{"id":"https://openalex.org/W4381164013","doi":"https://doi.org/10.1145/3604939","title":"Server-Client Collaborative Distillation for Federated Reinforcement Learning","display_name":"Server-Client Collaborative Distillation for Federated Reinforcement Learning","publication_year":2023,"publication_date":"2023-06-19","ids":{"openalex":"https://openalex.org/W4381164013","doi":"https://doi.org/10.1145/3604939"},"language":"en","primary_location":{"id":"doi:10.1145/3604939","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3604939","pdf_url":null,"source":{"id":"https://openalex.org/S41523882","display_name":"ACM Transactions on Knowledge Discovery from Data","issn_l":"1556-4681","issn":["1556-4681","1556-472X"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319798","host_organization_name":"Association for Computing Machinery","host_organization_lineage":["https://openalex.org/P4310319798"],"host_organization_lineage_names":["Association for Computing Machinery"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ACM Transactions on Knowledge Discovery from Data","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/A5003053702","display_name":"Weiming Mai","orcid":"https://orcid.org/0000-0003-1368-6630"},"institutions":[{"id":"https://openalex.org/I141568987","display_name":"Hong Kong Baptist University","ror":"https://ror.org/0145fw131","country_code":"HK","type":"education","lineage":["https://openalex.org/I141568987"]}],"countries":["HK"],"is_corresponding":false,"raw_author_name":"Weiming Mai","raw_affiliation_strings":["Department of CS, Hong Kong Baptist University, Hong Kong SAR, China"],"raw_orcid":"https://orcid.org/0000-0003-1368-6630","affiliations":[{"raw_affiliation_string":"Department of CS, Hong Kong Baptist University, Hong Kong SAR, China","institution_ids":["https://openalex.org/I141568987"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102922412","display_name":"Jiangchao Yao","orcid":"https://orcid.org/0000-0001-6115-5194"},"institutions":[{"id":"https://openalex.org/I183067930","display_name":"Shanghai Jiao Tong University","ror":"https://ror.org/0220qvk04","country_code":"CN","type":"education","lineage":["https://openalex.org/I183067930"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jiangchao Yao","raw_affiliation_strings":["CMIC, Shanghai Jiao Tong University & Shanghai AI Laboratory, China"],"raw_orcid":"https://orcid.org/0000-0001-6115-5194","affiliations":[{"raw_affiliation_string":"CMIC, Shanghai Jiao Tong University & Shanghai AI Laboratory, China","institution_ids":["https://openalex.org/I183067930"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5030222911","display_name":"Chen Gong","orcid":"https://orcid.org/0000-0002-4092-9856"},"institutions":[{"id":"https://openalex.org/I36399199","display_name":"Nanjing University of Science and Technology","ror":"https://ror.org/00xp9wg62","country_code":"CN","type":"education","lineage":["https://openalex.org/I36399199"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Gong Chen","raw_affiliation_strings":["School of CSE, Nanjing University of Science and Technology, China"],"raw_orcid":"https://orcid.org/0000-0002-4092-9856","affiliations":[{"raw_affiliation_string":"School of CSE, Nanjing University of Science and Technology, China","institution_ids":["https://openalex.org/I36399199"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100342828","display_name":"Ya Zhang","orcid":"https://orcid.org/0000-0002-5390-9053"},"institutions":[{"id":"https://openalex.org/I183067930","display_name":"Shanghai Jiao Tong University","ror":"https://ror.org/0220qvk04","country_code":"CN","type":"education","lineage":["https://openalex.org/I183067930"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Ya Zhang","raw_affiliation_strings":["CMIC, Shanghai Jiao Tong University & Shanghai AI Laboratory, China"],"raw_orcid":"https://orcid.org/0000-0002-5390-9053","affiliations":[{"raw_affiliation_string":"CMIC, Shanghai Jiao Tong University & Shanghai AI Laboratory, China","institution_ids":["https://openalex.org/I183067930"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5038516431","display_name":"Yiu\u2010ming Cheung","orcid":"https://orcid.org/0000-0001-7629-4648"},"institutions":[{"id":"https://openalex.org/I141568987","display_name":"Hong Kong Baptist