{"id":"https://openalex.org/W4385767983","doi":"https://doi.org/10.24963/ijcai.2023/273","title":"Towards Hierarchical Policy Learning for Conversational Recommendation with Hypergraph-based Reinforcement Learning","display_name":"Towards Hierarchical Policy Learning for Conversational Recommendation with Hypergraph-based Reinforcement Learning","publication_year":2023,"publication_date":"2023-08-01","ids":{"openalex":"https://openalex.org/W4385767983","doi":"https://doi.org/10.24963/ijcai.2023/273"},"language":"en","primary_location":{"id":"doi:10.24963/ijcai.2023/273","is_oa":true,"landing_page_url":"https://doi.org/10.24963/ijcai.2023/273","pdf_url":"https://www.ijcai.org/proceedings/2023/0273.pdf","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Thirty-Second International Joint Conference on Artificial Intelligence","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://www.ijcai.org/proceedings/2023/0273.pdf","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5101836987","display_name":"Sen Zhao","orcid":"https://orcid.org/0000-0003-3860-8647"},"institutions":[{"id":"https://openalex.org/I47720641","display_name":"Huazhong University of Science and Technology","ror":"https://ror.org/00p991c53","country_code":"CN","type":"education","lineage":["https://openalex.org/I47720641"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Sen Zhao","raw_affiliation_strings":["Cognitive Computing and Intelligent Information Processing (CCIIP) Laboratory, School of Computer Science and Technology, Huazhong University of Science and Technology","Joint Laboratory of HUST and Pingan Property & Casualty Research (HPL)","Cognitive Computing and Intelligent Information Processing (CCIIP) Laboratory, School of Computer Science and Technology, Huazhong University of Science and Technology; Joint Laboratory of HUST and Pingan Property & Casualty Research (HPL)"],"affiliations":[{"raw_affiliation_string":"Cognitive Computing and Intelligent Information Processing (CCIIP) Laboratory, School of Computer Science and Technology, Huazhong University of Science and Technology","institution_ids":["https://openalex.org/I47720641"]},{"raw_affiliation_string":"Joint Laboratory of HUST and Pingan Property & Casualty Research (HPL)","institution_ids":[]},{"raw_affiliation_string":"Cognitive Computing and Intelligent Information Processing (CCIIP) Laboratory, School of Computer Science and Technology, Huazhong University of Science and Technology; Joint Laboratory of HUST and Pingan Property & Casualty Research (HPL)","institution_ids":["https://openalex.org/I47720641"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100323842","display_name":"Wei Wei","orcid":"https://orcid.org/0000-0003-4488-0102"},"institutions":[{"id":"https://openalex.org/I47720641","display_name":"Huazhong University of Science and Technology","ror":"https://ror.org/00p991c53","country_code":"CN","type":"education","lineage":["https://openalex.org/I47720641"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Wei Wei","raw_affiliation_strings":["Cognitive Computing and Intelligent Information Processing (CCIIP) Laboratory, School of Computer Science and Technology, Huazhong University of Science and Technology","Joint Laboratory of HUST and Pingan Property & Casualty Research (HPL)","Cognitive Computing and Intelligent Information Processing (CCIIP) Laboratory, School of Computer Science and Technology, Huazhong University of Science and Technology; Joint Laboratory of HUST and Pingan Property & Casualty Research (HPL)"],"affiliations":[{"raw_affiliation_string":"Cognitive Computing and Intelligent Information Processing (CCIIP) Laboratory, School of Computer Science and Technology, Huazhong University of Science and Technology","institution_ids":["https://openalex.org/I47720641"]},{"raw_affiliation_string":"Joint Laboratory of HUST and Pingan Property & Casualty Research (HPL)","institution_ids":[]},{"raw_affiliation_string":"Cognitive Computing and Intelligent Information Processing (CCIIP) Laboratory, School of Computer Science and Technology, Huazhong University of Science and Technology; Joint Laboratory of HUST and Pingan Property & Casualty Research (HPL)","institution_ids":["https://openalex.org/I47720641"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100376156","display_name":"Yifan Liu","orcid":"https://orcid.org/0000-0002-7982-1455"},"institutions":[{"id":"https://openalex.org/I47720641","display_name":"Huazhong University of Science and Technology","ror":"https://ror.org/00p991c53","country_code":"CN","type":"education","lineage":["https://openalex.org/I47720641"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yifan Liu","raw_affiliation_strings":["Cognitive Computing and Intelligent Information Processing (CCIIP) Laboratory, School of Computer Science and Technology, Huazhong University of Science and Technology","Joint Laboratory of HUST and Pingan Property & Casualty Research (HPL)","Cognitive Computing and Intelligent Information Processing (CCIIP) Laboratory, School of Computer