{"id":"https://openalex.org/W4385767680","doi":"https://doi.org/10.24963/ijcai.2023/462","title":"FedSampling: A Better Sampling Strategy for Federated Learning","display_name":"FedSampling: A Better Sampling Strategy for Federated Learning","publication_year":2023,"publication_date":"2023-08-01","ids":{"openalex":"https://openalex.org/W4385767680","doi":"https://doi.org/10.24963/ijcai.2023/462"},"language":"en","primary_location":{"id":"doi:10.24963/ijcai.2023/462","is_oa":true,"landing_page_url":"https://doi.org/10.24963/ijcai.2023/462","pdf_url":"https://www.ijcai.org/proceedings/2023/0462.pdf","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Thirty-Second International Joint Conference on Artificial Intelligence","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://www.ijcai.org/proceedings/2023/0462.pdf","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5035067940","display_name":"Tao Qi","orcid":"https://orcid.org/0000-0002-1250-3217"},"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":"Tao Qi","raw_affiliation_strings":["Department of Electronic Engineering, Tsinghua University, Beijing 100084, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Electronic Engineering, Tsinghua University, Beijing 100084, China","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5076423724","display_name":"Fangzhao Wu","orcid":"https://orcid.org/0000-0001-9138-1272"},"institutions":[{"id":"https://openalex.org/I4210113369","display_name":"Microsoft Research Asia (China)","ror":"https://ror.org/0300m5276","country_code":"CN","type":"company","lineage":["https://openalex.org/I1290206253","https://openalex.org/I4210113369"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Fangzhao Wu","raw_affiliation_strings":["Microsoft Research Asia, Beijing 100080, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Microsoft Research Asia, Beijing 100080, China","institution_ids":["https://openalex.org/I4210113369"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5052577882","display_name":"Lingjuan Lyu","orcid":"https://orcid.org/0000-0003-3170-4994"},"institutions":[{"id":"https://openalex.org/I4210122684","display_name":"Sony Computer Science Laboratories","ror":"https://ror.org/02nc46417","country_code":"JP","type":"facility","lineage":["https://openalex.org/I4210122684"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Lingjuan Lyu","raw_affiliation_strings":["Sony AI, 1-7-1 Konan Minato-ku Tokyo 108-0075, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Sony AI, 1-7-1 Konan Minato-ku Tokyo 108-0075, Japan","institution_ids":["https://openalex.org/I4210122684"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100768896","display_name":"Yongfeng Huang","orcid":"https://orcid.org/0000-0003-3825-2230"},"institutions":[{"id":"https://openalex.org/I4210089285","display_name":"Ji Hua Laboratory","ror":"https://ror.org/006aydy55","country_code":"CN","type":"facility","lineage":["https://openalex.org/I4210089285"]},{"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":"Yongfeng Huang","raw_affiliation_strings":["Department of Electronic Engineering, Tsinghua University, Beijing 100084, China","Institute for Precision Medicine of Tsinghua University, Beijing 102218, China","Zhongguancun Laboratory, Beijing 100094, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Electronic Engineering, Tsinghua University, Beijing 100084, China","institution_ids":["https://openalex.org/I99065089"]},{"raw_affiliation_string":"Institute for Precision Medicine of Tsinghua University, Beijing 102218, China","institution_ids":["https://openalex.org/I99065089"]},{"raw_affiliation_string":"Zhongguancun Laboratory, Beijing 100094, China","institution_ids":["https://openalex.org/I4210089285"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5044651577","display_name":"Xing Xie","orcid":"https://orcid.org/0000-0002-8608-8482"},"institutions":[{"id":"https://openalex.org/I4210113369","display_name":"Microsoft Research Asia (China)","ror":"https://ror.org/0300m5276","country_code":"CN","type":"company","lineage":["https://openalex.org/I1290206253","https://openalex.org/I4210113369"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xing Xie","raw_affiliation_strings":["Microsoft Research Asia, Beijing 100080, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Microsoft