{"id":"https://openalex.org/W7138452553","doi":"https://doi.org/10.1609/aaai.v40i26.39361","title":"Federated Linear Dueling Bandits","display_name":"Federated Linear Dueling Bandits","publication_year":2026,"publication_date":"2026-03-14","ids":{"openalex":"https://openalex.org/W7138452553","doi":"https://doi.org/10.1609/aaai.v40i26.39361"},"language":null,"primary_location":{"id":"doi:10.1609/aaai.v40i26.39361","is_oa":true,"landing_page_url":"https://doi.org/10.1609/aaai.v40i26.39361","pdf_url":null,"source":{"id":"https://openalex.org/S4210191458","display_name":"Proceedings of the AAAI Conference on Artificial Intelligence","issn_l":"2159-5399","issn":["2159-5399","2374-3468"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/P4310320058","host_organization_name":"Association for the Advancement of Artificial Intelligence","host_organization_lineage":["https://openalex.org/P4310320058"],"host_organization_lineage_names":["Association for the Advancement of Artificial Intelligence"],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the AAAI Conference on Artificial Intelligence","raw_type":"journal-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"diamond","oa_url":"https://doi.org/10.1609/aaai.v40i26.39361","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5116145180","display_name":"Xuhan Huang","orcid":null},"institutions":[{"id":"https://openalex.org/I4210116924","display_name":"Chinese University of Hong Kong, Shenzhen","ror":"https://ror.org/02d5ks197","country_code":"CN","type":"education","lineage":["https://openalex.org/I177725633","https://openalex.org/I180726961","https://openalex.org/I4210116924"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xuhan Huang","raw_affiliation_strings":["School of Science and Engineering, The Chinese University of Hong Kong, Shenzhen"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Science and Engineering, The Chinese University of Hong Kong, Shenzhen","institution_ids":["https://openalex.org/I4210116924"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5129718470","display_name":"Yan Hu","orcid":null},"institutions":[{"id":"https://openalex.org/I4210116924","display_name":"Chinese University of Hong Kong, Shenzhen","ror":"https://ror.org/02d5ks197","country_code":"CN","type":"education","lineage":["https://openalex.org/I177725633","https://openalex.org/I180726961","https://openalex.org/I4210116924"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yan Hu","raw_affiliation_strings":["School of Data Science, The Chinese University of Hong Kong, Shenzhen\nNational Health Data Institute, Shenzhen"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Data Science, The Chinese University of Hong Kong, Shenzhen\nNational Health Data Institute, Shenzhen","institution_ids":["https://openalex.org/I4210116924"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5129711378","display_name":"Zhiyan Li","orcid":null},"institutions":[{"id":"https://openalex.org/I4210116924","display_name":"Chinese University of Hong Kong, Shenzhen","ror":"https://ror.org/02d5ks197","country_code":"CN","type":"education","lineage":["https://openalex.org/I177725633","https://openalex.org/I180726961","https://openalex.org/I4210116924"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhiyan Li","raw_affiliation_strings":["School of Data Science, The Chinese University of Hong Kong, Shenzhen"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Data Science, The Chinese University of Hong Kong, Shenzhen","institution_ids":["https://openalex.org/I4210116924"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5129737117","display_name":"Zhiyong Wang","orcid":null},"institutions":[{"id":"https://openalex.org/I98677209","display_name":"University of Edinburgh","ror":"https://ror.org/01nrxwf90","country_code":"GB","type":"education","lineage":["https://openalex.org/I98677209"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Zhiyong Wang","raw_affiliation_strings":["The University of Edinburgh"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"The University of Edinburgh","institution_ids":["https://openalex.org/I98677209"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5129704637","display_name":"Zhongxiang Dai","orcid":null},"institutions":[{"id":"https://openalex.org/I4210116924","display_name":"Chinese University of Hong Kong, Shenzhen","ror":"https://ror.org/02d5ks197","country_code":"CN","type":"education","lineage":["https://openalex.org/I177725633","https://openalex.org/I180726961","https://openalex.org/I4210116924"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhongxiang Dai","raw_affiliation_strings":["School of Data Science, The Chinese University of Hong Kong, Shenzhen"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Data Science, The