{"id":"https://openalex.org/W4376480684","doi":"https://doi.org/10.1109/wcnc55385.2023.10118781","title":"Deep Reinforcement Learning-based Quantization for Federated Learning","display_name":"Deep Reinforcement Learning-based Quantization for Federated Learning","publication_year":2023,"publication_date":"2023-03-01","ids":{"openalex":"https://openalex.org/W4376480684","doi":"https://doi.org/10.1109/wcnc55385.2023.10118781"},"language":"en","primary_location":{"id":"doi:10.1109/wcnc55385.2023.10118781","is_oa":false,"landing_page_url":"https://doi.org/10.1109/wcnc55385.2023.10118781","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2023 IEEE Wireless Communications and Networking Conference (WCNC)","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/A5023200236","display_name":"Sihui Zheng","orcid":"https://orcid.org/0000-0003-1437-9659"},"institutions":[{"id":"https://openalex.org/I3131625388","display_name":"University Town of Shenzhen","ror":"https://ror.org/05f5j6225","country_code":"CN","type":"education","lineage":["https://openalex.org/I3131625388"]},{"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":true,"raw_author_name":"Sihui Zheng","raw_affiliation_strings":["Tsinghua University,Shenzhen International Graduate School,Shenzhen,China","Shenzhen International Graduate School, Tsinghua University, Shenzhen, China","Department of Electronic Engineering, Tsinghua University, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Tsinghua University,Shenzhen International Graduate School,Shenzhen,China","institution_ids":["https://openalex.org/I99065089"]},{"raw_affiliation_string":"Shenzhen International Graduate School, Tsinghua University, Shenzhen, China","institution_ids":["https://openalex.org/I3131625388","https://openalex.org/I99065089"]},{"raw_affiliation_string":"Department of Electronic Engineering, Tsinghua University, Beijing, China","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5108047157","display_name":"Yuhan Dong","orcid":"https://orcid.org/0000-0001-5275-1787"},"institutions":[{"id":"https://openalex.org/I3131625388","display_name":"University Town of Shenzhen","ror":"https://ror.org/05f5j6225","country_code":"CN","type":"education","lineage":["https://openalex.org/I3131625388"]},{"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":"Yuhan Dong","raw_affiliation_strings":["Tsinghua University,Shenzhen International Graduate School,Shenzhen,China","Shenzhen International Graduate School, Tsinghua University, Shenzhen, China","Department of Electronic Engineering, Tsinghua University, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Tsinghua University,Shenzhen International Graduate School,Shenzhen,China","institution_ids":["https://openalex.org/I99065089"]},{"raw_affiliation_string":"Shenzhen International Graduate School, Tsinghua University, Shenzhen, China","institution_ids":["https://openalex.org/I3131625388","https://openalex.org/I99065089"]},{"raw_affiliation_string":"Department of Electronic Engineering, Tsinghua University, Beijing, China","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100441900","display_name":"Xiang Chen","orcid":"https://orcid.org/0000-0001-8254-8907"},"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"]},{"id":"https://openalex.org/I3131625388","display_name":"University Town of Shenzhen","ror":"https://ror.org/05f5j6225","country_code":"CN","type":"education","lineage":["https://openalex.org/I3131625388"]},{"id":"https://openalex.org/I4210114105","display_name":"Tsinghua\u2013Berkeley Shenzhen Institute","ror":"https://ror.org/02hhwwz98","country_code":"CN","type":"facility","lineage":["https://openalex.org/I4210114105","https://openalex.org/I95457486","https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xiang Chen","raw_affiliation_strings":["Research Institute of Tsinghua University in Shenzhen (RITS),Shenzhen,China","Guangxi Key Laboratory of Wireless Wideband Communication and Signal Processing, Guilin, China","Research Institute of Tsinghua University in Shenzhen (RITS), Shenzhen, China"],"affiliations":[{"raw_affiliation_string":"Research Institute of Tsinghua University in Shenzhen (RITS),Shenzhen,China","institution_ids":["https://openalex.org/I3131625388","https://openalex.org/I4210114105"]},{"raw_affiliation_string":"Guangxi Key Laboratory of Wireless Wideband Communication and Signal Processing, Guilin, China","institution_ids":[]},{"raw_affiliation_string":"Research Institute of Tsinghua University in Shenzhen (RITS), Shenzhen, China","institution_ids":["https://openalex.org/I3131625388","https://openalex.org/I99065089"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5023200236"],"corresponding_institution_ids":["https://openalex.org/I3131625388","https://openalex.org/I99065089"],"apc_list":null,"apc_paid":null,"fwci":0.8757,"has_fulltext":false,"cited_by_count":5,"citation_normalized_percentile":{"value":0.77961734,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":94,"max":97},"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"6"},"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/T10964","display_name":"Wireless Communication Security Techniques","score":0.9890999794006348,"subfield":{"id":"https://openalex.org/subfields/2208","display_name":"Electrical and Electronic Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T11612","display_name":"Stochastic Gradient Optimization Techniques","score":0.9815000295639038,"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/reinforcement-learning","display_name":"Reinforcement learning","score":0.8922607898712158},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7883924841880798},{"id":"https://openalex.org/keywords/markov-decision-process","display_name":"Markov decision process","score":0.7385962009429932},{"id":"https://openalex.org/keywords/quantization","display_name":"Quantization (signal processing)","score":0.7160122990608215},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5953887104988098},{"id":"https://openalex.org/keywords/overhead","display_name":"Overhead (engineering)","score":0.4628888964653015},{"id":"https://openalex.org/keywords/federated-learning","display_name":"Federated learning","score":0.4615402817726135},{"id":"https://openalex.org/keywords/distributed-learning","display_name":"Distributed learning","score":0.4611506760120392},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.4519120156764984},{"id":"https://openalex.org/keywords/partially-observable-markov-decision-process","display_name":"Partially observable Markov decision process","score":0.42085549235343933},{"id":"https://openalex.org/keywords/premise","display_name":"Premise","score":0.41602861881256104},{"id":"https://openalex.org/keywords/distributed-computing","display_name":"Distributed computing","score":0.36509740352630615},{"id":"https://openalex.org/keywords/markov-process","display_name":"Markov process","score":0.3207465410232544},{"id":"https://openalex.org/keywords/markov-chain","display_name":"Markov chain","score":0.2103566825389862},{"id":"https://openalex.org/keywords/markov-model","display_name":"Markov model","score":0.2096521258354187},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.1454232633113861},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.074899822473526}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.8922607898712158},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7883924841880798},{"id":"https://openalex.org/C106189395","wikidata":"https://www.wikidata.org/wiki/Q176789","display_name":"Markov decision process","level":3,"score":0.7385962009429932},{"id":"https://openalex.org/C28855332","wikidata":"https://www.wikidata.org/wiki/Q198099","display_name":"Quantization (signal processing)","level":2,"score":0.7160122990608215},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5953887104988098},{"id":"https://openalex.org/C2779960059","wikidata":"https://www.wikidata.org/wiki/Q7113681","display_name":"Overhead (engineering)","level":2,"score":0.4628888964653015},{"id":"https://openalex.org/C2992525071","wikidata":"https://www.wikidata.org/wiki/Q50818671","display_name":"Federated learning","level":2,"score":0.4615402817726135},{"id":"https://openalex.org/C2779582901","wikidata":"https://www.wikidata.org/wiki/Q21013010","display_name":"Distributed learning","level":2,"score":0.4611506760120392},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.4519120156764984},{"id":"https://openalex.org/C17098449","wikidata":"https://www.wikidata.org/wiki/Q176814","display_name":"Partially observable Markov decision process","level":4,"score":0.42085549235343933},{"id":"https://openalex.org/C2778023277","wikidata":"https://www.wikidata.org/wiki/Q321703","display_name":"Premise","level":2,"score":0.41602861881256104},{"id":"https://openalex.org/C120314980","wikidata":"https://www.wikidata.org/wiki/Q180634","display_name":"Distributed computing","level":1,"score":0.36509740352630615},{"id":"https://openalex.org/C159886148","wikidata":"https://www.wikidata.org/wiki/Q176645","display_name":"Markov