{"id":"https://openalex.org/W3154925836","doi":"https://doi.org/10.1145/3442381.3449846","title":"Reinforcement Recommendation with User Multi-aspect Preference","display_name":"Reinforcement Recommendation with User Multi-aspect Preference","publication_year":2021,"publication_date":"2021-04-19","ids":{"openalex":"https://openalex.org/W3154925836","doi":"https://doi.org/10.1145/3442381.3449846","mag":"3154925836"},"language":"en","primary_location":{"id":"doi:10.1145/3442381.3449846","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3442381.3449846","pdf_url":null,"source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Web Conference 2021","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://doi.org/10.1145/3442381.3449846","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5101755392","display_name":"Xu Chen","orcid":"https://orcid.org/0000-0003-0144-1775"},"institutions":[{"id":"https://openalex.org/I78988378","display_name":"Renmin University of China","ror":"https://ror.org/041pakw92","country_code":"CN","type":"education","lineage":["https://openalex.org/I78988378"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Xu Chen","raw_affiliation_strings":["Renmin University of China, China"],"affiliations":[{"raw_affiliation_string":"Renmin University of China, China","institution_ids":["https://openalex.org/I78988378"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5002080576","display_name":"Yali Du","orcid":"https://orcid.org/0000-0001-5683-2621"},"institutions":[{"id":"https://openalex.org/I45129253","display_name":"University College London","ror":"https://ror.org/02jx3x895","country_code":"GB","type":"education","lineage":["https://openalex.org/I124357947","https://openalex.org/I45129253"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Yali Du","raw_affiliation_strings":["University College London, United Kingdom"],"affiliations":[{"raw_affiliation_string":"University College London, United Kingdom","institution_ids":["https://openalex.org/I45129253"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5103251082","display_name":"Long Xia","orcid":"https://orcid.org/0000-0003-2580-6206"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Long Xia","raw_affiliation_strings":["York University, China"],"affiliations":[{"raw_affiliation_string":"York University, China","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100384727","display_name":"Jun Wang","orcid":"https://orcid.org/0000-0002-4021-4228"},"institutions":[{"id":"https://openalex.org/I45129253","display_name":"University College London","ror":"https://ror.org/02jx3x895","country_code":"GB","type":"education","lineage":["https://openalex.org/I124357947","https://openalex.org/I45129253"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Jun Wang","raw_affiliation_strings":["University College London, United Kingdom"],"affiliations":[{"raw_affiliation_string":"University College London, United Kingdom","institution_ids":["https://openalex.org/I45129253"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5101755392"],"corresponding_institution_ids":["https://openalex.org/I78988378"],"apc_list":null,"apc_paid":null,"fwci":4.2652,"has_fulltext":true,"cited_by_count":17,"citation_normalized_percentile":{"value":0.94503278,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":94,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"425","last_page":"435"},"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/T11161","display_name":"Consumer Market Behavior and Pricing","score":0.9941999912261963,"subfield":{"id":"https://openalex.org/subfields/1406","display_name":"Marketing"},"field":{"id":"https://openalex.org/fields/14","display_name":"Business, Management and Accounting"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},{"id":"https://openalex.org/T12101","display_name":"Advanced Bandit Algorithms Research","score":0.9894000291824341,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7085616588592529},{"id":"https://openalex.org/keywords/reinforcement","display_name":"Reinforcement","score":0.6944119334220886},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.6868101954460144},{"id":"https://openalex.org/keywords/preference","display_name":"Preference","score":0.6507581472396851},{"id":"https://openalex.org/keywords/human\u2013computer-interaction","display_name":"Human\u2013computer interaction","score":0.4213869571685791},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.25726616382598877},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.10725107789039612},{"id":"https://openalex.org/keywords/structural-engineering","display_name":"Structural engineering","score":0.05080804228782654},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.04760080575942993}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7085616588592529},{"id":"https://openalex.org/C67203356","wikidata":"https://www.wikidata.org/wiki/Q1321905","display_name":"Reinforcement","level":2,"score":0.6944119334220886},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.6868101954460144},{"id":"https://openalex.org/C2781249084","wikidata":"https://www.wikidata.org/wiki/Q908656","display_name":"Preference","level":2,"score":0.6507581472396851},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.4213869571685791},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.25726616382598877},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.10725107789039612},{"id":"https://openalex.org/C66938386","wikidata":"https://www.wikidata.org/wiki/Q633538","display_name":"Structural