{"id":"https://openalex.org/W4285328726","doi":"https://doi.org/10.1145/3522596","title":"A Text-based Deep Reinforcement Learning Framework Using Self-supervised Graph Representation for Interactive Recommendation","display_name":"A Text-based Deep Reinforcement Learning Framework Using Self-supervised Graph Representation for Interactive Recommendation","publication_year":2021,"publication_date":"2021-11-30","ids":{"openalex":"https://openalex.org/W4285328726","doi":"https://doi.org/10.1145/3522596"},"language":"en","primary_location":{"id":"doi:10.1145/3522596","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3522596","pdf_url":null,"source":{"id":"https://openalex.org/S4210185969","display_name":"ACM/IMS Transactions on Data Science","issn_l":"2577-3224","issn":["2577-3224","2691-1922"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319798","host_organization_name":"Association for Computing Machinery","host_organization_lineage":["https://openalex.org/P4310319798"],"host_organization_lineage_names":["Association for Computing Machinery"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ACM/IMS Transactions on Data Science","raw_type":"journal-article"},"type":"article","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/A5100669681","display_name":"Chaoyang Wang","orcid":"https://orcid.org/0000-0003-4371-7514"},"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":"Chaoyang Wang","raw_affiliation_strings":["Huazhong University of Science and Technology, Wuhan, China"],"affiliations":[{"raw_affiliation_string":"Huazhong University of Science and Technology, Wuhan, China","institution_ids":["https://openalex.org/I47720641"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5007911614","display_name":"Zhiqiang Guo","orcid":"https://orcid.org/0000-0001-9393-4854"},"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":"Zhiqiang Guo","raw_affiliation_strings":["Huazhong University of Science and Technology, Wuhan, China"],"affiliations":[{"raw_affiliation_string":"Huazhong University of Science and Technology, Wuhan, China","institution_ids":["https://openalex.org/I47720641"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100605911","display_name":"Jianjun Li","orcid":"https://orcid.org/0000-0002-5265-7624"},"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":"Jianjun Li","raw_affiliation_strings":["Huazhong University of Science and Technology, Wuhan, China"],"affiliations":[{"raw_affiliation_string":"Huazhong University of Science and Technology, Wuhan, China","institution_ids":["https://openalex.org/I47720641"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100337866","display_name":"Guohui Li","orcid":"https://orcid.org/0000-0001-6984-1914"},"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":"Guohui Li","raw_affiliation_strings":["Huazhong University of Science and Technology, Wuhan, China"],"affiliations":[{"raw_affiliation_string":"Huazhong University of Science and Technology, Wuhan, China","institution_ids":["https://openalex.org/I47720641"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5059541904","display_name":"Peng Pan","orcid":"https://orcid.org/0000-0002-9598-2072"},"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":"Peng Pan","raw_affiliation_strings":["Huazhong University of Science and Technology, Wuhan, China"],"affiliations":[{"raw_affiliation_string":"Huazhong University of Science and Technology, Wuhan, China","institution_ids":["https://openalex.org/I47720641"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5100669681"],"corresponding_institution_ids":["https://openalex.org/I47720641"],"apc_list":null,"apc_paid":null,"fwci":0.8262,"has_fulltext":false,"cited_by_count":5,"citation_normalized_percentile":{"value":0.80746346,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":99},"biblio":{"volume":"2","issue":"4","first_page":"1","last_page":"25"},"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/T12101","display_name":"Advanced Bandit Algorithms Research","score":0.9912999868392944,"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/T10028","display_name":"Topic