University","ror":"https://ror.org/0145fw131","country_code":"HK","type":"education","lineage":["https://openalex.org/I141568987"]}],"countries":["HK"],"is_corresponding":false,"raw_author_name":"Yiu-Ming Cheung","raw_affiliation_strings":["Department of CS, Hong Kong Baptist University, Hong Kong SAR, China"],"raw_orcid":"https://orcid.org/0000-0001-7629-4648","affiliations":[{"raw_affiliation_string":"Department of CS, Hong Kong Baptist University, Hong Kong SAR, China","institution_ids":["https://openalex.org/I141568987"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5047240103","display_name":"Bo Han","orcid":"https://orcid.org/0000-0002-6338-0958"},"institutions":[{"id":"https://openalex.org/I141568987","display_name":"Hong Kong Baptist University","ror":"https://ror.org/0145fw131","country_code":"HK","type":"education","lineage":["https://openalex.org/I141568987"]}],"countries":["HK"],"is_corresponding":false,"raw_author_name":"Bo Han","raw_affiliation_strings":["Department of CS, Hong Kong Baptist University, Hong Kong SAR, China"],"raw_orcid":"https://orcid.org/0000-0002-6338-0958","affiliations":[{"raw_affiliation_string":"Department of CS, Hong Kong Baptist University, Hong Kong SAR, China","institution_ids":["https://openalex.org/I141568987"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":1.9035,"has_fulltext":false,"cited_by_count":13,"citation_normalized_percentile":{"value":0.87845072,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":99},"biblio":{"volume":"18","issue":"1","first_page":"1","last_page":"22"},"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":0.9987000226974487,"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/T10462","display_name":"Reinforcement Learning in Robotics","score":0.961899995803833,"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/computer-science","display_name":"Computer science","score":0.8400005102157593},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.8240607380867004},{"id":"https://openalex.org/keywords/field","display_name":"Field (mathematics)","score":0.5260260701179504},{"id":"https://openalex.org/keywords/variance","display_name":"Variance (accounting)","score":0.5173391699790955},{"id":"https://openalex.org/keywords/distillation","display_name":"Distillation","score":0.5086615681648254},{"id":"https://openalex.org/keywords/federated-learning","display_name":"Federated learning","score":0.5070936679840088},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.41676628589630127},{"id":"https://openalex.org/keywords/constant","display_name":"Constant (computer programming)","score":0.4147254526615143},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.3529145121574402},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.07588645815849304}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8400005102157593},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.8240607380867004},{"id":"https://openalex.org/C9652623","wikidata":"https://www.wikidata.org/wiki/Q190109","display_name":"Field (mathematics)","level":2,"score":0.5260260701179504},{"id":"https://openalex.org/C196083921","wikidata":"https://www.wikidata.org/wiki/Q7915758","display_name":"Variance (accounting)","level":2,"score":0.5173391699790955},{"id":"https://openalex.org/C204030448","wikidata":"https://www.wikidata.org/wiki/Q101017","display_name":"Distillation","level":2,"score":0.5086615681648254},{"id":"https://openalex.org/C2992525071","wikidata":"https://www.wikidata.org/wiki/Q50818671","display_name":"Federated learning","level":2,"score":0.5070936679840088},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.41676628589630127},{"id":"https://openalex.org/C2777027219","wikidata":"https://www.wikidata.org/wiki/Q1284190","display_name":"Constant (computer programming)","level":2,"score":0.4147254526615143},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3529145121574402},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.07588645815849304},{"id":"https://openalex.org/C121955636","wikidata":"https://www.wikidata.org/wiki/Q4116214","display_name":"Accounting","level":1,"score":0.0},{"id":"https://openalex.org/C144133560","wikidata":"https://www.wikidata.org/wiki/Q4830453","display_name":"Business","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/C178790620","wikidata":"https://www.wikidata.org/wiki/Q11351","display_name":"Organic chemistry","level":1,"score":0.0},{"id":"https://openalex.org/C202444582","wikidata":"https://www.wikidata.org/wiki/Q837863","display_name":"Pure