Science and Technology, Huazhong University of Science and Technology; Joint Laboratory of HUST and Pingan Property & Casualty Research (HPL)"],"affiliations":[{"raw_affiliation_string":"Cognitive Computing and Intelligent Information Processing (CCIIP) Laboratory, School of Computer Science and Technology, Huazhong University of Science and Technology","institution_ids":["https://openalex.org/I47720641"]},{"raw_affiliation_string":"Joint Laboratory of HUST and Pingan Property & Casualty Research (HPL)","institution_ids":[]},{"raw_affiliation_string":"Cognitive Computing and Intelligent Information Processing (CCIIP) Laboratory, School of Computer Science and Technology, Huazhong University of Science and Technology; Joint Laboratory of HUST and Pingan Property & Casualty Research (HPL)","institution_ids":["https://openalex.org/I47720641"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100348425","display_name":"Ziyang Wang","orcid":"https://orcid.org/0009-0006-4832-3345"},"institutions":[{"id":"https://openalex.org/I47720641","display_name":"Huazhong University of Science and Technology","ror":"https://ror.org/00p991c53","country_code":"CN","type":"education","lineage":["https://openalex.org/I47720641"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Ziyang Wang","raw_affiliation_strings":["Cognitive Computing and Intelligent Information Processing (CCIIP) Laboratory, School of Computer Science and Technology, Huazhong University of Science and Technology","Joint Laboratory of HUST and Pingan Property & Casualty Research (HPL)","Cognitive Computing and Intelligent Information Processing (CCIIP) Laboratory, School of Computer Science and Technology, Huazhong University of Science and Technology; Joint Laboratory of HUST and Pingan Property & Casualty Research (HPL)"],"affiliations":[{"raw_affiliation_string":"Cognitive Computing and Intelligent Information Processing (CCIIP) Laboratory, School of Computer Science and Technology, Huazhong University of Science and Technology","institution_ids":["https://openalex.org/I47720641"]},{"raw_affiliation_string":"Joint Laboratory of HUST and Pingan Property & Casualty Research (HPL)","institution_ids":[]},{"raw_affiliation_string":"Cognitive Computing and Intelligent Information Processing (CCIIP) Laboratory, School of Computer Science and Technology, Huazhong University of Science and Technology; Joint Laboratory of HUST and Pingan Property & Casualty Research (HPL)","institution_ids":["https://openalex.org/I47720641"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101683216","display_name":"Wendi Li","orcid":"https://orcid.org/0000-0001-9083-8824"},"institutions":[{"id":"https://openalex.org/I47720641","display_name":"Huazhong University of Science and Technology","ror":"https://ror.org/00p991c53","country_code":"CN","type":"education","lineage":["https://openalex.org/I47720641"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Wendi Li","raw_affiliation_strings":["Cognitive Computing and Intelligent Information Processing (CCIIP) Laboratory, School of Computer Science and Technology, Huazhong University of Science and Technology","Joint Laboratory of HUST and Pingan Property & Casualty Research (HPL)","Cognitive Computing and Intelligent Information Processing (CCIIP) Laboratory, School of Computer Science and Technology, Huazhong University of Science and Technology; Joint Laboratory of HUST and Pingan Property & Casualty Research (HPL)"],"affiliations":[{"raw_affiliation_string":"Cognitive Computing and Intelligent Information Processing (CCIIP) Laboratory, School of Computer Science and Technology, Huazhong University of Science and Technology","institution_ids":["https://openalex.org/I47720641"]},{"raw_affiliation_string":"Joint Laboratory of HUST and Pingan Property & Casualty Research (HPL)","institution_ids":[]},{"raw_affiliation_string":"Cognitive Computing and Intelligent Information Processing (CCIIP) Laboratory, School of Computer Science and Technology, Huazhong University of Science and Technology; Joint Laboratory of HUST and Pingan Property & Casualty Research (HPL)","institution_ids":["https://openalex.org/I47720641"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5017626590","display_name":"Xian-Ling Mao","orcid":"https://orcid.org/0000-0001-6795-2311"},"institutions":[{"id":"https://openalex.org/I125839683","display_name":"Beijing Institute of Technology","ror":"https://ror.org/01skt4w74","country_code":"CN","type":"education","lineage":["https://openalex.org/I125839683","https://openalex.org/I890469752"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xian-Ling Mao","raw_affiliation_strings":["School of Computer Science and Technology, Beijing Institute of Technology"],"affiliations":[{"raw_affiliation_string":"School of Computer Science and Technology, Beijing Institute of Technology","institution_ids":["https://openalex.org/I125839683"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101026934","display_name":"Shuai