{"id":"https://openalex.org/W4319303175","doi":"https://doi.org/10.1109/jsac.2023.3242734","title":"FedKL: Tackling Data Heterogeneity in Federated Reinforcement Learning by Penalizing KL Divergence","display_name":"FedKL: Tackling Data Heterogeneity in Federated Reinforcement Learning by Penalizing KL Divergence","publication_year":2023,"publication_date":"2023-02-06","ids":{"openalex":"https://openalex.org/W4319303175","doi":"https://doi.org/10.1109/jsac.2023.3242734"},"language":"en","primary_location":{"id":"doi:10.1109/jsac.2023.3242734","is_oa":false,"landing_page_url":"https://doi.org/10.1109/jsac.2023.3242734","pdf_url":null,"source":{"id":"https://openalex.org/S90422530","display_name":"IEEE Journal on Selected Areas in Communications","issn_l":"0733-8716","issn":["0733-8716","1558-0008"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Journal on Selected Areas in Communications","raw_type":"journal-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/A5049082301","display_name":"Zhijie Xie","orcid":"https://orcid.org/0000-0002-2003-0472"},"institutions":[{"id":"https://openalex.org/I200769079","display_name":"Hong Kong University of Science and Technology","ror":"https://ror.org/00q4vv597","country_code":"HK","type":"education","lineage":["https://openalex.org/I200769079"]}],"countries":["HK"],"is_corresponding":true,"raw_author_name":"Zhijie Xie","raw_affiliation_strings":["Department of Electronic and Computer Engineering, The Hong Kong University of Science and Technology, Sai kung, Hong Kong"],"affiliations":[{"raw_affiliation_string":"Department of Electronic and Computer Engineering, The Hong Kong University of Science and Technology, Sai kung, Hong Kong","institution_ids":["https://openalex.org/I200769079"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5025467937","display_name":"Shenghui Song","orcid":"https://orcid.org/0000-0001-6316-8415"},"institutions":[{"id":"https://openalex.org/I200769079","display_name":"Hong Kong University of Science and Technology","ror":"https://ror.org/00q4vv597","country_code":"HK","type":"education","lineage":["https://openalex.org/I200769079"]}],"countries":["HK"],"is_corresponding":false,"raw_author_name":"Shenghui Song","raw_affiliation_strings":["Department of Electronic and Computer Engineering, The Hong Kong University of Science and Technology, Sai kung, Hong Kong"],"affiliations":[{"raw_affiliation_string":"Department of Electronic and Computer Engineering, The Hong Kong University of Science and Technology, Sai kung, Hong Kong","institution_ids":["https://openalex.org/I200769079"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5049082301"],"corresponding_institution_ids":["https://openalex.org/I200769079"],"apc_list":null,"apc_paid":null,"fwci":8.8634,"has_fulltext":false,"cited_by_count":51,"citation_normalized_percentile":{"value":0.98364952,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":99,"max":100},"biblio":{"volume":"41","issue":"4","first_page":"1227","last_page":"1242"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10764","display_name":"Privacy-Preserving Technologies in Data","score":0.9998999834060669,"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":0.9998999834060669,"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":0.9948999881744385,"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/T13553","display_name":"Age of Information Optimization","score":0.9904000163078308,"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/reinforcement-learning","display_name":"Reinforcement learning","score":0.8134170770645142},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7900769710540771},{"id":"https://openalex.org/keywords/divergence","display_name":"Divergence (linguistics)","score":0.707754373550415},{"id":"https://openalex.org/keywords/bottleneck","display_name":"Bottleneck","score":0.685196042060852},{"id":"https://openalex.org/keywords/convergence","display_name":"Convergence (economics)","score":0.6651933193206787},{"id":"https://openalex.org/keywords/kullback\u2013leibler-divergence","display_name":"Kullback\u2013Leibler