{"id":"https://openalex.org/W7156590561","doi":"https://doi.org/10.48550/arxiv.2604.23426","title":"Enhanced Privacy and Communication Efficiency in Non-IID Federated Learning with Adaptive Quantization and Differential Privacy","display_name":"Enhanced Privacy and Communication Efficiency in Non-IID Federated Learning with Adaptive Quantization and Differential Privacy","publication_year":2026,"publication_date":"2026-04-25","ids":{"openalex":"https://openalex.org/W7156590561","doi":"https://doi.org/10.48550/arxiv.2604.23426"},"language":null,"primary_location":{"id":"doi:10.48550/arxiv.2604.23426","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2604.23426","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"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.2604.23426","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5008235516","display_name":"Emre Ard\u0131\u00e7","orcid":"https://orcid.org/0000-0002-4324-8052"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Ard\u0131\u00e7, Emre","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5010447124","display_name":"Yakup Gen\u00e7","orcid":"https://orcid.org/0000-0002-6952-6735"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Gen\u00e7, Yakup","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":0.906499981880188,"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":0.906499981880188,"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/T10273","display_name":"IoT and Edge/Fog Computing","score":0.01640000008046627,"subfield":{"id":"https://openalex.org/subfields/1705","display_name":"Computer Networks and Communications"},"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/T13553","display_name":"Age of Information Optimization","score":0.01209999993443489,"subfield":{"id":"https://openalex.org/subfields/1705","display_name":"Computer Networks and Communications"},"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":0.7634000182151794},{"id":"https://openalex.org/keywords/differential-privacy","display_name":"Differential privacy","score":0.7246000170707703},{"id":"https://openalex.org/keywords/bottleneck","display_name":"Bottleneck","score":0.6621000170707703},{"id":"https://openalex.org/keywords/quantization","display_name":"Quantization (signal processing)","score":0.5751000046730042},{"id":"https://openalex.org/keywords/data-sharing","display_name":"Data sharing","score":0.47609999775886536},{"id":"https://openalex.org/keywords/information-privacy","display_name":"Information privacy","score":0.43849998712539673},{"id":"https://openalex.org/keywords/robustness","display_name":"Robustness (evolution)","score":0.43140000104904175},{"id":"https://openalex.org/keywords/server","display_name":"Server","score":0.4068000018596649}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8287000060081482},{"id":"https://openalex.org/C2992525071","wikidata":"https://www.wikidata.org/wiki/Q50818671","display_name":"Federated learning","level":2,"score":0.7634000182151794},{"id":"https://openalex.org/C23130292","wikidata":"https://www.wikidata.org/wiki/Q5275358","display_name":"Differential privacy","level":2,"score":0.7246000170707703},{"id":"https://openalex.org/C2780513914","wikidata":"https://www.wikidata.org/wiki/Q18210350","display_name":"Bottleneck","level":2,"score":0.6621000170707703},{"id":"https://openalex.org/C28855332","wikidata":"https://www.wikidata.org/wiki/Q198099","display_name":"Quantization (signal processing)","level":2,"score":0.5751000046730042},{"id":"https://openalex.org/C2779965156","wikidata":"https://www.wikidata.org/wiki/Q5227350","display_name":"Data sharing","level":3,"score":0.47609999775886536},{"id":"https://openalex.org/C123201435","wikidata":"https://www.wikidata.org/wiki/Q456632","display_name":"Information privacy","level":2,"score":0.43849998712539673},{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.43140000104904175},{"id":"https://openalex.org/C93996380","wikidata":"https://www.wikidata.org/wiki/Q44127","display_name":"Server","level":2,"score":0.4068000018596649},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.4068000018596649},{"id":"https://openalex.org/C2779582901","wikidata":"https://www.wikidata.org/wiki/Q21013010","display_name":"Distributed learning","level":2,"score":0.39079999923706055},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.37790000438690186},{"id":"https://openalex.org/C106301342","wikidata":"https://www.wikidata.org/wiki/Q4117933","display_name":"Entropy (arrow of time)","level":2,"score":0.3610000014305115},{"id":"https://openalex.org/C137822555","wikidata":"https://www.wikidata.org/wiki/Q2587068","display_name":"Information