{"id":"https://openalex.org/W4319653664","doi":"https://doi.org/10.1145/3543507.3583467","title":"Multi-Task Recommendations with Reinforcement Learning","display_name":"Multi-Task Recommendations with Reinforcement Learning","publication_year":2023,"publication_date":"2023-04-26","ids":{"openalex":"https://openalex.org/W4319653664","doi":"https://doi.org/10.1145/3543507.3583467"},"language":"en","primary_location":{"id":"doi:10.1145/3543507.3583467","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3543507.3583467","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the ACM Web Conference 2023","raw_type":"proceedings-article"},"type":"article","indexed_in":["arxiv","crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2302.03328","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5062737232","display_name":"Ziru Liu","orcid":null},"institutions":[{"id":"https://openalex.org/I168719708","display_name":"City University of Hong Kong","ror":"https://ror.org/03q8dnn23","country_code":"HK","type":"education","lineage":["https://openalex.org/I168719708"]}],"countries":["HK"],"is_corresponding":true,"raw_author_name":"Ziru Liu","raw_affiliation_strings":["City University of Hong Kong, China"],"raw_orcid":"https://orcid.org/0000-0001-6654-2329","affiliations":[{"raw_affiliation_string":"City University of Hong Kong, China","institution_ids":["https://openalex.org/I168719708"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5018281281","display_name":"Jiejie Tian","orcid":"https://orcid.org/0000-0001-7251-9782"},"institutions":[{"id":"https://openalex.org/I168719708","display_name":"City University of Hong Kong","ror":"https://ror.org/03q8dnn23","country_code":"HK","type":"education","lineage":["https://openalex.org/I168719708"]}],"countries":["HK"],"is_corresponding":false,"raw_author_name":"Jiejie Tian","raw_affiliation_strings":["City University of Hong Kong, China"],"raw_orcid":"https://orcid.org/0000-0001-7251-9782","affiliations":[{"raw_affiliation_string":"City University of Hong Kong, China","institution_ids":["https://openalex.org/I168719708"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5016589992","display_name":"Qingpeng Cai","orcid":"https://orcid.org/0000-0001-6451-9299"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Qingpeng Cai","raw_affiliation_strings":["Kuaishou, China"],"raw_orcid":"https://orcid.org/0000-0001-6451-9299","affiliations":[{"raw_affiliation_string":"Kuaishou, China","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100645854","display_name":"Xiangyu Zhao","orcid":"https://orcid.org/0000-0003-2926-4416"},"institutions":[{"id":"https://openalex.org/I168719708","display_name":"City University of Hong Kong","ror":"https://ror.org/03q8dnn23","country_code":"HK","type":"education","lineage":["https://openalex.org/I168719708"]}],"countries":["HK"],"is_corresponding":false,"raw_author_name":"Xiangyu Zhao","raw_affiliation_strings":["City University of Hong Kong, China"],"raw_orcid":"https://orcid.org/0000-0003-2926-4416","affiliations":[{"raw_affiliation_string":"City University of Hong Kong, China","institution_ids":["https://openalex.org/I168719708"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5040803163","display_name":"Jingtong Gao","orcid":"https://orcid.org/0000-0002-4470-5972"},"institutions":[{"id":"https://openalex.org/I168719708","display_name":"City University of Hong Kong","ror":"https://ror.org/03q8dnn23","country_code":"HK","type":"education","lineage":["https://openalex.org/I168719708"]}],"countries":["HK"],"is_corresponding":false,"raw_author_name":"Jingtong Gao","raw_affiliation_strings":["City University of Hong Kong, China"],"raw_orcid":"https://orcid.org/0000-0002-4470-5972","affiliations":[{"raw_affiliation_string":"City University of Hong Kong, China","institution_ids":["https://openalex.org/I168719708"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100600807","display_name":"Shuchang Liu","orcid":"https://orcid.org/0000-0002-1440-911X"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Shuchang Liu","raw_affiliation_strings":["Kuaishou, China"],"raw_orcid":"https://orcid.org/0000-0002-1440-911X","affiliations":[{"raw_affiliation_string":"Kuaishou, China","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5027784773","display_name":"Dayou