{"id":"https://openalex.org/W7162013894","doi":"https://doi.org/10.48550/arxiv.2605.20975","title":"Choose Wisely and Privately: Proactive Client Selection for Fair and Efficient Federated Learning","display_name":"Choose Wisely and Privately: Proactive Client Selection for Fair and Efficient Federated Learning","publication_year":2026,"publication_date":"2026-05-20","ids":{"openalex":"https://openalex.org/W7162013894","doi":"https://doi.org/10.48550/arxiv.2605.20975"},"language":null,"primary_location":{"id":"doi:10.48550/arxiv.2605.20975","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2605.20975","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,"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"},"type":"preprint","indexed_in":["datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://doi.org/10.48550/arxiv.2605.20975","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5071072753","display_name":"Adda Akram Bendoukha","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Bendoukha, Adda Akram","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5122609876","display_name":"H\u00e9ber Hwang Arcolezi","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Arcolezi, Heber Hwang","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5136638871","display_name":"Nesrine Kaaniche","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Kaaniche, Nesrine","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5086710605","display_name":"Aymen Boudguiga","orcid":"https://orcid.org/0000-0001-6717-8848"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Boudguiga, Aymen","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"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":0,"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":0.9542999863624573,"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":0.9542999863624573,"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/T11704","display_name":"Mobile Crowdsensing and Crowdsourcing","score":0.009999999776482582,"subfield":{"id":"https://openalex.org/subfields/1706","display_name":"Computer Science Applications"},"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/T10883","display_name":"Ethics and Social Impacts of AI","score":0.007699999958276749,"subfield":{"id":"https://openalex.org/subfields/3311","display_name":"Safety Research"},"field":{"id":"https://openalex.org/fields/33","display_name":"Social Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/differential-privacy","display_name":"Differential privacy","score":0.7369999885559082},{"id":"https://openalex.org/keywords/federated-learning","display_name":"Federated learning","score":0.7008000016212463},{"id":"https://openalex.org/keywords/selection","display_name":"Selection (genetic algorithm)","score":0.5270000100135803},{"id":"https://openalex.org/keywords/relevance","display_name":"Relevance (law)","score":0.5188999772071838},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.490200012922287},{"id":"https://openalex.org/keywords/convergence","display_name":"Convergence (economics)","score":0.4300000071525574},{"id":"https://openalex.org/keywords/information-privacy","display_name":"Information privacy","score":0.40070000290870667},{"id":"https://openalex.org/keywords/computation","display_name":"Computation","score":0.3260999917984009},{"id":"https://openalex.org/keywords/synthetic-data","display_name":"Synthetic data","score":0.31869998574256897}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8008000254631042},{"id":"https://openalex.org/C23130292","wikidata":"https://www.wikidata.org/wiki/Q5275358","display_name":"Differential privacy","level":2,"score":0.7369999885559082},{"id":"https://openalex.org/C2992525071","wikidata":"https://www.wikidata.org/wiki/Q50818671","display_name":"Federated learning","level":2,"score":0.7008000016212463},{"id":"https://openalex.org/C81917197","wikidata":"https://www.wikidata.org/wiki/Q628760","display_name":"Selection (genetic algorithm)","level":2,"score":0.5270000100135803},{"id":"https://openalex.org/C158154518","wikidata":"https://www.wikidata.org/wiki/Q7310970","display_name":"Relevance (law)","level":2,"score":0.5188999772071838},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.490200012922287},{"id":"https://openalex.org/C2777303404","wikidata":"https://www.wikidata.org/wiki/Q759757","display_name":"Convergence (economics)","level":2,"score":0.4300000071525574},{"id":"https://openalex.org/C123201435","wikidata":"https://www.wikidata.org/wiki/Q456632","display_name":"Information privacy","level":2,"score":0.40070000290870667},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.3571000099182129},{"id":"https://openalex.org/C45374587","wikidata":"https://www.wikidata.org/wiki/Q12525525","display_name":"Computation","level":2,"score":0.3260999917984009},{"id":"https://openalex.org/C160920958","wikidata":"https://www.wikidata.org/wiki/Q7662746","display_name":"Synthetic data","level":2,"score":0.31869998574256897},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.31279999017715454},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3070000112056732},{"id":"https://openalex.org/C2777868144","wikidata":"https://www.wikidata.org/wiki/Q7239817","display_name":"Preference elicitation","level":3,"score":0.29919999837875366},{"id":"https://openalex.org/C93226319","wikidata":"https://www.wikidata.org/wiki/Q193137","display_name":"Differential (mechanical device)","level":2,"score":0.2957000136375427},{"id":"https://openalex.org/C99221444","wikidata":"https://www.wikidata.org/wiki/Q1532069","display_name":"Private