Zhu","orcid":"https://orcid.org/0000-0001-6970-0214"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Shuai Zhu","raw_affiliation_strings":["Ant Group"],"affiliations":[{"raw_affiliation_string":"Ant Group","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100438304","display_name":"Minghui Yang","orcid":"https://orcid.org/0000-0002-7435-0957"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Minghui Yang","raw_affiliation_strings":["Ant Group"],"affiliations":[{"raw_affiliation_string":"Ant Group","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5083773395","display_name":"Zujie Wen","orcid":"https://orcid.org/0000-0002-2771-1801"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zujie Wen","raw_affiliation_strings":["Ant Group"],"affiliations":[{"raw_affiliation_string":"Ant Group","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":9,"corresponding_author_ids":["https://openalex.org/A5101836987"],"corresponding_institution_ids":["https://openalex.org/I47720641"],"apc_list":null,"apc_paid":null,"fwci":3.2122,"has_fulltext":false,"cited_by_count":7,"citation_normalized_percentile":{"value":0.92990505,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"2459","last_page":"2467"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10203","display_name":"Recommender Systems and Techniques","score":0.9998000264167786,"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":0.9998000264167786,"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/T10028","display_name":"Topic Modeling","score":0.9973000288009644,"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/T11273","display_name":"Advanced Graph Neural Networks","score":0.9930999875068665,"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/computer-science","display_name":"Computer science","score":0.770868182182312},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.6161257028579712},{"id":"https://openalex.org/keywords/recommender-system","display_name":"Recommender system","score":0.6093400716781616},{"id":"https://openalex.org/keywords/heuristic","display_name":"Heuristic","score":0.5821345448493958},{"id":"https://openalex.org/keywords/categorical-variable","display_name":"Categorical variable","score":0.5731738209724426},{"id":"https://openalex.org/keywords/ask-price","display_name":"Ask price","score":0.5391355752944946},{"id":"https://openalex.org/keywords/hypergraph","display_name":"Hypergraph","score":0.4328545331954956},{"id":"https://openalex.org/keywords/space","display_name":"Space (punctuation)","score":0.4269734025001526},{"id":"https://openalex.org/keywords/action","display_name":"Action (physics)","score":0.4262406826019287},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4062032401561737},{"id":"https://openalex.org/keywords/human\u2013computer-interaction","display_name":"Human\u2013computer interaction","score":0.37636613845825195},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.36208873987197876},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.0884166955947876}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.770868182182312},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.6161257028579712},{"id":"https://openalex.org/C557471498","wikidata":"https://www.wikidata.org/wiki/Q554950","display_name":"Recommender system","level":2,"score":0.6093400716781616},{"id":"https://openalex.org/C173801870","wikidata":"https://www.wikidata.org/wiki/Q201413","display_name":"Heuristic","level":2,"score":0.5821345448493958},{"id":"https://openalex.org/C5274069","wikidata":"https://www.wikidata.org/wiki/Q2285707","display_name":"Categorical variable","level":2,"score":0.5731738209724426},{"id":"https://openalex.org/C90329073","wikidata":"https://www.wikidata.org/wiki/Q914232","display_name":"Ask price","level":2,"score":0.5391355752944946},{"id":"https://openalex.org/C2781221856","wikidata":"https://www.wikidata.org/wiki/Q840247","display_name":"Hypergraph","level":2,"score":0.4328545331954956},{"id":"https://openalex.org/C2778572836","wikidata":"https://www.wikidata.org/wiki/Q380933","display_name":"Space (punctuation)","level":2,"score":0.4269734025001526},{"id":"https://openalex.org/C2780791683","wikidata":"https://www.wikidata.org/wiki/Q846785","display_name":"Action (physics)","level":2,"score":0.4262406826019287},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4062032401561737},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.37636613845825195},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.36208873987197876},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0884166955947876},{"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/C118615104","wikidata":"https://www.wikidata.org/wiki/Q121416","display_name":"Discrete mathematics","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/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","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/C136264566","wikidata":"https://www.wikidata.org/wiki/Q159810","display_name":"Economy","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.24963/ijcai.2023/273","is_oa":true,"landing_page_url":"https://doi.org/10.24963/ijcai.2023/273","pdf_url":"https://www.ijcai.org/proceedings/2023/0273.pdf","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Thirty-Second