Chen","orcid":"https://orcid.org/0000-0001-9957-3244"},"institutions":[{"id":"https://openalex.org/I168719708","display_name":"City University of Hong Kong","ror":"https://ror.org/03q8dnn23","country_code":"HK","type":"education","lineage":["https://openalex.org/I168719708"]}],"countries":["HK"],"is_corresponding":false,"raw_author_name":"Dayou Chen","raw_affiliation_strings":["City University of Hong Kong, China"],"raw_orcid":"https://orcid.org/0000-0001-9957-3244","affiliations":[{"raw_affiliation_string":"City University of Hong Kong, China","institution_ids":["https://openalex.org/I168719708"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5103275122","display_name":"Tonghao He","orcid":"https://orcid.org/0000-0002-2230-4625"},"institutions":[{"id":"https://openalex.org/I168719708","display_name":"City University of Hong Kong","ror":"https://ror.org/03q8dnn23","country_code":"HK","type":"education","lineage":["https://openalex.org/I168719708"]}],"countries":["HK"],"is_corresponding":false,"raw_author_name":"Tonghao He","raw_affiliation_strings":["City University of Hong Kong, China"],"raw_orcid":"https://orcid.org/0000-0002-2230-4625","affiliations":[{"raw_affiliation_string":"City University of Hong Kong, China","institution_ids":["https://openalex.org/I168719708"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5086177569","display_name":"Dong Zheng","orcid":"https://orcid.org/0000-0003-0424-9658"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Dong Zheng","raw_affiliation_strings":["Kuaishou, China"],"raw_orcid":"https://orcid.org/0000-0003-0424-9658","affiliations":[{"raw_affiliation_string":"Kuaishou, China","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5001339397","display_name":"Peng Jiang","orcid":"https://orcid.org/0000-0002-9266-0780"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Peng Jiang","raw_affiliation_strings":["Kuaishou, China"],"raw_orcid":"https://orcid.org/0000-0002-9266-0780","affiliations":[{"raw_affiliation_string":"Kuaishou, China","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5062939922","display_name":"Kun Gai","orcid":"https://orcid.org/0000-0002-3636-3618"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Kun Gai","raw_affiliation_strings":["Unaffiliated, China"],"raw_orcid":"https://orcid.org/0000-0002-3636-3618","affiliations":[{"raw_affiliation_string":"Unaffiliated, China","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":11,"corresponding_author_ids":["https://openalex.org/A5062737232"],"corresponding_institution_ids":["https://openalex.org/I168719708"],"apc_list":null,"apc_paid":null,"fwci":10.0788,"has_fulltext":true,"cited_by_count":41,"citation_normalized_percentile":{"value":0.98400023,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":98,"max":100},"biblio":{"volume":null,"issue":null,"first_page":"1273","last_page":"1282"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12101","display_name":"Advanced Bandit Algorithms Research","score":0.9997000098228455,"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":0.9997000098228455,"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/T10203","display_name":"Recommender Systems and Techniques","score":0.9991999864578247,"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/T12761","display_name":"Data Stream Mining Techniques","score":0.9941999912261963,"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":0.8027318716049194},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7355195879936218},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.6704976558685303},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4670495092868805},{"id":"https://openalex.org/keywords/reinforcement","display_name":"Reinforcement","score":0.4341937303543091},{"id":"https://openalex.org/keywords/human\u2013computer-interaction","display_name":"Human\u2013computer interaction","score":0.35206103324890137},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.3484461307525635},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.1305667757987976},{"id":"https://openalex.org/keywords/psychology","display_name":"Psychology","score":0.1156790554523468},{"id":"https://openalex.org/keywords/social-psychology","display_name":"Social