Research Asia, Beijing 100080, China","institution_ids":["https://openalex.org/I4210113369"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":4,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":2.8312,"has_fulltext":false,"cited_by_count":13,"citation_normalized_percentile":{"value":0.92610711,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":97,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"4154","last_page":"4162"},"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/T11045","display_name":"Privacy, Security, and Data Protection","score":0.9412999749183655,"subfield":{"id":"https://openalex.org/subfields/3312","display_name":"Sociology and Political Science"},"field":{"id":"https://openalex.org/fields/33","display_name":"Social Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},{"id":"https://openalex.org/T11719","display_name":"Data Quality and Management","score":0.921999990940094,"subfield":{"id":"https://openalex.org/subfields/1803","display_name":"Management Science and Operations Research"},"field":{"id":"https://openalex.org/fields/18","display_name":"Decision Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7989153265953064},{"id":"https://openalex.org/keywords/sample","display_name":"Sample (material)","score":0.6899873614311218},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.6797313690185547},{"id":"https://openalex.org/keywords/federated-learning","display_name":"Federated learning","score":0.6620500683784485},{"id":"https://openalex.org/keywords/sampling","display_name":"Sampling (signal processing)","score":0.587038516998291},{"id":"https://openalex.org/keywords/differential-privacy","display_name":"Differential privacy","score":0.5435388684272766},{"id":"https://openalex.org/keywords/sample-size-determination","display_name":"Sample size determination","score":0.5320713520050049},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.46367737650871277},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.4471462368965149},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.345764696598053},{"id":"https://openalex.org/keywords/statistics","display_name":"Statistics","score":0.0886983871459961}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7989153265953064},{"id":"https://openalex.org/C198531522","wikidata":"https://www.wikidata.org/wiki/Q485146","display_name":"Sample (material)","level":2,"score":0.6899873614311218},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.6797313690185547},{"id":"https://openalex.org/C2992525071","wikidata":"https://www.wikidata.org/wiki/Q50818671","display_name":"Federated learning","level":2,"score":0.6620500683784485},{"id":"https://openalex.org/C140779682","wikidata":"https://www.wikidata.org/wiki/Q210868","display_name":"Sampling (signal processing)","level":3,"score":0.587038516998291},{"id":"https://openalex.org/C23130292","wikidata":"https://www.wikidata.org/wiki/Q5275358","display_name":"Differential privacy","level":2,"score":0.5435388684272766},{"id":"https://openalex.org/C129848803","wikidata":"https://www.wikidata.org/wiki/Q2564360","display_name":"Sample size determination","level":2,"score":0.5320713520050049},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.46367737650871277},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.4471462368965149},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.345764696598053},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.0886983871459961},{"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/C43617362","wikidata":"https://www.wikidata.org/wiki/Q170050","display_name":"Chromatography","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/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"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/C106131492","wikidata":"https://www.wikidata.org/wiki/Q3072260","display_name":"Filter (signal processing)","level":2,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.24963/ijcai.2023/462","is_oa":true,"landing_page_url":"https://doi.org/10.24963/ijcai.2023/462","pdf_url":"https://www.ijcai.org/proceedings/2023/0462.pdf","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Thirty-Second International Joint Conference on Artificial