Chinese University of Hong Kong, Shenzhen","institution_ids":["https://openalex.org/I4210116924"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":5,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.48920863,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"40","issue":"26","first_page":"22066","last_page":"22074"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12101","display_name":"Advanced Bandit Algorithms Research","score":0.8174999952316284,"subfield":{"id":"https://openalex.org/subfields/1803","display_name":"Management Science and Operations Research"},"field":{"id":"https://openalex.org/fields/18","display_name":"Decision Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},"topics":[{"id":"https://openalex.org/T12101","display_name":"Advanced Bandit Algorithms Research","score":0.8174999952316284,"subfield":{"id":"https://openalex.org/subfields/1803","display_name":"Management Science and Operations Research"},"field":{"id":"https://openalex.org/fields/18","display_name":"Decision Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},{"id":"https://openalex.org/T11612","display_name":"Stochastic Gradient Optimization Techniques","score":0.03620000183582306,"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/T10203","display_name":"Recommender Systems and Techniques","score":0.01590000092983246,"subfield":{"id":"https://openalex.org/subfields/1710","display_name":"Information Systems"},"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/regret","display_name":"Regret","score":0.9319000244140625},{"id":"https://openalex.org/keywords/function","display_name":"Function (biology)","score":0.5967000126838684},{"id":"https://openalex.org/keywords/gradient-descent","display_name":"Gradient descent","score":0.5284000039100647},{"id":"https://openalex.org/keywords/recommender-system","display_name":"Recommender system","score":0.3776000142097473},{"id":"https://openalex.org/keywords/upper-and-lower-bounds","display_name":"Upper and lower bounds","score":0.3488999903202057},{"id":"https://openalex.org/keywords/stochastic-gradient-descent","display_name":"Stochastic gradient descent","score":0.3481999933719635},{"id":"https://openalex.org/keywords/linear-programming","display_name":"Linear programming","score":0.3366999924182892}],"concepts":[{"id":"https://openalex.org/C50817715","wikidata":"https://www.wikidata.org/wiki/Q79895177","display_name":"Regret","level":2,"score":0.9319000244140625},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7599999904632568},{"id":"https://openalex.org/C14036430","wikidata":"https://www.wikidata.org/wiki/Q3736076","display_name":"Function (biology)","level":2,"score":0.5967000126838684},{"id":"https://openalex.org/C153258448","wikidata":"https://www.wikidata.org/wiki/Q1199743","display_name":"Gradient descent","level":3,"score":0.5284000039100647},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.47909998893737793},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3790000081062317},{"id":"https://openalex.org/C557471498","wikidata":"https://www.wikidata.org/wiki/Q554950","display_name":"Recommender system","level":2,"score":0.3776000142097473},{"id":"https://openalex.org/C77553402","wikidata":"https://www.wikidata.org/wiki/Q13222579","display_name":"Upper and lower bounds","level":2,"score":0.3488999903202057},{"id":"https://openalex.org/C206688291","wikidata":"https://www.wikidata.org/wiki/Q7617819","display_name":"Stochastic gradient descent","level":3,"score":0.3481999933719635},{"id":"https://openalex.org/C41045048","wikidata":"https://www.wikidata.org/wiki/Q202843","display_name":"Linear programming","level":2,"score":0.3366999924182892},{"id":"https://openalex.org/C2984842247","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep neural networks","level":3,"score":0.32339999079704285},{"id":"https://openalex.org/C2776502983","wikidata":"https://www.wikidata.org/wiki/Q690182","display_name":"Contrast (vision)","level":2,"score":0.314300000667572},{"id":"https://openalex.org/C196921405","wikidata":"https://www.wikidata.org/wiki/Q786431","display_name":"Online algorithm","level":2,"score":0.3075000047683716},{"id":"https://openalex.org/C163175372","wikidata":"https://www.wikidata.org/wiki/Q3339222","display_name":"Linear model","level":2,"score":0.30660000443458557},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.296999990940094},{"id":"https://openalex.org/C42475967","wikidata":"https://www.wikidata.org/wiki/Q194292","display_name":"Operations research","level":1,"score":0.2761000096797943},{"id":"https://openalex.org/C123197309","wikidata":"https://www.wikidata.org/wiki/Q2882343","display_name":"Multi-armed