{"id":"https://openalex.org/W2921693870","doi":"https://doi.org/10.1145/3503181.3503203","title":"Diversity-Promoting Deep Reinforcement Learning for Interactive Recommendation","display_name":"Diversity-Promoting Deep Reinforcement Learning for Interactive Recommendation","publication_year":2021,"publication_date":"2021-10-16","ids":{"openalex":"https://openalex.org/W2921693870","doi":"https://doi.org/10.1145/3503181.3503203","mag":"2921693870"},"language":"en","primary_location":{"id":"doi:10.1145/3503181.3503203","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3503181.3503203","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"5th International Conference on Crowd Science and Engineering","raw_type":"proceedings-article"},"type":"preprint","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/A5072988055","display_name":"Yong Liu","orcid":"https://orcid.org/0000-0001-9031-9696"},"institutions":[{"id":"https://openalex.org/I172675005","display_name":"Nanyang Technological University","ror":"https://ror.org/02e7b5302","country_code":"SG","type":"education","lineage":["https://openalex.org/I172675005"]}],"countries":["SG"],"is_corresponding":true,"raw_author_name":"Yong Liu","raw_affiliation_strings":["Joint NTU-UBC Research Centre of Excellence in Active Living for the Elderly (LILY), Nanyang Technological University, Singapore"],"affiliations":[{"raw_affiliation_string":"Joint NTU-UBC Research Centre of Excellence in Active Living for the Elderly (LILY), Nanyang Technological University, Singapore","institution_ids":["https://openalex.org/I172675005"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101789458","display_name":"Zhiqi Shen","orcid":"https://orcid.org/0000-0001-7626-7295"},"institutions":[{"id":"https://openalex.org/I172675005","display_name":"Nanyang Technological University","ror":"https://ror.org/02e7b5302","country_code":"SG","type":"education","lineage":["https://openalex.org/I172675005"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Zhiqi Shen","raw_affiliation_strings":["School of Computer Science and Engineering, Nanyang Technological University, Singapore"],"affiliations":[{"raw_affiliation_string":"School of Computer Science and Engineering, Nanyang Technological University, Singapore","institution_ids":["https://openalex.org/I172675005"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100426662","display_name":"Yinan Zhang","orcid":"https://orcid.org/0000-0002-0357-3926"},"institutions":[{"id":"https://openalex.org/I172675005","display_name":"Nanyang Technological University","ror":"https://ror.org/02e7b5302","country_code":"SG","type":"education","lineage":["https://openalex.org/I172675005"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Yinan Zhang","raw_affiliation_strings":["School of Computer Science and Engineering, Nanyang Technological University, Singapore"],"affiliations":[{"raw_affiliation_string":"School of Computer Science and Engineering, Nanyang Technological University, Singapore","institution_ids":["https://openalex.org/I172675005"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5101414718","display_name":"Lizhen Cui","orcid":"https://orcid.org/0000-0002-8262-8883"},"institutions":[{"id":"https://openalex.org/I154099455","display_name":"Shandong University","ror":"https://ror.org/0207yh398","country_code":"CN","type":"education","lineage":["https://openalex.org/I154099455"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Lizhen Cui","raw_affiliation_strings":["Joint SDU-NTU Centre for Artificial Intelligence Research (C-FAIR) & School of Software, Shandong University, China"],"affiliations":[{"raw_affiliation_string":"Joint SDU-NTU Centre for Artificial Intelligence Research (C-FAIR) & School of Software, Shandong University, China","institution_ids":["https://openalex.org/I154099455"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5072988055"],"corresponding_institution_ids":["https://openalex.org/I172675005"],"apc_list":null,"apc_paid":null,"fwci":2.79732729,"has_fulltext":false,"cited_by_count":22,"citation_normalized_percentile":{"value":0.90051084,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":90,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"132","last_page":"139"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12101","display_name":"Advanced Bandit Algorithms