sensitivity","level":2,"score":0.3409999907016754},{"id":"https://openalex.org/C60008888","wikidata":"https://www.wikidata.org/wiki/Q6031013","display_name":"Information bottleneck method","level":3,"score":0.3305000066757202},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.303600013256073},{"id":"https://openalex.org/C2221639","wikidata":"https://www.wikidata.org/wiki/Q2877","display_name":"Discrete cosine transform","level":3,"score":0.29510000348091125},{"id":"https://openalex.org/C120314980","wikidata":"https://www.wikidata.org/wiki/Q180634","display_name":"Distributed computing","level":1,"score":0.28519999980926514},{"id":"https://openalex.org/C70061542","wikidata":"https://www.wikidata.org/wiki/Q989016","display_name":"Distributed database","level":2,"score":0.2842999994754791},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.2833000123500824},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.28060001134872437},{"id":"https://openalex.org/C101765175","wikidata":"https://www.wikidata.org/wiki/Q577764","display_name":"Communications system","level":2,"score":0.27959999442100525},{"id":"https://openalex.org/C199833920","wikidata":"https://www.wikidata.org/wiki/Q612536","display_name":"Vector quantization","level":2,"score":0.2741999924182892},{"id":"https://openalex.org/C509729295","wikidata":"https://www.wikidata.org/wiki/Q7246032","display_name":"Privacy software","level":3,"score":0.27410000562667847},{"id":"https://openalex.org/C67186912","wikidata":"https://www.wikidata.org/wiki/Q367664","display_name":"Data modeling","level":2,"score":0.25619998574256897}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.48550/arxiv.2604.23426","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2604.23426","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"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.2604.23426","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2604.23426","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"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":[1,7],"(FL)":[2],"is":[3,34,50,63,103],"a":[4,14,20,64,118,131],"distributed":[5],"machine":[6],"method":[8],"where":[9],"multiple":[10],"devices":[11],"collaboratively":[12],"train":[13],"model":[15,73,210],"under":[16],"the":[17,29,35,54,72],"management":[18],"of":[19,28,32,56,67],"central":[21],"server":[22],"without":[23],"sharing":[24],"underlying":[25],"data.":[26],"One":[27],"key":[30],"challenges":[31],"FL":[33,107],"communication":[36,84],"bottleneck":[37],"caused":[38],"by":[39,185],"variations":[40],"in":[41,106],"connection":[42],"speed":[43],"and":[44,83,91,108,120,156,170,194,212],"bandwidth":[45],"across":[46,164],"devices.":[47],"Therefore,":[48],"it":[49],"essential":[51],"to":[52,99,187,196,203],"reduce":[53,181],"size":[55],"transmitted":[57],"data":[58,162,184],"during":[59,77],"training.":[60,78],"Additionally,":[61],"there":[62],"potential":[65],"risk":[66],"exposing":[68],"sensitive":[69],"information":[70],"through":[71,142,150,216],"or":[74],"gradient":[75],"analysis":[76],"To":[79],"address":[80],"both":[81],"privacy":[82,89,111,171,215],"efficiency,":[85],"we":[86],"combine":[87],"differential":[88,217],"(DP)":[90],"adaptive":[92,178],"quantization":[93,179],"methods.":[94],"We":[95,116,146],"use":[96],"Laplacian-based":[97],"DP":[98],"preserve":[100],"privacy,":[101],"which":[102],"relatively":[104],"underexplored":[105],"offers":[109],"tighter":[110],"guarantees":[112],"than":[113],"Gaussian-based":[114],"DP.":[115],"propose":[117],"simple":[119],"efficient":[121],"global":[122],"bit-length":[123,168],"scheduler":[124,133],"using":[125,160],"round-based":[126],"cosine":[127],"annealing,":[128],"along":[129],"with":[130],"client-based":[132],"that":[134,176],"dynamically":[135],"adapts":[136],"based":[137],"on":[138,153],"client":[139,166],"contribution":[140],"estimated":[141],"dataset":[143],"entropy":[144],"analysis.":[145],"evaluate":[147],"our":[148,177],"approach":[149],"extensive":[151],"experiments":[152],"CIFAR10,":[154,193],"MNIST,":[155,190],"medical":[157,199],"imaging":[158,200],"datasets,":[159],"non-IID":[161],"distributions":[163],"varying":[165],"counts,":[167],"schedulers,":[169],"budgets.":[172],"The":[173],"results":[174],"show":[175],"methods":[180],"total":[182],"communicated":[183],"up":[186],"52.64%":[188],"for":[189,192,198],"45.06%":[191],"31%":[195],"37%":[197],"datasets":[201],"compared":[202],"32-bit":[204],"float":[205],"training":[206],"while":[207],"maintaining":[208],"competitive":[209],"accuracy":[211],"ensuring":[213],"robust":[214],"privacy.":[218]},"counts_by_year":[],"updated_date":"2026-07-01T06:00:48.157686","created_date":"2026-04-29T00:00:00"}