bandit","level":3,"score":0.26409998536109924},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.25920000672340393},{"id":"https://openalex.org/C107321475","wikidata":"https://www.wikidata.org/wiki/Q5374254","display_name":"Empirical risk minimization","level":2,"score":0.25130000710487366}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1609/aaai.v40i26.39361","is_oa":true,"landing_page_url":"https://doi.org/10.1609/aaai.v40i26.39361","pdf_url":null,"source":{"id":"https://openalex.org/S4210191458","display_name":"Proceedings of the AAAI Conference on Artificial Intelligence","issn_l":"2159-5399","issn":["2159-5399","2374-3468"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/P4310320058","host_organization_name":"Association for the Advancement of Artificial Intelligence","host_organization_lineage":["https://openalex.org/P4310320058"],"host_organization_lineage_names":["Association for the Advancement of Artificial Intelligence"],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the AAAI Conference on Artificial Intelligence","raw_type":"journal-article"}],"best_oa_location":{"id":"doi:10.1609/aaai.v40i26.39361","is_oa":true,"landing_page_url":"https://doi.org/10.1609/aaai.v40i26.39361","pdf_url":null,"source":{"id":"https://openalex.org/S4210191458","display_name":"Proceedings of the AAAI Conference on Artificial Intelligence","issn_l":"2159-5399","issn":["2159-5399","2374-3468"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/P4310320058","host_organization_name":"Association for the Advancement of Artificial Intelligence","host_organization_lineage":["https://openalex.org/P4310320058"],"host_organization_lineage_names":["Association for the Advancement of Artificial Intelligence"],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the AAAI Conference on Artificial Intelligence","raw_type":"journal-article"},"sustainable_development_goals":[{"score":0.4478154480457306,"display_name":"Partnerships for the goals","id":"https://metadata.un.org/sdg/17"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Contextual":[0],"linear":[1,94,108,116,120,167,177],"dueling":[2,26,41,117,178],"bandits":[3,42],"have":[4,91],"recently":[5],"garnered":[6],"significant":[7],"attention":[8],"due":[9],"to":[10,33,48,56,63,74,111,164,215],"their":[11,58,77,86,128],"widespread":[12],"applications":[13,39],"in":[14,115],"important":[15],"domains":[16],"such":[17,225],"as":[18,226],"recommender":[19],"systems":[20],"and":[21,127,151,170,201,208,221],"large":[22],"language":[23],"models.":[24],"Classical":[25],"bandit":[27,95,104,179],"algorithms":[28,96],"are":[29,54],"typically":[30],"only":[31],"applicable":[32],"a":[34,124,132,193,203,230],"single":[35],"agent.":[36],"However,":[37,114],"many":[38],"of":[40,102,154,219,229,233],"involve":[43],"multiple":[44,71],"agents":[45,72],"who":[46],"wish":[47],"collaborate":[49],"for":[50,159],"improved":[51],"performance":[52],"yet":[53],"unwilling":[55],"share":[57],"data.":[59,88],"This":[60,135],"motivates":[61],"us":[62],"draw":[64],"inspirations":[65],"from":[66],"federated":[67,93,171,176],"learning,":[68,172],"which":[69,97],"involves":[70],"aiming":[73],"collaboratively":[75],"train":[76],"neural":[78],"networks":[79],"via":[80],"gradient":[81,156],"descent":[82,157],"(GD)":[83],"without":[84],"sharing":[85],"raw":[87],"Previous":[89],"works":[90],"developed":[92],"rely":[98],"on":[99,197],"closed-form":[100,125],"updates":[101],"the":[103,107,119,161,166,217,227,235],"parameters":[105,122],"(e.g.,":[106],"function":[109,121,163,168],"parameters)":[110,169],"achieve":[112],"collaboration.":[113],"bandits,":[118],"lack":[123],"expression":[126],"estimation":[129],"requires":[130],"minimizing":[131,160],"loss":[133,162],"function.":[134],"renders":[136],"these":[137],"previous":[138],"methods":[139],"inapplicable.":[140],"In":[141],"this":[142,146],"work,":[143],"we":[144,188],"overcome":[145],"challenge":[147],"through":[148],"an":[149],"innovative":[150],"principled":[152],"combination":[153],"online":[155],"(OGD,":[158],"estimate":[165],"hence":[173],"introducing":[174],"our":[175],"with":[180],"OGD":[181],"(FLDB-OGD)":[182],"algorithm.":[183],"Through":[184],"rigorous":[185],"theoretical":[186,204],"analysis,":[187],"prove":[189],"that":[190],"FLDB-OGD":[191,220],"enjoys":[192],"sub-linear":[194],"upper":[195],"bound":[196],"its":[198],"cumulative":[199],"regret":[200,207],"demonstrate":[202,216],"trade-off":[205],"between":[206],"communication":[209],"complexity.":[210],"We":[211],"conduct":[212],"empirical":[213],"experiments":[214],"effectiveness":[218],"reveal":[222],"valuable":[223],"insights,":[224],"benefit":[228],"larger":[231],"number":[232],"agents,":[234],"regret-communication":[236],"trade-off,":[237],"among":[238],"others.":[239]},"counts_by_year":[],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2026-03-18T00:00:00"}