Modeling","score":0.9882000088691711,"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":0.8371841907501221},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7709056735038757},{"id":"https://openalex.org/keywords/leverage","display_name":"Leverage (statistics)","score":0.6414151191711426},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6340125799179077},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.5344701409339905},{"id":"https://openalex.org/keywords/embedding","display_name":"Embedding","score":0.517208456993103},{"id":"https://openalex.org/keywords/graph","display_name":"Graph","score":0.4865245223045349},{"id":"https://openalex.org/keywords/recommender-system","display_name":"Recommender system","score":0.4786038100719452},{"id":"https://openalex.org/keywords/feature-learning","display_name":"Feature learning","score":0.4272086024284363},{"id":"https://openalex.org/keywords/theoretical-computer-science","display_name":"Theoretical computer science","score":0.29612642526626587}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.8371841907501221},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7709056735038757},{"id":"https://openalex.org/C153083717","wikidata":"https://www.wikidata.org/wiki/Q6535263","display_name":"Leverage (statistics)","level":2,"score":0.6414151191711426},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6340125799179077},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.5344701409339905},{"id":"https://openalex.org/C41608201","wikidata":"https://www.wikidata.org/wiki/Q980509","display_name":"Embedding","level":2,"score":0.517208456993103},{"id":"https://openalex.org/C132525143","wikidata":"https://www.wikidata.org/wiki/Q141488","display_name":"Graph","level":2,"score":0.4865245223045349},{"id":"https://openalex.org/C557471498","wikidata":"https://www.wikidata.org/wiki/Q554950","display_name":"Recommender system","level":2,"score":0.4786038100719452},{"id":"https://openalex.org/C59404180","wikidata":"https://www.wikidata.org/wiki/Q17013334","display_name":"Feature learning","level":2,"score":0.4272086024284363},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.29612642526626587}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3522596","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3522596","pdf_url":null,"source":{"id":"https://openalex.org/S4210185969","display_name":"ACM/IMS Transactions on Data Science","issn_l":"2577-3224","issn":["2577-3224","2691-1922"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319798","host_organization_name":"Association for Computing Machinery","host_organization_lineage":["https://openalex.org/P4310319798"],"host_organization_lineage_names":["Association for Computing Machinery"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ACM/IMS Transactions on Data Science","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G5471023988","display_name":null,"funder_award_id":"61672252","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G7844923478","display_name":null,"funder_award_id":"2019kfyXKJC021","funder_id":"https://openalex.org/F4320335787","funder_display_name":"Fundamental Research Funds for the Central Universities"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"},{"id":"https://openalex.org/F4320335787","display_name":"Fundamental Research Funds for the Central Universities","ror":null}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":42,"referenced_works":["https://openalex.org/W1538021842","https://openalex.org/W1720514416","https://openalex.org/W2020631728","https://openalex.org/W2054141820","https://openalex.org/W2069870183","https://openalex.org/W2078455576","https://openalex.org/W2091780923","https://openalex.org/W2112420033","https://openalex.org/W2145339207","https://openalex.org/W2250539671","https://openalex.org/W2253995343","https://openalex.org/W2560674852","https://openalex.org/W2575006718","https://openalex.org/W2604314403","https://openalex.org/W2605350416","https://openalex.org/W2615497679","https://openalex.org/W2624407581","https://openalex.org/W2740384884","https://openalex.org/W2741274947","https://openalex.org/W2742657630","https://openalex.org/W2781763969","https://openalex.org/W2788295351","https://openalex.org/W2799544270","https://openalex.org/W2894196154","https://