mathematics","level":1,"score":0.0},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3604939","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3604939","pdf_url":null,"source":{"id":"https://openalex.org/S41523882","display_name":"ACM Transactions on Knowledge Discovery from Data","issn_l":"1556-4681","issn":["1556-4681","1556-472X"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319798","host_organization_name":"Association for Computing Machinery","host_organization_lineage":["https://openalex.org/P4310319798"],"host_organization_lineage_names":["Association for Computing Machinery"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ACM Transactions on Knowledge Discovery from Data","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G149644784","display_name":null,"funder_award_id":"2022ZD0160702, 2022ZD0160703","funder_id":"https://openalex.org/F4320335777","funder_display_name":"National Key Research and Development Program of China"},{"id":"https://openalex.org/G1509257010","display_name":null,"funder_award_id":"21DZ1100100","funder_id":"https://openalex.org/F4320321885","funder_display_name":"Science and Technology Commission of Shanghai Municipality"},{"id":"https://openalex.org/G1587973290","display_name":null,"funder_award_id":"30920032202","funder_id":"https://openalex.org/F4320335787","funder_display_name":"Fundamental Research Funds for the Central Universities"},{"id":"https://openalex.org/G1774008162","display_name":null,"funder_award_id":"22511106101","funder_id":"https://openalex.org/F4320321885","funder_display_name":"Science and Technology Commission of Shanghai Municipality"},{"id":"https://openalex.org/G2021513510","display_name":null,"funder_award_id":"30921013114","funder_id":"https://openalex.org/F4320335787","funder_display_name":"Fundamental Research Funds for the Central Universities"},{"id":"https://openalex.org/G2141978782","display_name":null,"funder_award_id":"30920032202, 30921013114","funder_id":"https://openalex.org/F4320335787","funder_display_name":"Fundamental Research Funds for the Central Universities"},{"id":"https://openalex.org/G2189095408","display_name":null,"funder_award_id":"62006202","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G4787607161","display_name":null,"funder_award_id":"RC-FNRA-IG/18-19/SCI/03","funder_id":"https://openalex.org/F4320320955","funder_display_name":"Hong Kong Baptist University"},{"id":"https://openalex.org/G5047994227","display_name":null,"funder_award_id":"BP0719010","funder_id":"https://openalex.org/F4320321885","funder_display_name":"Science and Technology Commission of Shanghai Municipality"},{"id":"https://openalex.org/G5140599133","display_name":null,"funder_award_id":"12201321","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G6177657093","display_name":null,"funder_award_id":"BP0719010","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G635492164","display_name":null,"funder_award_id":"22511105700","funder_id":"https://openalex.org/F4320321885","funder_display_name":"Science and Technology Commission of Shanghai Municipality"},{"id":"https://openalex.org/G6515857316","display_name":null,"funder_award_id":"N_HKBU214/21","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G7957291013","display_name":null,"funder_award_id":"2022A1515011652","funder_id":"https://openalex.org/F4320337111","funder_display_name":"Basic and Applied Basic Research Foundation of Guangdong Province"},{"id":"https://openalex.org/G7992385955","display_name":null,"funder_award_id":"61973162","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G8229360684","display_name":null,"funder_award_id":"22511106101, 22511105700, 21DZ1100100","funder_id":"https://openalex.org/F4320321885","funder_display_name":"Science and Technology Commission of Shanghai Municipality"}],"funders":[{"id":"https://openalex.org/F4320306076","display_name":"National Science Foundation","ror":"https://ror.org/021nxhr62"},{"id":"https://openalex.org/F4320320955","display_name":"Hong Kong Baptist University","ror":"https://ror.org/0145fw131"},{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"},{"id":"https://openalex.org/F4320321605","display_name":"Government of Jiangsu Province","ror":"https://ror.org/004svx814"},{"id":"https://openalex.org/F4320321885","display_name":"Science and Technology Commission of