information retrieval","level":2,"score":0.28949999809265137},{"id":"https://openalex.org/C58489278","wikidata":"https://www.wikidata.org/wiki/Q1172284","display_name":"Data set","level":2,"score":0.2849999964237213},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.2809999883174896},{"id":"https://openalex.org/C93959086","wikidata":"https://www.wikidata.org/wiki/Q6888345","display_name":"Model selection","level":2,"score":0.27889999747276306},{"id":"https://openalex.org/C67186912","wikidata":"https://www.wikidata.org/wiki/Q367664","display_name":"Data modeling","level":2,"score":0.273499995470047},{"id":"https://openalex.org/C152139883","wikidata":"https://www.wikidata.org/wiki/Q252973","display_name":"Mutual information","level":2,"score":0.2678999900817871},{"id":"https://openalex.org/C2779530757","wikidata":"https://www.wikidata.org/wiki/Q1207505","display_name":"Quality (philosophy)","level":2,"score":0.2662000060081482},{"id":"https://openalex.org/C137836250","wikidata":"https://www.wikidata.org/wiki/Q984063","display_name":"Optimization problem","level":2,"score":0.26100000739097595},{"id":"https://openalex.org/C2776654903","wikidata":"https://www.wikidata.org/wiki/Q2601463","display_name":"SAFER","level":2,"score":0.258899986743927},{"id":"https://openalex.org/C2777212361","wikidata":"https://www.wikidata.org/wiki/Q5127848","display_name":"Class (philosophy)","level":2,"score":0.2583000063896179},{"id":"https://openalex.org/C93996380","wikidata":"https://www.wikidata.org/wiki/Q44127","display_name":"Server","level":2,"score":0.2556000053882599},{"id":"https://openalex.org/C140779682","wikidata":"https://www.wikidata.org/wiki/Q210868","display_name":"Sampling (signal processing)","level":3,"score":0.2542000114917755},{"id":"https://openalex.org/C24756922","wikidata":"https://www.wikidata.org/wiki/Q1757694","display_name":"Data quality","level":3,"score":0.2533000111579895}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.48550/arxiv.2605.20975","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2605.20975","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,"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":null,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"doi:10.48550/arxiv.2605.20975","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2605.20975","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,"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"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Federated":[0],"Learning":[1],"enables":[2],"collaborative":[3],"model":[4,30],"training":[5,102],"across":[6],"decentralized":[7],"data":[8,11,44,95,146],"sources":[9],"without":[10],"transfer.":[12],"Averaging-based":[13],"FL":[14],"is":[15,159],"limited":[16],"by":[17],"the":[18,118,124,135,168],"presence":[19],"of":[20,91,120,137],"non-IID":[21],"data,":[22],"which":[23,140,171],"negatively":[24],"impacts":[25],"convergence":[26],"speed":[27],"and":[28,68,98,194],"final":[29],"accuracy.":[31],"Conventional":[32],"alternatives":[33],"suffer":[34],"from":[35,111],"significant":[36],"inefficiency.":[37],"Clients":[38],"with":[39],"noisy":[40],"or":[41,53,212],"highly":[42],"heterogeneous":[43],"contribute":[45],"expensive":[46],"gradient":[47],"computations":[48],"that":[49,84],"are":[50,215],"either":[51],"discarded":[52],"heavily":[54],"down-weighted":[55],"before":[56,101],"aggregation.":[57],"These":[58],"reactive":[59],"approaches":[60],"waste":[61],"computational":[62],"resources,":[63],"require":[64],"more":[65,195],"communication":[66],"rounds":[67],"result":[69],"in":[70,123],"unnecessary":[71],"privacy":[72,180],"exposure.":[73],"In":[74],"this":[75],"paper,":[76],"we":[77,172],"propose":[78],"a":[79,129],"proactive":[80],"client":[81],"selection":[82,158],"framework":[83],"aims":[85],"to":[86,116,153,204],"find":[87],"an":[88,162],"optimal":[89,163],"federation":[90],"clients":[92],"whose":[93],"combined":[94],"match":[96],"utility":[97,147],"fairness":[99],"requirements":[100],"begins.":[103],"Our":[104],"method":[105],"relies":[106],"on":[107,188,199],"mutual":[108],"information":[109],"computed":[110],"differentially":[112],"private":[113],"contingency":[114],"tables":[115],"quantify":[117],"relevance":[119],"cross-feature":[121],"correlations":[122,152],"union":[125],"dataset.":[126],"We":[127],"introduce":[128],"Potential":[130],"Federation":[131],"Loss":[132],"(PFL)":[133],"over":[134,167],"set":[136],"fixed-size":[138],"federations,":[139,202],"balances":[141],"two":[142],"objectives.":[143],"Maximizing":[144],"collective":[145],"while":[148],"ensuring":[149],"fair":[150],"cross-features":[151],"prevent":[154],"group":[155],"unfairness.":[156],"Client":[157],"expressed":[160],"as":[161],"subset":[164],"search":[165],"problem":[166],"PFL":[169],"objective,":[170],"solve":[173],"using":[174],"simulated":[175],"annealing":[176],"under":[177],"strong":[178],"differential":[179],"guarantees":[181],"for":[182],"clients'":[183],"local":[184],"statistics.":[185],"Experimental":[186],"results":[187],"four":[189],"benchmarks":[190],"show":[191],"faster,":[192],"fairer,":[193],"accurate":[196],"models":[197],"trained":[198],"optimally":[200],"found":[201],"compared":[203],"uniform":[205],"sampling,":[206],"even":[207],"when":[208],"state-of-the-art":[209],"adaptive":[210],"aggregation":[211],"sampling":[213],"strategies":[214],"employed.":[216]},"counts_by_year":[],"updated_date":"2026-07-28T07:46:37.118299","created_date":"2026-05-22T00:00:00"}