openalex.org/W2912834476","https://openalex.org/W2945827670","https://openalex.org/W2964108915","https://openalex.org/W2965512832","https://openalex.org/W2990130970","https://openalex.org/W3045200674","https://openalex.org/W3090447370","https://openalex.org/W3094605801","https://openalex.org/W3100278010","https://openalex.org/W3102778384","https://openalex.org/W3102899483","https://openalex.org/W3123956618","https://openalex.org/W3153325943","https://openalex.org/W4205171160","https://openalex.org/W4213245422","https://openalex.org/W4297808394","https://openalex.org/W4300868310","https://openalex.org/W4394672593"],"related_works":["https://openalex.org/W4390273403","https://openalex.org/W4386781444","https://openalex.org/W4246980185","https://openalex.org/W2150182025","https://openalex.org/W3092950680","https://openalex.org/W3197542405","https://openalex.org/W4238861846","https://openalex.org/W3125580266","https://openalex.org/W44246808","https://openalex.org/W2768698792"],"abstract_inverted_index":{"Due":[0],"to":[1,67,77,122,155,180,194,225],"its":[2],"nature":[3],"of":[4,28,59,165,172,187],"learning":[5,104,175],"from":[6,229],"dynamic":[7],"interactions":[8],"and":[9,125],"planning":[10],"for":[11,85,111],"long-run":[12],"performance,":[13],"Reinforcement":[14],"Learning":[15],"(RL)":[16],"has":[17],"attracted":[18],"much":[19],"attention":[20],"in":[21,93,250],"Interactive":[22],"Recommender":[23],"Systems":[24],"(IRSs).":[25],"However,":[26],"most":[27,52],"the":[29,139,163,166,184,203,230],"existing":[30,71],"RL-based":[31,72],"IRSs":[32,53],"usually":[33],"face":[34],"large":[35],"discrete":[36,227],"action":[37,158,167,185],"space":[38,131,168,186],"problem,":[39],"which":[40,143,161,220],"severely":[41],"limits":[42],"their":[43],"efficiency.":[44],"Moreover,":[45,149],"data":[46,146],"sparsity":[47,147],"is":[48,189,192],"another":[49],"problem":[50,66],"that":[51,242],"are":[54,82],"confronted":[55],"with.":[56],"The":[57],"utilization":[58],"recommendation-related":[60],"textual":[61,79,120],"knowledge":[62],"can":[63,221],"tackle":[64],"this":[65,94],"some":[68],"extent,":[69],"but":[70],"recommendation":[73],"methods":[74],"either":[75],"neglect":[76],"combine":[78],"information":[80,121],"or":[81],"not":[83],"suitable":[84],"incorporating":[86],"it.":[87],"To":[88],"address":[89],"these":[90],"two":[91],"problems,":[92],"article,":[95],"we":[96,118,150,215,240],"propose":[97],"a":[98,128,133,217,251],"T":[99],"ext-based":[100],"deep":[101],"R":[102,114],"einforcement":[103],"framework":[105],"using":[106],"self-supervised":[107,134],"G":[108],"raph":[109],"representation":[110],"I":[112],"nteractive":[113],"ecommendation":[115],"(TRGIR).":[116],"Specifically,":[117],"leverage":[119],"map":[123],"items":[124],"users":[126],"into":[127],"same":[129],"feature":[130],"by":[132],"embedding":[135],"method":[136,154],"based":[137],"on":[138,236],"graph":[140],"convolutional":[141],"network,":[142],"greatly":[144],"alleviates":[145],"problem.":[148],"design":[151,216],"an":[152,157],"effective":[153],"construct":[156],"candidate":[159,231],"set,":[160],"reduces":[162],"scale":[164],"directly.":[169],"Two":[170],"types":[171],"representative":[173],"reinforcement":[174],"algorithms":[176],"have":[177],"been":[178],"applied":[179],"implement":[181,195],"TRGIR.":[182],"Since":[183],"IRS":[188],"discrete,":[190],"it":[191],"natural":[193],"TRGIR":[196,204],"with":[197,206],"Deep":[198,207],"Q-learning":[199],"Network":[200],"(DQN).":[201],"In":[202],"implementation":[205],"Deterministic":[208],"Policy":[209],"Gradient":[210],"(DDPG),":[211],"denoted":[212],"as":[213],"TRGIR-DDPG,":[214],"policy":[218],"vector,":[219],"represent":[222],"user\u2019s":[223],"preferences,":[224],"generate":[226],"actions":[228],"set.":[232],"Through":[233],"extensive":[234],"experiments":[235],"three":[237],"public":[238],"datasets,":[239],"demonstrate":[241],"TRGIR-DDPG":[243],"achieves":[244],"state-of-the-art":[245],"performance":[246],"over":[247],"several":[248],"baselines":[249],"time-efficient":[252],"manner.":[253]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":1},{"year":2021,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}