Shanghai Municipality","ror":"https://ror.org/03kt66j61"},{"id":"https://openalex.org/F4320335581","display_name":"Young Scientists Fund","ror":null},{"id":"https://openalex.org/F4320335777","display_name":"National Key Research and Development Program of China","ror":null},{"id":"https://openalex.org/F4320335787","display_name":"Fundamental Research Funds for the Central Universities","ror":null},{"id":"https://openalex.org/F4320337111","display_name":"Basic and Applied Basic Research Foundation of Guangdong Province","ror":null}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":22,"referenced_works":["https://openalex.org/W14611369","https://openalex.org/W1641379095","https://openalex.org/W1980516134","https://openalex.org/W2137983211","https://openalex.org/W2147492008","https://openalex.org/W2155027007","https://openalex.org/W2165698076","https://openalex.org/W2604873668","https://openalex.org/W2802595847","https://openalex.org/W2968937098","https://openalex.org/W3004397388","https://openalex.org/W3025869479","https://openalex.org/W3034225898","https://openalex.org/W3172419167","https://openalex.org/W3182158470","https://openalex.org/W3207250575","https://openalex.org/W4220842548","https://openalex.org/W4283790903","https://openalex.org/W4284974283","https://openalex.org/W4293412085","https://openalex.org/W4317815302","https://openalex.org/W4362653493"],"related_works":["https://openalex.org/W4298221930","https://openalex.org/W4362501864","https://openalex.org/W2777914285","https://openalex.org/W4306904969","https://openalex.org/W4380318855","https://openalex.org/W4287823391","https://openalex.org/W2138720691","https://openalex.org/W3013363440","https://openalex.org/W2031695474","https://openalex.org/W2586732548"],"abstract_inverted_index":{"Federated":[0,33],"Learning":[1,35],"(FL)":[2],"learns":[3,75],"a":[4,8,39,118,156,175,191],"global":[5,168],"model":[6,120,147],"in":[7,28,56,109,194],"distributional":[9],"manner,":[10],"which":[11],"does":[12],"not":[13],"require":[14],"local":[15,140,157],"clients":[16],"to":[17,76,104],"share":[18],"private":[19],"data.":[20],"Such":[21],"merit":[22],"has":[23,190],"drawn":[24],"lots":[25],"of":[26,48,68,153,177],"attention":[27],"the":[29,45,53,62,66,71,79,84,91,101,106,134,143,151,154,164,167],"interaction":[30],"scenarios,":[31],"where":[32],"Reinforcement":[34],"(FRL)":[36],"emerges":[37],"as":[38,126],"cross-field":[40],"research":[41],"direction":[42],"focusing":[43],"on":[44,65,142],"robust":[46],"training":[47],"agents.":[49],"Different":[50],"from":[51],"FL,":[52,136],"heterogeneity":[54,107],"problem":[55,108],"FRL":[57,74,110,115],"is":[58,131,159],"more":[59],"challenging":[60],"because":[61],"data":[63,93],"depends":[64],"policy":[67],"agents":[69],"and":[70,111,122,183],"environment":[72,81],"dynamics.":[73],"interact":[77],"under":[78],"non-stationary":[80],"feedback,":[82],"while":[83],"typical":[85],"FL":[86,181],"methods":[87,182],"aim":[88],"at":[89],"handling":[90],"constant":[92],"heterogeneity.":[94],"In":[95],"this":[96],"article,":[97],"we":[98,137,171],"are":[99],"among":[100],"first":[102],"attempts":[103],"analyze":[105],"propose":[112],"an":[113],"off-policy":[114],"framework.":[116],"Specifically,":[117],"student\u2013teacher\u2013student":[119],"learning":[121],"fusion":[123],"method,":[124],"termed":[125],"Server-Client":[127],"Collaborative":[128],"Distillation":[129],"(SCCD),":[130],"introduced.":[132],"Unlike":[133],"traditional":[135],"distill":[138],"all":[139],"models":[141],"server":[144],"side":[145],"for":[146],"fusion.":[148],"To":[149],"reduce":[150],"variance":[152],"training,":[155],"distillation":[158],"also":[160],"conducted":[161],"every":[162],"time":[163],"agent":[165],"receives":[166],"model.":[169],"Experimentally,":[170],"compare":[172],"SCCD":[173,189],"with":[174,200],"range":[176],"straightforward":[178],"combinations":[179],"between":[180],"RL.":[184],"The":[185],"results":[186],"demonstrate":[187],"that":[188],"superior":[192],"performance":[193],"four":[195],"classical":[196],"continuous":[197],"control":[198],"tasks":[199],"non-IID":[201],"environments.":[202]},"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2025,"cited_by_count":8},{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":1},{"year":2021,"cited_by_count":1}],"updated_date":"2026-05-21T06:26:12.895304","created_date":"2025-10-10T00:00:00"}