International Joint Conference on Artificial Intelligence","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.24963/ijcai.2023/273","is_oa":true,"landing_page_url":"https://doi.org/10.24963/ijcai.2023/273","pdf_url":"https://www.ijcai.org/proceedings/2023/0273.pdf","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Thirty-Second International Joint Conference on Artificial Intelligence","raw_type":"proceedings-article"},"sustainable_development_goals":[{"display_name":"Peace, Justice and strong institutions","id":"https://metadata.un.org/sdg/16","score":0.8199999928474426}],"awards":[],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"}],"has_content":{"grobid_xml":false,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4385767983.pdf"},"referenced_works_count":29,"referenced_works":["https://openalex.org/W2120087366","https://openalex.org/W2127795553","https://openalex.org/W2139612737","https://openalex.org/W2349436533","https://openalex.org/W2746553466","https://openalex.org/W2798914047","https://openalex.org/W2805516822","https://openalex.org/W2889583850","https://openalex.org/W2892880750","https://openalex.org/W2952215380","https://openalex.org/W2953070460","https://openalex.org/W2964112275","https://openalex.org/W2964199361","https://openalex.org/W2966720510","https://openalex.org/W2970236742","https://openalex.org/W2970799419","https://openalex.org/W2997662139","https://openalex.org/W3035355914","https://openalex.org/W3080122044","https://openalex.org/W3100790518","https://openalex.org/W3152509363","https://openalex.org/W3153059551","https://openalex.org/W4200098598","https://openalex.org/W4224312735","https://openalex.org/W4224983022","https://openalex.org/W4225680488","https://openalex.org/W4225868472","https://openalex.org/W4323543183","https://openalex.org/W4385245566"],"related_works":["https://openalex.org/W4376608589","https://openalex.org/W1537073411","https://openalex.org/W1948107826","https://openalex.org/W3138003926","https://openalex.org/W1630514295","https://openalex.org/W4300037846","https://openalex.org/W4288275998","https://openalex.org/W2963081352","https://openalex.org/W4376608938","https://openalex.org/W2472555608"],"abstract_inverted_index":{"Conversational":[0,127],"recommendation":[1],"systems":[2],"(CRS)":[3],"aim":[4],"to":[5,41,68,79,102,156,165,174],"timely":[6],"and":[7,59,63,160,189],"proactively":[8],"acquire":[9],"user":[10,61,148,158],"dynamic":[11,154],"preferred":[12],"attributes":[13],"through":[14],"conversations":[15],"for":[16,54],"item":[17],"recommendation.":[18],"In":[19],"each":[20,35],"turn":[21],"of":[22,83,106,179],"CRS,":[23],"there":[24],"naturally":[25],"have":[26],"two":[27],"decision-making":[28,95],"processes":[29],"with":[30],"different":[31,107],"roles":[32,105],"that":[33,50,146,205],"influence":[34,185],"other:":[36],"1)":[37],"director,":[38],"which":[39,66],"is":[40,51,67],"select":[42],"the":[43,56,81,84,104,113,131,134,140,171,176,183,187,193],"follow-up":[44],"option":[45,195],"(i.e.,":[46,73],"ask":[47],"or":[48,76,97],"recommend)":[49],"more":[52],"effective":[53,136],"reducing":[55],"action":[57],"space":[58],"acquiring":[60],"preferences;":[62],"2)":[64],"actor,":[65,190],"accordingly":[69,142],"choose":[70],"primitive":[71,144],"actions":[72,145],"asked":[74],"attribute":[75],"recommended":[77],"item)":[78],"estimate":[80],"effectiveness":[82],"director\u2019s":[85,194],"option.":[86],"However,":[87],"existing":[88],"methods":[89],"heavily":[90],"rely":[91],"on":[92,182],"a":[93,123,153,199],"unified":[94],"module":[96],"heuristic":[98],"rules,":[99],"while":[100],"neglecting":[101],"distinguish":[103],"decision":[108],"procedures,":[109],"as":[110,112],"well":[111],"mutual":[114,184],"influences":[115],"between":[116,186],"them.":[117],"To":[118],"address":[119],"this,":[120],"we":[121,151,191],"propose":[122],"novel":[124],"Director-Actor":[125],"Hierarchical":[126],"Recommender":[128],"(DAHCR),":[129],"where":[130],"director":[132,188],"selects":[133],"most":[135],"option,":[137],"followed":[138],"by":[139,196],"actor":[141],"choosing":[143],"satisfy":[147],"preferences.":[149],"Specifically,":[150],"develop":[152],"hypergraph":[155],"model":[157,180,192],"preferences":[159],"introduce":[161],"an":[162],"intrinsic":[163],"motivation":[164],"train":[166],"from":[167,198],"weak":[168],"supervision":[169],"over":[170],"director.":[172],"Finally,":[173],"alleviate":[175],"bad":[177],"effect":[178],"bias":[181],"sampling":[197],"categorical":[200],"distribution.":[201],"Extensive":[202],"experiments":[203],"demonstrate":[204],"DAHCR":[206],"outperforms":[207],"state-of-the-art":[208],"methods.":[209]},"counts_by_year":[{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":4},{"year":2023,"cited_by_count":1}],"updated_date":"2025-12-21T01:58:51.020947","created_date":"2025-10-10T00:00:00"}