divergence","score":0.48266011476516724},{"id":"https://openalex.org/keywords/mathematical-optimization","display_name":"Mathematical optimization","score":0.3869172930717468},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3189981281757355},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.13639792799949646}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.8134170770645142},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7900769710540771},{"id":"https://openalex.org/C207390915","wikidata":"https://www.wikidata.org/wiki/Q1230525","display_name":"Divergence (linguistics)","level":2,"score":0.707754373550415},{"id":"https://openalex.org/C2780513914","wikidata":"https://www.wikidata.org/wiki/Q18210350","display_name":"Bottleneck","level":2,"score":0.685196042060852},{"id":"https://openalex.org/C2777303404","wikidata":"https://www.wikidata.org/wiki/Q759757","display_name":"Convergence (economics)","level":2,"score":0.6651933193206787},{"id":"https://openalex.org/C171752962","wikidata":"https://www.wikidata.org/wiki/Q255166","display_name":"Kullback\u2013Leibler divergence","level":2,"score":0.48266011476516724},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.3869172930717468},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3189981281757355},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.13639792799949646},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C149635348","wikidata":"https://www.wikidata.org/wiki/Q193040","display_name":"Embedded system","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},{"id":"https://openalex.org/C50522688","wikidata":"https://www.wikidata.org/wiki/Q189833","display_name":"Economic growth","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/jsac.2023.3242734","is_oa":false,"landing_page_url":"https://doi.org/10.1109/jsac.2023.3242734","pdf_url":null,"source":{"id":"https://openalex.org/S90422530","display_name":"IEEE Journal on Selected Areas in Communications","issn_l":"0733-8716","issn":["0733-8716","1558-0008"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Journal on Selected Areas in Communications","raw_type":"journal-article"},{"id":"pmh:oai:repository.hkust.edu.hk:1783.1-124508","is_oa":false,"landing_page_url":"https://repository.hkust.edu.hk/ir/Record/1783.1-124508","pdf_url":null,"source":{"id":"https://openalex.org/S4306401796","display_name":"Rare & Special e-Zone (The Hong Kong University of Science and Technology)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I200769079","host_organization_name":"Hong Kong University of Science and Technology","host_organization_lineage":["https://openalex.org/I200769079"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/16","score":0.5699999928474426,"display_name":"Peace, Justice and strong institutions"}],"awards":[{"id":"https://openalex.org/G8197906940","display_name":null,"funder_award_id":"N_HKUST656/22","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"},{"id":"https://openalex.org/F4320321592","display_name":"Research Grants Council, University Grants Committee","ror":"https://ror.org/00djwmt25"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":59,"referenced_works":["https://openalex.org/W1771410628","https://openalex.org/W2149414429","https://openalex.org/W2158782408","https://openalex.org/W2535838896","https://openalex.org/W2736601468","https://openalex.org/W2807006176","https://openalex.org/W2900182564","https://openalex.org/W2904435756","https://openalex.org/W2912213068","https://openalex.org/W3004397388","https://openalex.org/W3009175007","https://openalex.org/W3021654819","https://openalex.org/W3027501728","https://openalex.org/W3045638580","https://openalex.org/W3047304572","https://openalex.org/W3165469371","https://openalex.org/W3193144148","https://openalex.org/W3196371845","https://openalex.org/W3200561352","https://openalex.org/W3205564238","https://openalex.org/W3205598877","https://openalex.org/W4214717370","https://openalex.org/W4285723212","https://openalex.org/W4287332481","https://openalex.org/W4297687186","https://openalex.org/W4297779625","https://openalex.org/W4302366875","https://openalex.org/W4377562264","https://openalex.org/W4380