psychology","score":0.052034586668014526},{"id":"https://openalex.org/keywords/systems-engineering","display_name":"Systems engineering","score":0.051728278398513794}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.8027318716049194},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7355195879936218},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.6704976558685303},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4670495092868805},{"id":"https://openalex.org/C67203356","wikidata":"https://www.wikidata.org/wiki/Q1321905","display_name":"Reinforcement","level":2,"score":0.4341937303543091},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.35206103324890137},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3484461307525635},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.1305667757987976},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.1156790554523468},{"id":"https://openalex.org/C77805123","wikidata":"https://www.wikidata.org/wiki/Q161272","display_name":"Social psychology","level":1,"score":0.052034586668014526},{"id":"https://openalex.org/C201995342","wikidata":"https://www.wikidata.org/wiki/Q682496","display_name":"Systems engineering","level":1,"score":0.051728278398513794}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1145/3543507.3583467","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3543507.3583467","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the ACM Web Conference 2023","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2302.03328","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2302.03328","pdf_url":"https://arxiv.org/pdf/2302.03328","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"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:2302.03328","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2302.03328","pdf_url":"https://arxiv.org/pdf/2302.03328","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"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":[{"display_name":"Partnerships for the goals","score":0.46000000834465027,"id":"https://metadata.un.org/sdg/17"}],"awards":[{"id":"https://openalex.org/G7271486925","display_name":null,"funder_award_id":"9360163","funder_id":"https://openalex.org/F4320309893","funder_display_name":"City University of Hong Kong"},{"id":"https://openalex.org/G8226490486","display_name":null,"funder_award_id":"9360163","funder_id":"https://openalex.org/F4320334123","funder_display_name":"Hong Kong Institute for Data Science"}],"funders":[{"id":"https://openalex.org/F4320309893","display_name":"City University of Hong Kong","ror":"https://ror.org/03q8dnn23"},{"id":"https://openalex.org/F4320318398","display_name":"Ant Group","ror":null},{"id":"https://openalex.org/F4320319065","display_name":"Aromatic Plant Research Center","ror":"https://ror.org/05eebgw43"},{"id":"https://openalex.org/F4320334123","display_name":"Hong Kong Institute for Data Science","ror":null}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4319653664.pdf","grobid_xml":"https://content.openalex.org/works/W4319653664.grobid-xml"},"referenced_works_count":69,"referenced_works":["https://openalex.org/W41554520","https://openalex.org/W639708223","https://openalex.org/W1968563228","https://openalex.org/W2012516036","https://openalex.org/W2024390895","https://openalex.org/W2049655669","https://openalex.org/W2054141820","https://openalex.org/W2127480961","https://openalex.org/W2135263912","https://openalex.org/W2136602922","https://openalex.org/W2137063737","https://openalex.org/W2155027007","https://openalex.org/W2172968643","https://openalex.org/W2251324968","https://openalex.org/W2433963325","https://openalex.org/W2475334473","https://openalex.org/W2604662567","https://openalex.org/W2606089314","https://openalex.org/W2781763969","https://openalex.org/W2787933113","https://openalex.org/W2788295351","https://openalex.org/W2788728386","https://openalex.org/W2788953034","https://openalex.org/W2797234205","https://openalex.org/W2799125281","https://openalex.org/W2799544270","https://openalex.org/W2809290718","https://openalex.org/W2898273872","https://openalex.org/W2902572