communication":[17,30],"round,":[18],"selecting":[19,44],"some":[20,66],"clients":[21,45,62,68,107,119],"to":[22,39,130],"participate":[23],"aggregation":[25,142],"can":[26,128,148],"effectively":[27],"reduce":[28],"overhead":[31],"caused":[32],"by":[33],"exchanging":[34],"model":[35],"parameters.":[36],"However,":[37,72],"due":[38],"statistical":[40],"heterogeneity":[41],"FL,":[43],"randomly":[46],"may":[47,76],"affect":[48],"performance":[50],"aggregated":[52],"global":[53],"models.":[54],"existing":[55],"approaches":[56,75],"regarding":[57],"firstly":[60],"cluster":[61],"and":[63,115,134,169,176],"then":[64,116],"sample(select)":[65],"representative":[67],"from":[69],"cluster.":[71],"these":[73,85],"clustering-based":[74,95],"be":[77,149],"either":[78],"time-intensive":[79],"or":[80],"high":[81],"complexity.":[82],"To":[83],"address":[84],"issues,":[86],"this":[88],"paper,":[89],"we":[90],"introduce":[91],"Bi-level":[92,104,126],"Sampling,":[93],"a":[94],"approach":[96,147,164],"for":[97,120],"selection.":[99],"After":[100],"multinomial":[101],"distribution":[102],"sampling,":[103],"Sampling":[105,127],"clusters":[106],"based":[108],"on":[109],"weighted":[110],"per-label":[111],"mean":[112],"class":[113],"scores":[114],"selects":[117],"participating":[118],"federated":[121],"learning":[122],"round.":[125],"lead":[129],"better":[131],"representativity":[133],"reduced":[136],"variance":[137],"client\u2019s":[140],"stochastic":[141],"weights":[143],"FL.":[145],"Our":[146],"integrated":[150],"into":[151],"typical":[152],"FL":[153],"frameworks.":[154],"Experimental":[155],"results":[156],"show":[157],"that,":[158],"compared":[159],"with":[160],"state-of-the-art":[161],"approaches,":[162],"our":[163],"demonstrates":[165],"significantly":[166],"more":[167],"stable":[168],"accurate":[170],"convergence":[171],"behavior-getting":[172],"higher":[173],"test":[174],"accuracy":[175],"less":[177],"training":[178],"time,":[179],"especially":[180],"highly":[182],"Non-IID":[183],"settings.":[184]},"counts_by_year":[{"year":2023,"cited_by_count":1}],"updated_date":"2025-12-21T01:58:51.020947","created_date":"2025-10-10T00:00:00"}