process","level":2,"score":0.3207465410232544},{"id":"https://openalex.org/C98763669","wikidata":"https://www.wikidata.org/wiki/Q176645","display_name":"Markov chain","level":2,"score":0.2103566825389862},{"id":"https://openalex.org/C163836022","wikidata":"https://www.wikidata.org/wiki/Q6771326","display_name":"Markov model","level":3,"score":0.2096521258354187},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.1454232633113861},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.074899822473526},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","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/C19417346","wikidata":"https://www.wikidata.org/wiki/Q7922","display_name":"Pedagogy","level":1,"score":0.0},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.0},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/wcnc55385.2023.10118781","is_oa":false,"landing_page_url":"https://doi.org/10.1109/wcnc55385.2023.10118781","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2023 IEEE Wireless Communications and Networking Conference (WCNC)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/16","display_name":"Peace, Justice and strong institutions","score":0.7200000286102295}],"awards":[],"funders":[{"id":"https://openalex.org/F4320321408","display_name":"Ministry of Education","ror":"https://ror.org/01p262204"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":18,"referenced_works":["https://openalex.org/W2600687292","https://openalex.org/W2736601468","https://openalex.org/W2902986194","https://openalex.org/W2995022099","https://openalex.org/W3047304572","https://openalex.org/W3108383389","https://openalex.org/W3162286130","https://openalex.org/W3180608480","https://openalex.org/W3198422819","https://openalex.org/W4287755088","https://openalex.org/W6696004547","https://openalex.org/W6728757088","https://openalex.org/W6741002519","https://openalex.org/W6746200960","https://openalex.org/W6752012617","https://openalex.org/W6759226220","https://openalex.org/W6768511045","https://openalex.org/W6779409229"],"related_works":["https://openalex.org/W2096013579","https://openalex.org/W52153049","https://openalex.org/W1760611253","https://openalex.org/W1515117609","https://openalex.org/W1589140671","https://openalex.org/W4323315247","https://openalex.org/W2294884454","https://openalex.org/W3169161914","https://openalex.org/W4321379664","https://openalex.org/W2211790881"],"abstract_inverted_index":{"Federated":[0],"learning":[1,13,70,162],"(FL)":[2],"is":[3,92,112],"a":[4,60,67,85,104,160],"promising":[5],"solution":[6],"to":[7,30,74,94,114,159],"harness":[8],"the":[9,15,21,42,46,54,76,79,89,96,117,134,145,156],"advances":[10],"of":[11,17,24,45,56,78,122],"machine":[12],"under":[14],"premise":[16],"privacy":[18],"security,":[19],"whereas":[20],"communication":[22],"overhead":[23],"model":[25,48],"exchange":[26],"remains":[27],"an":[28],"obstacle":[29],"deploying":[31],"FL":[32,109],"in":[33,49],"wireless":[34],"networks.":[35],"To":[36],"tackle":[37],"this":[38,50],"challenge,":[39],"we":[40,65],"consider":[41],"non-uniform":[43],"quantization":[44,57,97],"global":[47],"work.":[51],"By":[52],"formulating":[53],"optimization":[55],"intervals":[58],"as":[59],"Markov":[61],"decision":[62],"process":[63],"(MDP),":[64],"propose":[66],"deep":[68],"reinforcement":[69],"(DRL)-":[71],"based":[72],"approach":[73],"improve":[75],"performance":[77],"quantizer":[80],"for":[81],"FL.":[82],"Through":[83],"crafting":[84],"compound":[86],"reward":[87],"function,":[88],"DRL":[90,111,123],"agent":[91],"guided":[93],"reduce":[95],"error":[98],"and":[99,110,119,141,149],"training":[100],"loss":[101],"simultaneously.":[102],"Furthermore,":[103],"dual":[105],"time-scale":[106],"mechanism":[107],"between":[108],"adopted":[113],"ensure":[115],"that":[116,133],"actor":[118],"critic":[120],"models":[121],"converge":[124],"more":[125],"steadily.":[126],"Simulations":[127],"on":[128],"various":[129],"real-world":[130],"datasets":[131],"reveal":[132],"proposed":[135],"method":[136],"can":[137,150],"provide":[138],"higher":[139],"accuracy":[140],"faster":[142],"convergence":[143],"than":[144],"existing":[146],"uniform":[147],"quantizers,":[148],"retain":[151],"these":[152],"benefits":[153],"when":[154],"applying":[155],"learned":[157],"policy":[158],"similar":[161],"task.":[163]},"counts_by_year":[{"year":2025,"cited_by_count":3},{"year":2024,"cited_by_count":2}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}