Intelligence","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.24963/ijcai.2023/462","is_oa":true,"landing_page_url":"https://doi.org/10.24963/ijcai.2023/462","pdf_url":"https://www.ijcai.org/proceedings/2023/0462.pdf","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Thirty-Second International Joint Conference on Artificial Intelligence","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G7090494443","display_name":null,"funder_award_id":"2022YFC3302104","funder_id":"https://openalex.org/F4320335777","funder_display_name":"National Key Research and Development Program of China"}],"funders":[{"id":"https://openalex.org/F4320322392","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549"},{"id":"https://openalex.org/F4320335777","display_name":"National Key Research and Development Program of China","ror":null}],"has_content":{"grobid_xml":false,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4385767680.pdf"},"referenced_works_count":31,"referenced_works":["https://openalex.org/W1522301498","https://openalex.org/W1832693441","https://openalex.org/W2027731328","https://openalex.org/W2194775991","https://openalex.org/W2734358244","https://openalex.org/W2798247400","https://openalex.org/W2891952073","https://openalex.org/W2904190483","https://openalex.org/W2955213239","https://openalex.org/W3034503922","https://openalex.org/W3035046187","https://openalex.org/W3043723611","https://openalex.org/W3101970908","https://openalex.org/W3103802018","https://openalex.org/W3111919937","https://openalex.org/W3162275801","https://openalex.org/W3168511142","https://openalex.org/W3169042981","https://openalex.org/W3174074918","https://openalex.org/W3177828909","https://openalex.org/W3183536570","https://openalex.org/W3192324887","https://openalex.org/W3193066552","https://openalex.org/W3200840849","https://openalex.org/W3207947959","https://openalex.org/W4287110849","https://openalex.org/W4287720355","https://openalex.org/W4299283926","https://openalex.org/W4318619660","https://openalex.org/W4382499875","https://openalex.org/W4385245566"],"related_works":["https://openalex.org/W4286971788","https://openalex.org/W3199340467","https://openalex.org/W3157608626","https://openalex.org/W3132132958","https://openalex.org/W4321612632","https://openalex.org/W4322580403","https://openalex.org/W4399147128","https://openalex.org/W3193217249","https://openalex.org/W4280591108","https://openalex.org/W3021849752"],"abstract_inverted_index":{"Federated":[0],"learning":[1,8,27,79,89,104,117],"(FL)":[2],"is":[3,96,111,145],"an":[4],"important":[5],"technique":[6],"for":[7,24,77,114],"models":[9],"from":[10],"decentralized":[11],"data":[12,38,45,73,93,107,140],"in":[13,28],"a":[14,71,120,149,159],"privacy-preserving":[15,150],"way.":[16],"Existing":[17],"FL":[18],"methods":[19],"usually":[20],"uniformly":[21],"sample":[22,127,132,156],"clients":[23,33,42],"local":[25,106,115],"model":[26,53,116],"each":[29,102,109,143],"round.":[30],"However,":[31],"different":[32,37],"may":[34,56],"have":[35,47],"significantly":[36],"sizes,":[39],"and":[40,129],"the":[41,85,124,130,139,154,174],"with":[43,158],"more":[44,48],"cannot":[46],"opportunities":[49],"to":[50,52,58,119,152],"contribute":[51],"training,":[54],"which":[55,81],"lead":[57],"inferior":[59],"performance.":[60],"In":[61,101],"this":[62],"paper,":[63],"instead":[64],"of":[65,87,176],"client":[66,92,110,144],"uniform":[67,74],"sampling,":[68],"we":[69,147],"propose":[70,148],"novel":[72],"sampling":[75],"strategy":[76],"federated":[78,88,103,177],"(FedSampling),":[80],"can":[82,171],"effectively":[83,172],"improve":[84,173],"performance":[86,175],"especially":[90],"when":[91],"size":[94,128,133,141,157],"distribution":[95],"highly":[97],"imbalanced":[98],"across":[99],"clients.":[100,137],"round,":[105],"on":[108,123,134,142,164],"randomly":[112],"sampled":[113],"according":[118],"probability":[121],"based":[122],"server":[125],"desired":[126],"total":[131,155],"all":[135],"available":[136],"Since":[138],"privacy-sensitive,":[146],"way":[151],"estimate":[153],"differential":[160],"privacy":[161],"guarantee.":[162],"Experiments":[163],"four":[165],"benchmark":[166],"datasets":[167],"show":[168],"that":[169],"FedSampling":[170],"learning.":[178]},"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2025,"cited_by_count":5},{"year":2024,"cited_by_count":6}],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}