Research","score":0.9991000294685364,"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":0.9991000294685364,"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/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9945999979972839,"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":0.9753000140190125,"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/recommender-system","display_name":"Recommender system","score":0.8140811920166016},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.7933264970779419},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7915040254592896},{"id":"https://openalex.org/keywords/similarity","display_name":"Similarity (geometry)","score":0.6261277198791504},{"id":"https://openalex.org/keywords/diversity","display_name":"Diversity (politics)","score":0.5761982798576355},{"id":"https://openalex.org/keywords/relevance","display_name":"Relevance (law)","score":0.5744971036911011},{"id":"https://openalex.org/keywords/determinantal-point-process","display_name":"Determinantal point process","score":0.5729514360427856},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.5470690131187439},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4990730285644531},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.487265944480896},{"id":"https://openalex.org/keywords/focus","display_name":"Focus (optics)","score":0.47870874404907227},{"id":"https://openalex.org/keywords/kernel","display_name":"Kernel (algebra)","score":0.4781004786491394},{"id":"https://openalex.org/keywords/interactive-learning","display_name":"Interactive Learning","score":0.4580816626548767},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.3331829905509949},{"id":"https://openalex.org/keywords/world-wide-web","display_name":"World Wide Web","score":0.23583203554153442}],"concepts":[{"id":"https://openalex.org/C557471498","wikidata":"https://www.wikidata.org/wiki/Q554950","display_name":"Recommender system","level":2,"score":0.8140811920166016},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.7933264970779419},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7915040254592896},{"id":"https://openalex.org/C103278499","wikidata":"https://www.wikidata.org/wiki/Q254465","display_name":"Similarity (geometry)","level":3,"score":0.6261277198791504},{"id":"https://openalex.org/C2781316041","wikidata":"https://www.wikidata.org/wiki/Q1230584","display_name":"Diversity (politics)","level":2,"score":0.5761982798576355},{"id":"https://openalex.org/C158154518","wikidata":"https://www.wikidata.org/wiki/Q7310970","display_name":"Relevance (law)","level":2,"score":0.5744971036911011},{"id":"https://openalex.org/C72010251","wikidata":"https://www.wikidata.org/wiki/Q5265688","display_name":"Determinantal point process","level":4,"score":0.5729514360427856},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.5470690131187439},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4990730285644531},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.487265944480896},{"id":"https://openalex.org/C192209626","wikidata":"https://www.wikidata.org/wiki/Q190909","display_name":"Focus (optics)","level":2,"score":0.47870874404907227},{"id":"https://openalex.org/C74193536","wikidata":"https://www.wikidata.org/wiki/Q574844","display_name":"Kernel (algebra)","level":2,"score":0.4781004786491394},{"id":"https://openalex.org/C2776716048","wikidata":"https://www.wikidata.org/wiki/Q6045290","display_name":"Interactive Learning","level":2,"score":0.4580816626548767},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.3331829905509949},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.23583203554153442},{"id":"https://openalex.org/C64812099","wikidata":"https://www.wikidata.org/wiki/Q176604","display_name":"Random matrix","level":3,"score":0.0},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.0},{"id":"https://openalex.org/C19165224","wikidata":"https://www.wikidata.org/wiki/Q23404","display_name":"Anthropology","level":1,"score":0.0},{"id":"https://openalex.org/C199539241","wikidata":"https://www.wikidata.org/wiki/Q7748","display_name":"Law","level":1,"score":0.0},{"id":"https://openalex.org/C114614502","wikidata":"https://www.wikidata.org/wiki/Q76592","display_name":"Combinatorics","level":1,"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/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C17744445","wikidata":"https://www.wikidata.org/wiki/Q36442","display_name":"Political science","level":0,"score":0.0},{"id":"https://openalex.org/C158693339","wikidata":"https://www.wikidata.org/wiki/Q190524","display_name":"Eigenvalues and