078504","https://openalex.org/W4391473131","https://openalex.org/W6627932998","https://openalex.org/W6633472939","https://openalex.org/W6634413486","https://openalex.org/W6638018090","https://openalex.org/W6676971703","https://openalex.org/W6679257226","https://openalex.org/W6683195989","https://openalex.org/W6683204974","https://openalex.org/W6684205842","https://openalex.org/W6728757088","https://openalex.org/W6737893269","https://openalex.org/W6738796088","https://openalex.org/W6741002519","https://openalex.org/W6746200960","https://openalex.org/W6748310522","https://openalex.org/W6752029299","https://openalex.org/W6755921573","https://openalex.org/W6757082500","https://openalex.org/W6758713102","https://openalex.org/W6759238902","https://openalex.org/W6765541894","https://openalex.org/W6766831760","https://openalex.org/W6769116889","https://openalex.org/W6780559895","https://openalex.org/W6790230083","https://openalex.org/W6802002411","https://openalex.org/W6802464851","https://openalex.org/W6802550813","https://openalex.org/W6810897048"],"related_works":["https://openalex.org/W1517908938","https://openalex.org/W2105321464","https://openalex.org/W2165272709","https://openalex.org/W2887774187","https://openalex.org/W1981749300","https://openalex.org/W2375053028","https://openalex.org/W2388220555","https://openalex.org/W3048739257","https://openalex.org/W1665563134","https://openalex.org/W2963604926"],"abstract_inverted_index":{"One":[0],"of":[1,26,59,157,169,185,220],"the":[2,19,24,36,55,67,70,83,87,94,100,109,116,127,132,146,150,154,158,167,170,174,186,193,218,221,231],"fundamental":[3],"issues":[4],"for":[5,39,62,108],"Federated":[6,40],"Learning":[7,42,213],"(FL)":[8],"is":[9,44,90,119,123,141,161],"data":[10,27,60],"heterogeneity,":[11],"which":[12,122],"causes":[13],"accuracy":[14],"degradation,":[15],"slow":[16],"convergence,":[17],"and":[18,57,72,102,153,181,205,229],"communication":[20],"bottleneck":[21],"issue.":[22],"Although":[23],"impact":[25],"heterogeneity":[28,61,128],"on":[29,131,209],"supervised":[30],"FL":[31],"has":[32],"been":[33],"widely":[34],"studied,":[35],"related":[37,125],"investigation":[38],"Reinforcement":[41,212],"(FRL)":[43],"still":[45],"in":[46,149,227],"its":[47],"infancy.":[48],"In":[49],"this":[50],"paper,":[51],"we":[52,76],"first":[53],"define":[54],"type":[56],"level":[58],"FRL":[63],"systems.":[64],"By":[65,164],"inspecting":[66],"connection":[68],"between":[69,99,200],"global":[71,84,103,110,175,179],"local":[73,79,88,101,117,171,187,191],"objective":[74],"functions,":[75],"prove":[77],"that":[78],"training":[80,188,201,232],"can":[81],"benefit":[82],"objective,":[85],"if":[86],"update":[89],"properly":[91],"penalized":[92],"by":[93],"total":[95],"variation":[96],"(TV)":[97],"distance":[98],"policies.":[104],"A":[105],"necessary":[106],"condition":[107],"policy":[111,172,176],"to":[112,126,143],"be":[113],"learn-able":[114],"from":[115,173],"environments":[118],"also":[120,162],"derived,":[121],"directly":[124,144],"level.":[129],"Based":[130],"theoretical":[133],"result,":[134],"a":[135,178,190,197],"Kullback-Leibler":[136],"(KL)":[137],"divergence":[138,168],"based":[139],"penalty":[140,180],"proposed":[142,159,194,222],"constrain":[145],"model":[147],"outputs":[148],"distribution":[151],"space":[152],"convergence":[155],"proof":[156],"algorithm":[160,223],"provided.":[163],"jointly":[165],"penalizing":[166,182],"with":[177,189,234],"each":[183],"iteration":[184],"penalty,":[192],"method":[195],"achieves":[196],"better":[198],"trade-off":[199],"speed":[202],"(step":[203],"size)":[204],"convergence.":[206],"Experiment":[207],"results":[208],"two":[210],"popular":[211],"(RL)":[214],"experiment":[215],"platforms":[216],"demonstrate":[217],"advantage":[219],"over":[224],"existing":[225],"methods":[226],"accelerating":[228],"stabilizing":[230],"process":[233],"heterogeneous":[235],"data.":[236]},"counts_by_year":[{"year":2026,"cited_by_count":4},{"year":2025,"cited_by_count":18},{"year":2024,"cited_by_count":17},{"year":2023,"cited_by_count":12}],"updated_date":"2026-04-03T22:45:19.894376","created_date":"2023-02-07T00:00:00"}