{"id":"https://openalex.org/W4290827187","doi":"https://doi.org/10.1145/3534678.3539040","title":"Multi-Task Fusion via Reinforcement Learning for Long-Term User Satisfaction in Recommender Systems","display_name":"Multi-Task Fusion via Reinforcement Learning for Long-Term User Satisfaction in Recommender Systems","publication_year":2022,"publication_date":"2022-08-12","ids":{"openalex":"https://openalex.org/W4290827187","doi":"https://doi.org/10.1145/3534678.3539040"},"language":"en","primary_location":{"id":"doi:10.1145/3534678.3539040","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3534678.3539040","pdf_url":null,"source":{"id":"https://openalex.org/S4363608767","display_name":"Proceedings of the 28th ACM SIGKDD Conference on Knowledge Discovery and Data Mining","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 28th ACM SIGKDD Conference on Knowledge Discovery and Data Mining","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["arxiv","crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2208.04560","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5101932826","display_name":"Qihua Zhang","orcid":"https://orcid.org/0000-0002-0707-2299"},"institutions":[{"id":"https://openalex.org/I2250653659","display_name":"Tencent (China)","ror":"https://ror.org/00hhjss72","country_code":"CN","type":"company","lineage":["https://openalex.org/I2250653659"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Qihua Zhang","raw_affiliation_strings":["Tencent, Shenzhen, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tencent, Shenzhen, China","institution_ids":["https://openalex.org/I2250653659"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5043185748","display_name":"Junning Liu","orcid":"https://orcid.org/0000-0003-0844-4071"},"institutions":[{"id":"https://openalex.org/I2250653659","display_name":"Tencent (China)","ror":"https://ror.org/00hhjss72","country_code":"CN","type":"company","lineage":["https://openalex.org/I2250653659"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Junning Liu","raw_affiliation_strings":["Tencent, Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tencent, Beijing, China","institution_ids":["https://openalex.org/I2250653659"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5085218392","display_name":"Yuzhuo Dai","orcid":null},"institutions":[{"id":"https://openalex.org/I2250653659","display_name":"Tencent (China)","ror":"https://ror.org/00hhjss72","country_code":"CN","type":"company","lineage":["https://openalex.org/I2250653659"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yuzhuo Dai","raw_affiliation_strings":["Tencent, Shenzhen, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tencent, Shenzhen, China","institution_ids":["https://openalex.org/I2250653659"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5109583372","display_name":"Yiyan Qi","orcid":null},"institutions":[{"id":"https://openalex.org/I2250653659","display_name":"Tencent (China)","ror":"https://ror.org/00hhjss72","country_code":"CN","type":"company","lineage":["https://openalex.org/I2250653659"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yiyan Qi","raw_affiliation_strings":["Tencent, Shenzhen, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tencent, Shenzhen, China","institution_ids":["https://openalex.org/I2250653659"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5103139028","display_name":"Yifan Yuan","orcid":"https://orcid.org/0009-0009-9279-2191"},"institutions":[{"id":"https://openalex.org/I2250653659","display_name":"Tencent (China)","ror":"https://ror.org/00hhjss72","country_code":"CN","type":"company","lineage":["https://openalex.org/I2250653659"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yifan Yuan","raw_affiliation_strings":["Tencent, Shenzhen, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tencent, Shenzhen, China","institution_ids":["https://openalex.org/I2250653659"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5109583373","display_name":"Kunlun Zheng","orcid":null},"institutions":[{"id":"https://openalex.org/I2250653659","display_name":"Tencent (China)","ror":"https://ror.org/00hhjss72","country_code":"CN","type":"company","lineage":["https://openalex.org/I2250653659"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Kunlun Zheng","raw_affiliation_strings":["Tencent, Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tencent, Beijing, China","institution_ids":["https://openalex.org/I2250653659"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5030892313","display_name":"Fan Huang","orcid":"https://orcid.org/0000-0002-1817-6501"},"institutions":[{"id":"https://openalex.org/I2250653659","display_name":"Tencent (China)","ror":"https://ror.org/00hhjss72","country_code":"CN","type":"company","lineage":["https://openalex.org/I2250653659"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Fan Huang","raw_affiliation_strings":["Tencent, Shenzhen, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tencent, Shenzhen, China","institution_ids":["https://openalex.org/I2250653659"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5086149782","display_name":"Xianfeng Tan","orcid":null},"institutions":[{"id":"https://openalex.org/I2250653659","display_name":"Tencent (China)","ror":"https://ror.org/00hhjss72","country_code":"CN","type":"company","lineage":["https://openalex.org/I2250653659"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xianfeng Tan","raw_affiliation_strings":["Tencent, Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tencent, Beijing, China","institution_ids":["https://openalex.org/I2250653659"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I2250653659"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":49,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"4510","last_page":"4520"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10203","display_name":"Recommender Systems and Techniques","score":0.9998999834060669,"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"}},"topics":[{"id":"https://openalex.org/T10203","display_name":"Recommender Systems and Techniques","score":0.9998999834060669,"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"}},{"id":"https://openalex.org/T12101","display_name":"Advanced Bandit Algorithms Research","score":0.9988999962806702,"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/T10603","display_name":"Smart Grid Energy Management","score":0.9793000221252441,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/recommender-system","display_name":"Recommender system","score":0.8328851461410522},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8163420557975769},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.7259467840194702},{"id":"https://openalex.org/keywords/ranking","display_name":"Ranking (information retrieval)","score":0.598347008228302},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.5810089707374573},{"id":"https://openalex.org/keywords/markov-decision-process","display_name":"Markov decision process","score":0.5270650386810303},{"id":"https://openalex.org/keywords/term","display_name":"Term (time)","score":0.5087526440620422},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.4664815068244934},{"id":"https://openalex.org/keywords/heuristics","display_name":"Heuristics","score":0.4628294110298157},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4322333037853241},{"id":"https://openalex.org/keywords/session","display_name":"Session (web analytics)","score":0.42027193307876587},{"id":"https://openalex.org/keywords/markov-process","display_name":"Markov process","score":0.24313700199127197},{"id":"https://openalex.org/keywords/world-wide-web","display_name":"World Wide Web","score":0.1512824296951294}],"concepts":[{"id":"https://openalex.org/C557471498","wikidata":"https://www.wikidata.org/wiki/Q554950","display_name":"Recommender system","level":2,"score":0.8328851461410522},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8163420557975769},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.7259467840194702},{"id":"https://openalex.org/C189430467","wikidata":"https://www.wikidata.org/wiki/Q7293293","display_name":"Ranking (information retrieval)","level":2,"score":0.598347008228302},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.5810089707374573},{"id":"https://openalex.org/C106189395","wikidata":"https://www.wikidata.org/wiki/Q176789","display_name":"Markov decision process","level":3,"score":0.5270650386810303},{"id":"https://openalex.org/C61797465","wikidata":"https://www.wikidata.org/wiki/Q1188986","display_name":"Term (time)","level":2,"score":0.5087526440620422},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.4664815068244934},{"id":"https://openalex.org/C127705205","wikidata":"https://www.wikidata.org/wiki/Q5748245","display_name":"Heuristics","level":2,"score":0.4628294110298157},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4322333037853241},{"id":"https://openalex.org/C2779182362","wikidata":"https://www.wikidata.org/wiki/Q17126187","display_name":"Session (web analytics)","level":2,"score":0.42027193307876587},{"id":"https://openalex.org/C159886148","wikidata":"https://www.wikidata.org/wiki/Q176645","display_name":"Markov process","level":2,"score":0.24313700199127197},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.1512824296951294},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"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/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.0},{"id":"https://openalex.org/C187736073","wikidata":"https://www.wikidata.org/wiki/Q2920921","display_name":"Management","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1145/3534678.3539040","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3534678.3539040","pdf_url":null,"source":{"id":"https://openalex.org/S4363608767","display_name":"Proceedings of the 28th ACM SIGKDD Conference on Knowledge Discovery and Data Mining","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 28th ACM SIGKDD Conference on Knowledge Discovery and Data