eigenvectors","level":2,"score":0.0},{"id":"https://openalex.org/C144024400","wikidata":"https://www.wikidata.org/wiki/Q21201","display_name":"Sociology","level":0,"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/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0},{"id":"https://openalex.org/C120665830","wikidata":"https://www.wikidata.org/wiki/Q14620","display_name":"Optics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3503181.3503203","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3503181.3503203","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"5th International Conference on Crowd Science and Engineering","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/17","score":0.4300000071525574,"display_name":"Partnerships for the goals"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":37,"referenced_works":["https://openalex.org/W2008886893","https://openalex.org/W2029604041","https://openalex.org/W2049874054","https://openalex.org/W2063871698","https://openalex.org/W2083305840","https://openalex.org/W2097951507","https://openalex.org/W2112420033","https://openalex.org/W2121863487","https://openalex.org/W2138779671","https://openalex.org/W2140310134","https://openalex.org/W2159155347","https://openalex.org/W2173248099","https://openalex.org/W2182342230","https://openalex.org/W2187580259","https://openalex.org/W2400213106","https://openalex.org/W2400255467","https://openalex.org/W2508625104","https://openalex.org/W2576271642","https://openalex.org/W2586601519","https://openalex.org/W2604639157","https://openalex.org/W2604822632","https://openalex.org/W2744446984","https://openalex.org/W2783272285","https://openalex.org/W2787933113","https://openalex.org/W2788295351","https://openalex.org/W2799544270","https://openalex.org/W2803794535","https://openalex.org/W2963619374","https://openalex.org/W2997672513","https://openalex.org/W3035705826","https://openalex.org/W3102778384","https://openalex.org/W3102899483","https://openalex.org/W3103014337","https://openalex.org/W3115040029","https://openalex.org/W3122507327","https://openalex.org/W3138773240","https://openalex.org/W3159868125"],"related_works":["https://openalex.org/W2161485269","https://openalex.org/W4319083788","https://openalex.org/W1995247875","https://openalex.org/W4287695425","https://openalex.org/W2073555250","https://openalex.org/W2944402528","https://openalex.org/W3186475613","https://openalex.org/W2165159668","https://openalex.org/W2165981566","https://openalex.org/W1730245467"],"abstract_inverted_index":{"The":[0],"interactive":[1,26,73],"recommendation":[2,27,33,43,49,58,74],"systems":[3],"have":[4,138],"recently":[5],"attracted":[6],"lots":[7],"of":[8,42,48,72,118,132],"research":[9],"attentions,":[10],"because":[11],"they":[12,36],"can":[13],"model":[14],"the":[15,18,21,46,70,78,116,130,133],"interactions":[16],"between":[17],"user":[19],"and":[20,115],"recommender":[22],"system.":[23],"Most":[24],"previous":[25],"methods":[28],"only":[29],"focus":[30],"on":[31],"optimizing":[32],"accuracy.":[34],"However,":[35],"usually":[37],"overlook":[38],"other":[39],"important":[40],"aspects":[41],"quality,":[44],"e.g.,":[45],"diversity":[47,71],"results.":[50,75],"In":[51,76],"this":[52],"work,":[53],"we":[54,137],"propose":[55],"a":[56,95,108],"novel":[57],"framework,":[59],"called":[60],"Diversity-promoting":[61],"Deep":[62],"Reinforcement":[63],"Learning":[64],"(D2RL),":[65],"which":[66,102],"aims":[67],"to":[68,85],"promote":[69],"D2RL,":[77],"Determinantal":[79],"Point":[80],"Process":[81],"(DPP)":[82],"is":[83,100,103],"used":[84],"generate":[86],"diverse,":[87],"while":[88],"relevant":[89],"item":[90],"recommendations.":[91],"For":[92],"each":[93],"user,":[94],"personalized":[96],"DPP":[97],"kernel":[98],"matrix":[99,111],"maintained,":[101],"constructed":[104],"from":[105],"two":[106],"parts:":[107],"fixed":[109],"similarity":[110],"capturing":[112],"item-item":[113],"similarity,":[114],"relevance":[117],"items":[119],"dynamically":[120],"learnt":[121],"through":[122],"an":[123],"actor-critic":[124],"reinforcement":[125],"learning":[126],"framework.":[127],"To":[128],"demonstrate":[129],"effectiveness":[131],"proposed":[134],"D2RL":[135],"model,":[136],"performed":[139],"extensive":[140],"offline":[141],"experiments":[142,148],"as":[143,145],"well":[144],"simulated":[146],"online":[147],"with":[149],"real-world":[150],"datasets.":[151]},"counts_by_year":[{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":3},{"year":2023,"cited_by_count":3},{"year":2022,"cited_by_count":4},{"year":2021,"cited_by_count":6},{"year":2020,"cited_by_count":3},{"year":2019,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}