{"id":"https://openalex.org/W3017289192","doi":"https://doi.org/10.1109/ijcnn48605.2020.9207010","title":"Knowledge-guided Deep Reinforcement Learning for Interactive Recommendation","display_name":"Knowledge-guided Deep Reinforcement Learning for Interactive Recommendation","publication_year":2020,"publication_date":"2020-07-01","ids":{"openalex":"https://openalex.org/W3017289192","doi":"https://doi.org/10.1109/ijcnn48605.2020.9207010","mag":"3017289192"},"language":"en","primary_location":{"id":"doi:10.1109/ijcnn48605.2020.9207010","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ijcnn48605.2020.9207010","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2020 International Joint Conference on Neural Networks (IJCNN)","raw_type":"proceedings-article"},"type":"article","indexed_in":["arxiv","crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2004.08068","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":null,"display_name":"Xiaocong Chen","orcid":null},"institutions":[{"id":"https://openalex.org/I31746571","display_name":"UNSW Sydney","ror":"https://ror.org/03r8z3t63","country_code":"AU","type":"education","lineage":["https://openalex.org/I31746571"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Xiaocong Chen","raw_affiliation_strings":["School of Computer Science and Engineering, University of New South Wales, Australia"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Computer Science and Engineering, University of New South Wales, Australia","institution_ids":["https://openalex.org/I31746571"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Chaoran Huang","orcid":null},"institutions":[{"id":"https://openalex.org/I31746571","display_name":"UNSW Sydney","ror":"https://ror.org/03r8z3t63","country_code":"AU","type":"education","lineage":["https://openalex.org/I31746571"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Chaoran Huang","raw_affiliation_strings":["School of Computer Science and Engineering, University of New South Wales, Australia"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Computer Science and Engineering, University of New South Wales, Australia","institution_ids":["https://openalex.org/I31746571"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Lina Yao","orcid":null},"institutions":[{"id":"https://openalex.org/I31746571","display_name":"UNSW Sydney","ror":"https://ror.org/03r8z3t63","country_code":"AU","type":"education","lineage":["https://openalex.org/I31746571"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Lina Yao","raw_affiliation_strings":["School of Computer Science and Engineering, University of New South Wales, Australia"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Computer Science and Engineering, University of New South Wales, Australia","institution_ids":["https://openalex.org/I31746571"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Xianzhi Wang","orcid":null},"institutions":[{"id":"https://openalex.org/I114017466","display_name":"University of Technology Sydney","ror":"https://ror.org/03f0f6041","country_code":"AU","type":"education","lineage":["https://openalex.org/I114017466"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Xianzhi Wang","raw_affiliation_strings":["School of Computer Science, University of Technology Sydney, Australia"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Computer Science, University of Technology Sydney, Australia","institution_ids":["https://openalex.org/I114017466"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Wei liu","orcid":null},"institutions":[{"id":"https://openalex.org/I31746571","display_name":"UNSW Sydney","ror":"https://ror.org/03r8z3t63","country_code":"AU","type":"education","lineage":["https://openalex.org/I31746571"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Wei liu","raw_affiliation_strings":["School of Computer Science and Engineering, University of New South Wales, Australia"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Computer Science and Engineering, University of New South Wales, Australia","institution_ids":["https://openalex.org/I31746571"]}]},{"author_position":"last","author":{"id":null,"display_name":"Wenjie Zhang","orcid":null},"institutions":[{"id":"https://openalex.org/I31746571","display_name":"UNSW Sydney","ror":"https://ror.org/03r8z3t63","country_code":"AU","type":"education","lineage":["https://openalex.org/I31746571"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Wenjie Zhang","raw_affiliation_strings":["School of Computer Science and Engineering, University of New South Wales, Australia"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Computer Science and Engineering, University of New South Wales, Australia","institution_ids":["https://openalex.org/I31746571"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":5.7084,"has_fulltext":false,"cited_by_count":41,"citation_normalized_percentile":{"value":0.96253818,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":93,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"8"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10203","display_name":"Recommender Systems and Techniques","score":0.9991000294685364,"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":0.9991000294685364,"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":0.9990000128746033,"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/T11612","display_name":"Stochastic Gradient Optimization Techniques","score":0.968999981880188,"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":0.8420000076293945},{"id":"https://openalex.org/keywords/interactive-learning","display_name":"Interactive Learning","score":0.4814000129699707},{"id":"https://openalex.org/keywords/semantics","display_name":"Semantics (computer science)","score":0.4668999910354614},{"id":"https://openalex.org/keywords/reinforcement","display_name":"Reinforcement","score":0.40139999985694885},{"id":"https://openalex.org/keywords/deep-learning","display_name":"Deep learning","score":0.3384999930858612},{"id":"https://openalex.org/keywords/online-learning","display_name":"Online learning","score":0.3098999857902527}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.8420000076293945},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.761900007724762},{"id":"https://openalex.org/C2776716048","wikidata":"https://www.wikidata.org/wiki/Q6045290","display_name":"Interactive Learning","level":2,"score":0.4814000129699707},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4691999852657318},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.4668999910354614},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.44690001010894775},{"id":"https://openalex.org/C67203356","wikidata":"https://www.wikidata.org/wiki/Q1321905","display_name":"Reinforcement","level":2,"score":0.40139999985694885},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.3384999930858612},{"id":"https://openalex.org/C2986087404","wikidata":"https://www.wikidata.org/wiki/Q15946010","display_name":"Online learning","level":2,"score":0.3098999857902527},{"id":"https://openalex.org/C2775924081","wikidata":"https://www.wikidata.org/wiki/Q55608371","display_name":"Control (management)","level":2,"score":0.3086000084877014},{"id":"https://openalex.org/C557471498","wikidata":"https://www.wikidata.org/wiki/Q554950","display_name":"Recommender system","level":2,"score":0.29600000381469727},{"id":"https://openalex.org/C47932503","wikidata":"https://www.wikidata.org/wiki/Q5395689","display_name":"Error-driven learning","level":3,"score":0.29580000042915344},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.2874000072479248}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/ijcnn48605.2020.9207010","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ijcnn48605.2020.9207010","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2020 International Joint Conference on Neural Networks (IJCNN)","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2004.08068","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2004.08068","pdf_url":"https://arxiv.org/pdf/2004.08068","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:2004.08068","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2004.08068","pdf_url":"https://arxiv.org/pdf/2004.08068","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":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":33,"referenced_works":["https://openalex.org/W2046376809","https://openalex.org/W2091780923","https://openalex.org/W2112420033","https://openalex.org/W2145339207","https://openalex.org/W2470873417","https://openalex.org/W2471222571","https://openalex.org/W2509893387","https://openalex.org/W2532022121","https://openalex.org/W2604942799","https://openalex.org/W2743159750","https://openalex.org/W2763015105","https://openalex.org/W2787933113","https://openalex.org/W2788295351","https://openalex.org/W2798385737","https://openalex.org/W2799544270","https://openalex.org/W2809162153","https://openalex.org/W2894370347","https://openalex.org/W2911778742","https://openalex.org/W2913560138","https://openalex.org/W2950275995","https://openalex.org/W2963367478","https://openalex.org/W2963619374","https://openalex.org/W2963911286","https://openalex.org/W4288083766","https://openalex.org/W4394672593","https://openalex.org/W6684921986","https://openalex.org/W6736274000","https://openalex.org/W6739901393","https://openalex.org/W6742449366","https://openalex.org/W6745946970","https://openalex.org/W6754582438","https://openalex.org/W6760331673","https://openalex.org/W6761783306"],"related_works":[],"abstract_inverted_index":{"Interactive":[0],"recommendation":[1,35],"aims":[2],"to":[3,12,48,77,85],"learn":[4],"from":[5],"dynamic":[6,25],"interactions":[7],"between":[8,89],"items":[9],"and":[10,15,27,56,80,106],"users":[11],"achieve":[13],"responsiveness":[14],"accuracy.":[16],"Reinforcement":[17,45],"learning":[18,46,55],"is":[19,64],"inherently":[20],"advantageous":[21],"for":[22,59],"coping":[23],"with":[24,101],"environments":[26],"thus":[28],"has":[29],"attracted":[30],"increasing":[31],"attention":[32,83],"in":[33,96],"interactive":[34,60],"research.":[36],"Inspired":[37],"by":[38],"knowledge-aware":[39],"recommendation,":[40],"we":[41],"proposed":[42],"Knowledge-Guided":[43],"deep":[44],"(KGRL)":[47],"harness":[49],"the":[50,67,82,108],"advantages":[51],"of":[52,110],"both":[53],"reinforcement":[54],"knowledge":[57,75],"graphs":[58],"recommendation.":[61],"This":[62],"model":[63,112],"implemented":[65],"upon":[66],"actor-critic":[68],"network":[69,76],"framework.":[70],"It":[71],"maintains":[72],"a":[73,97],"local":[74],"guide":[78],"decision-making":[79],"employs":[81],"mechanism":[84],"capture":[86],"long-term":[87],"semantics":[88],"items.":[90],"We":[91],"have":[92],"conducted":[93],"comprehensive":[94],"experiments":[95],"simulated":[98],"online":[99],"environment":[100],"six":[102],"public":[103],"real-world":[104],"datasets":[105],"demonstrated":[107],"superiority":[109],"our":[111],"over":[113],"several":[114],"state-of-the-art":[115],"methods.":[116]},"counts_by_year":[{"year":2026,"cited_by_count":3},{"year":2025,"cited_by_count":8},{"year":2024,"cited_by_count":9},{"year":2023,"cited_by_count":13},{"year":2022,"cited_by_count":6},{"year":2021,"cited_by_count":2}],"updated_date":"2026-07-03T08:13:44.112507","created_date":"2020-04-24T00:00:00"}