Mining","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2208.04560","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2208.04560","pdf_url":"https://arxiv.org/pdf/2208.04560","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"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":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2208.04560","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2208.04560","pdf_url":"https://arxiv.org/pdf/2208.04560","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"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":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":41,"referenced_works":["https://openalex.org/W41554520","https://openalex.org/W1608650045","https://openalex.org/W1979356488","https://openalex.org/W2076618162","https://openalex.org/W2125442594","https://openalex.org/W2155467656","https://openalex.org/W2156455250","https://openalex.org/W2159094788","https://openalex.org/W2478168051","https://openalex.org/W2512971201","https://openalex.org/W2584136418","https://openalex.org/W2723293840","https://openalex.org/W2781726626","https://openalex.org/W2787938642","https://openalex.org/W2799544270","https://openalex.org/W2904453761","https://openalex.org/W2912570479","https://openalex.org/W2945772520","https://openalex.org/W2948903560","https://openalex.org/W2962734844","https://openalex.org/W2962745591","https://openalex.org/W2963561234","https://openalex.org/W2963842088","https://openalex.org/W2984671888","https://openalex.org/W2997014384","https://openalex.org/W2999560001","https://openalex.org/W3010870049","https://openalex.org/W3029901419","https://openalex.org/W3033324992","https://openalex.org/W3087931390","https://openalex.org/W3088658870","https://openalex.org/W3093601757","https://openalex.org/W3102899483","https://openalex.org/W3105066045","https://openalex.org/W3106252282","https://openalex.org/W3123348991","https://openalex.org/W3170059879","https://openalex.org/W4252003911","https://openalex.org/W4302570325","https://openalex.org/W4394672593","https://openalex.org/W6836725202"],"related_works":["https://openalex.org/W4400868993","https://openalex.org/W3096874164","https://openalex.org/W1985560493","https://openalex.org/W2386410636","https://openalex.org/W2357975469","https://openalex.org/W2145363145","https://openalex.org/W1626977535","https://openalex.org/W4284974072","https://openalex.org/W2341346307","https://openalex.org/W2922107804"],"abstract_inverted_index":{"Recommender":[0],"System":[1],"(RS)":[2],"is":[3,20],"an":[4,130,140],"important":[5],"online":[6,131,161,228],"application":[7],"that":[8,30,45,123],"affects":[9],"billions":[10],"of":[11,22,84,188,209,238,243,268,270],"users":[12],"every":[13],"day.":[14],"The":[15,133],"mainstream":[16],"RS":[17],"ranking":[18,53],"framework":[19,121,128],"composed":[21],"two":[23,186],"parts:":[24],"a":[25,40,108,113,125,170,200,214,231,260],"Multi-Task":[26,41,119],"Learning":[27,116],"model":[28,43,69,177,223,254],"(MTL)":[29],"predicts":[31],"various":[32],"user":[33,58,90,152,174,179,189,192],"feedback,":[34],"i.e.,":[35],"clicks,":[36],"likes,":[37],"sharings,":[38],"and":[39,111,129,191],"Fusion":[42,120],"(MTF)":[44],"combines":[46],"the":[47,67,76,80,85,145,155,165,178,207],"multi-task":[48],"outputs":[49],"into":[50],"one":[51,242],"final":[52,77],"score":[54],"with":[55,182],"respect":[56],"to":[57,138,162,205,220,235],"satisfaction.":[59],"There":[60],"has":[61,72,255],"not":[62],"been":[63,257],"much":[64],"research":[65],"on":[66,75,173,199,259],"fusion":[68],"while":[70,154],"it":[71],"great":[73],"impact":[74],"recommendation":[78,109,142,233],"as":[79,102],"last":[81],"crucial":[82],"process":[83],"ranking.":[86],"To":[87],"optimize":[88],"long-term":[89,151],"satisfaction":[91,180],"rather":[92],"than":[93],"obtain":[94],"instant":[95],"returns":[96],"greedily,":[97],"we":[98,176,195,226],"formulate":[99],"MTF":[100,250],"task":[101,251],"Markov":[103],"Decision":[104],"Process":[105],"(MDP)":[106],"within":[107],"session":[110],"propose":[112,213],"Batch":[114,126,136,245],"Reinforcement":[115],"(RL)":[117],"based":[118],"(BatchRL-MTF)":[122],"includes":[124],"RL":[127,137,246],"exploration.":[132],"former":[134],"exploits":[135],"learn":[139],"optimal":[141,167],"policy":[143,217],"from":[144,185],"fixed":[146],"batch":[147],"data":[148],"offline":[149,216],"for":[150],"satisfaction,":[153],"latter":[156],"explores":[157],"potential":[158],"high-value":[159],"actions":[160],"break":[163],"through":[164],"local":[166],"dilemma.":[168],"With":[169],"comprehensive":[171],"investigation":[172],"behaviors,":[175],"reward":[181],"subtle":[183],"heuristics":[184],"aspects":[187],"stickiness":[190],"activeness.":[193],"Finally,":[194],"conduct":[196],"extensive":[197],"experiments":[198,229],"billion-sample":[201],"level":[202],"real-world":[203],"dataset":[204],"show":[206],"effectiveness":[208],"our":[210,222,253],"model.":[211],"We":[212],"conservative":[215],"estimator":[218],"(Conservative-OPEstimator)":[219],"test":[221],"offline.":[224],"Furthermore,":[225],"take":[227],"in":[230,249],"real":[232],"environment":[234],"compare":[236],"performance":[237],"different":[239],"models.":[240],"As":[241],"few":[244],"researches":[247],"applied":[248],"successfully,":[252],"also":[256],"deployed":[258],"large-scale":[261],"industrial":[262],"short":[263],"video":[264],"platform,":[265],"serving":[266],"hundreds":[267],"millions":[269],"users.":[271]},"counts_by_year":[{"year":2026,"cited_by_count":5},{"year":2025,"cited_by_count":12},{"year":2024,"cited_by_count":16},{"year":2023,"cited_by_count":16}],"updated_date":"2026-07-28T07:46:37.118299","created_date":"2025-10-10T00:00:00"}