901","https://openalex.org/W2945488061","https://openalex.org/W2948345531","https://openalex.org/W2949462525","https://openalex.org/W2952505042","https://openalex.org/W2953132212","https://openalex.org/W2962989965","https://openalex.org/W2963619374","https://openalex.org/W2963842088","https://openalex.org/W2963842982","https://openalex.org/W2963877604","https://openalex.org/W2964112275","https://openalex.org/W2972956685","https://openalex.org/W2984869362","https://openalex.org/W3003416843","https://openalex.org/W3006456063","https://openalex.org/W3013433464","https://openalex.org/W3040094401","https://openalex.org/W3081310128","https://openalex.org/W3087931390","https://openalex.org/W3091467596","https://openalex.org/W3100538332","https://openalex.org/W3102363765","https://openalex.org/W3102778384","https://openalex.org/W3102899483","https://openalex.org/W3116249021","https://openalex.org/W3122507327","https://openalex.org/W3123348991","https://openalex.org/W3124675547","https://openalex.org/W3141797743","https://openalex.org/W3157410348","https://openalex.org/W4288110508","https://openalex.org/W4289488615","https://openalex.org/W4290827187","https://openalex.org/W4290927958","https://openalex.org/W4292419518","https://openalex.org/W4298380504","https://openalex.org/W4302313152","https://openalex.org/W4302570325","https://openalex.org/W4394672593","https://openalex.org/W6653708959"],"related_works":["https://openalex.org/W4310083477","https://openalex.org/W2328553770","https://openalex.org/W2920061524","https://openalex.org/W1977959518","https://openalex.org/W2038908348","https://openalex.org/W2107890255","https://openalex.org/W2106552856","https://openalex.org/W2145821588","https://openalex.org/W3196817267","https://openalex.org/W1976600725"],"abstract_inverted_index":{"In":[0],"recent":[1],"years,":[2],"Multi-task":[3],"Learning":[4,72],"(MTL)":[5],"has":[6,43],"yielded":[7],"immense":[8],"success":[9],"in":[10,48,58,65],"Recommender":[11],"System":[12],"(RS)":[13],"applications":[14],"[40].":[15],"However,":[16],"current":[17],"MTL-based":[18,124,160],"recommendation":[19,85,125,161],"models":[20],"tend":[21],"to":[22,79],"disregard":[23],"the":[24,81,93,98,132,137,150],"session-wise":[25,109],"patterns":[26],"of":[27,83,152],"user-item":[28],"interactions":[29,110],"because":[30],"they":[31],"are":[32],"predominantly":[33],"constructed":[34],"based":[35],"on":[36,144],"item-wise":[37],"datasets.":[38],"Moreover,":[39],"balancing":[40],"multiple":[41],"objectives":[42],"always":[44],"been":[45],"a":[46,70,155],"challenge":[47],"this":[49,66],"field,":[50],"which":[51,118],"is":[52,119],"typically":[53],"avoided":[54],"via":[55],"linear":[56],"estimations":[57],"existing":[59,123],"works.":[60],"To":[61,90],"address":[62,97],"these":[63],"issues,":[64],"paper,":[67],"we":[68,164],"propose":[69],"Reinforcement":[71],"(RL)":[73],"enhanced":[74],"MTL":[75,106,133,174],"framework,":[76],"namely":[77],"RMTL,":[78],"combine":[80],"losses":[82],"different":[84],"tasks":[86],"using":[87,136],"dynamic":[88],"weights.":[89],"be":[91],"specific,":[92],"RMTL":[94,153],"structure":[95],"can":[96],"two":[99,145],"aforementioned":[100],"issues":[101],"by":[102,140],"(i)":[103],"constructing":[104],"an":[105],"environment":[107],"from":[108],"and":[111,127,130,166,170],"(ii)":[112],"training":[113],"multi-task":[114],"actor-critic":[115],"network":[116],"structure,":[117],"compatible":[120],"with":[121,154],"most":[122],"models,":[126],"(iii)":[128],"optimizing":[129],"fine-tuning":[131],"loss":[134],"function":[135],"weights":[138],"generated":[139],"critic":[141],"networks.":[142],"Experiments":[143],"real-world":[146],"public":[147],"datasets":[148],"demonstrate":[149],"effectiveness":[151],"higher":[156],"AUC":[157],"against":[158],"state-of-the-art":[159],"models.":[162,175],"Additionally,":[163],"evaluate":[165],"validate":[167],"RMTL\u2019s":[168],"compatibility":[169],"transferability":[171],"across":[172],"various":[173]},"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2025,"cited_by_count":17},{"year":2024,"cited_by_count":17},{"year":2023,"cited_by_count":5}],"updated_date":"2026-04-28T14:05:53.105641","created_date":"2025-10-10T00:00:00"}