engineering","level":1,"score":0.05080804228782654},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.04760080575942993},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1145/3442381.3449846","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3442381.3449846","pdf_url":null,"source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Web Conference 2021","raw_type":"proceedings-article"},{"id":"pmh:oai:eprints.ucl.ac.uk.OAI2:10130485","is_oa":true,"landing_page_url":"https://discovery.ucl.ac.uk/id/eprint/10130485/","pdf_url":"https://discovery.ucl.ac.uk/10130485/1/3442381.3449846.pdf","source":{"id":"https://openalex.org/S4306400024","display_name":"UCL Discovery (University College London)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I45129253","host_organization_name":"University College London","host_organization_lineage":["https://openalex.org/I45129253"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"     In:  WWW '21: Proceedings of the Web Conference 2021.  (pp. pp. 425-435).  ACM: Association for Computing Machinery: New York, NY, USA. (2021)     ","raw_type":"Proceedings paper"}],"best_oa_location":{"id":"doi:10.1145/3442381.3449846","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3442381.3449846","pdf_url":null,"source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Web Conference 2021","raw_type":"proceedings-article"},"sustainable_development_goals":[{"score":0.4699999988079071,"id":"https://metadata.un.org/sdg/9","display_name":"Industry, innovation and infrastructure"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":23,"referenced_works":["https://openalex.org/W2152184085","https://openalex.org/W2165150801","https://openalex.org/W2605350416","https://openalex.org/W2626454364","https://openalex.org/W2787933113","https://openalex.org/W2788295351","https://openalex.org/W2795688094","https://openalex.org/W2798908418","https://openalex.org/W2799544270","https://openalex.org/W2950673314","https://openalex.org/W2951336455","https://openalex.org/W2963561234","https://openalex.org/W2963601856","https://openalex.org/W2963842088","https://openalex.org/W2970470314","https://openalex.org/W2984869362","https://openalex.org/W2996959725","https://openalex.org/W3040127368","https://openalex.org/W3096311269","https://openalex.org/W3102619277","https://openalex.org/W3102778384","https://openalex.org/W3102899483","https://openalex.org/W3105787366"],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2899084033","https://openalex.org/W2748952813","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"],"abstract_inverted_index":{"Formulating":[0],"recommender":[1,66],"system":[2],"with":[3,32,87,107,126],"reinforcement":[4],"learning":[5,157],"(RL)":[6],"frameworks":[7],"has":[8],"attracted":[9],"increasing":[10],"attention":[11],"from":[12],"both":[13],"academic":[14],"and":[15,45,130,155,174],"industry":[16],"communities.":[17],"While":[18],"many":[19],"promising":[20],"results":[21],"have":[22],"been":[23],"achieved,":[24],"existing":[25],"models":[26],"mostly":[27],"simulate":[28],"the":[29,39,47,62,75,101,119,132,135,153,161,171,182,196],"environment":[30],"reward":[31],"a":[33,127,144,177],"unified":[34],"value,":[35],"which":[36,82,147,188],"may":[37,105],"hinder":[38],"understanding":[40],"of":[41,64,77,185],"users\u2019":[42],"complex":[43],"preferences":[44,60,98],"limit":[46],"model":[48,57,73,197],"performance.":[49,198],"In":[50],"this":[51,112,186],"paper,":[52],"we":[53,70,114,164,175],"consider":[54],"how":[55],"to":[56,180,191,208],"user":[58,96],"multi-aspect":[59,97],"in":[61,85,100,170],"context":[63],"RL-based":[65],"system.":[67],"More":[68],"specifically,":[69],"base":[71],"our":[72,210],"on":[74,160,204],"framework":[76],"deterministic":[78],"policy":[79],"gradient":[80,168],"(DPG),":[81],"is":[83,141,189],"effective":[84,193],"dealing":[86],"large":[88],"action":[89],"spaces.":[90],"A":[91],"major":[92],"challenge":[93],"for":[94,194],"modeling":[95],"lies":[99],"fact":[102],"that":[103],"they":[104],"contradict":[106],"each":[108,124],"other.":[109],"To":[110],"solve":[111],"problem,":[113],"introduce":[115],"Pareto":[116,139],"optimization":[117,140,172],"into":[118,152],"DPG":[120],"framework.":[121],"We":[122,199],"assign":[123],"aspect":[125],"tailored":[128],"critic,":[129],"all":[131],"critics":[133],"share":[134],"same":[136],"actor.":[137],"The":[138],"realized":[142],"by":[143],"gradient-based":[145],"method,":[146],"can":[148],"be":[149,192],"easily":[150],"integrated":[151],"actor":[154],"critic":[156],"process.":[158],"Based":[159],"designed":[162],"model,":[163],"theoretically":[165],"analyze":[166],"its":[167],"bias":[169],"process,":[173],"design":[176],"weight-reuse":[178],"mechanism":[179],"lower":[181],"upper":[183],"bound":[184],"bias,":[187],"shown":[190],"improving":[195],"conduct":[200],"extensive":[201],"experiments":[202],"based":[203],"three":[205],"real-world":[206],"datasets":[207],"demonstrate":[209],"model\u2019s":[211],"superiorities.":[212]},"counts_by_year":[{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":2},{"year":2023,"cited_by_count":7},{"year":2022,"cited_by_count":3},{"year":2021,"cited_by_count":3}],"updated_date":"2026-04-04T16:13:02.066488","created_date":"2025-10-10T00:00:00"}