{"id":"https://openalex.org/W3029587262","doi":"https://doi.org/10.1145/3397271.3401171","title":"Leveraging Demonstrations for Reinforcement Recommendation Reasoning over Knowledge Graphs","display_name":"Leveraging Demonstrations for Reinforcement Recommendation Reasoning over Knowledge Graphs","publication_year":2020,"publication_date":"2020-07-25","ids":{"openalex":"https://openalex.org/W3029587262","doi":"https://doi.org/10.1145/3397271.3401171","mag":"3029587262"},"language":"en","primary_location":{"id":"doi:10.1145/3397271.3401171","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3397271.3401171","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 43rd International ACM SIGIR Conference on Research and Development in Information Retrieval","raw_type":"proceedings-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/A5078879815","display_name":"Kangzhi Zhao","orcid":null},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Kangzhi Zhao","raw_affiliation_strings":["Tsinghua University, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Tsinghua University, Beijing, China","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101524540","display_name":"Xiting Wang","orcid":"https://orcid.org/0000-0001-5768-1095"},"institutions":[{"id":"https://openalex.org/I4210113369","display_name":"Microsoft Research Asia (China)","ror":"https://ror.org/0300m5276","country_code":"CN","type":"company","lineage":["https://openalex.org/I1290206253","https://openalex.org/I4210113369"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xiting Wang","raw_affiliation_strings":["Microsoft Research Asia, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Microsoft Research Asia, Beijing, China","institution_ids":["https://openalex.org/I4210113369"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5050281328","display_name":"Yuren Zhang","orcid":null},"institutions":[{"id":"https://openalex.org/I126520041","display_name":"University of Science and Technology of China","ror":"https://ror.org/04c4dkn09","country_code":"CN","type":"education","lineage":["https://openalex.org/I126520041","https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yuren Zhang","raw_affiliation_strings":["University of Science and Technology of China, Hefei, China"],"affiliations":[{"raw_affiliation_string":"University of Science and Technology of China, Hefei, China","institution_ids":["https://openalex.org/I126520041"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5032277491","display_name":"Zhao Li","orcid":"https://orcid.org/0000-0002-5056-0351"},"institutions":[{"id":"https://openalex.org/I4210113369","display_name":"Microsoft Research Asia (China)","ror":"https://ror.org/0300m5276","country_code":"CN","type":"company","lineage":["https://openalex.org/I1290206253","https://openalex.org/I4210113369"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Li Zhao","raw_affiliation_strings":["Microsoft Research Asia, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Microsoft Research Asia, Beijing, China","institution_ids":["https://openalex.org/I4210113369"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100423656","display_name":"Zheng Liu","orcid":"https://orcid.org/0000-0001-7765-8466"},"institutions":[{"id":"https://openalex.org/I4210113369","display_name":"Microsoft Research Asia (China)","ror":"https://ror.org/0300m5276","country_code":"CN","type":"company","lineage":["https://openalex.org/I1290206253","https://openalex.org/I4210113369"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zheng Liu","raw_affiliation_strings":["Microsoft Research Asia, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Microsoft Research Asia, Beijing, China","institution_ids":["https://openalex.org/I4210113369"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5058043497","display_name":"Chunxiao Xing","orcid":"https://orcid.org/0000-0001-9390-3097"},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Chunxiao Xing","raw_affiliation_strings":["Tsinghua University, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Tsinghua University, Beijing, China","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5044651577","display_name":"Xing Xie","orcid":"https://orcid.org/0000-0002-8608-8482"},"institutions":[{"id":"https://openalex.org/I4210113369","display_name":"Microsoft Research Asia (China)","ror":"https://ror.org/0300m5276","country_code":"CN","type":"company","lineage":["https://openalex.org/I1290206253","https://openalex.org/I4210113369"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xing Xie","raw_affiliation_strings":["Microsoft Research Asia, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Microsoft Research Asia, Beijing, China","institution_ids":["https://openalex.org/I4210113369"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":7,"corresponding_author_ids":["https://openalex.org/A5078879815"],"corresponding_institution_ids":["https://openalex.org/I99065089"],"apc_list":null,"apc_paid":null,"fwci":11.0025,"has_fulltext":false,"cited_by_count":114,"citation_normalized_percentile":{"value":0.98716192,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":96,"max":100},"biblio":{"volume":null,"issue":null,"first_page":"239","last_page":"248"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11273","display_name":"Advanced Graph Neural Networks","score":0.9998000264167786,"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"}},"topics":[{"id":"https://openalex.org/T11273","display_name":"Advanced Graph Neural Networks","score":0.9998000264167786,"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/T10028","display_name":"Topic Modeling","score":0.9988999962806702,"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":0.9987999796867371,"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/computer-science","display_name":"Computer science","score":0.8124535083770752},{"id":"https://openalex.org/keywords/leverage","display_name":"Leverage (statistics)","score":0.7514538764953613},{"id":"https://openalex.org/keywords/knowledge-graph","display_name":"Knowledge graph","score":0.6223940849304199},{"id":"https://openalex.org/keywords/path","display_name":"Path (computing)","score":0.6072592735290527},{"id":"https://openalex.org/keywords/recommender-system","display_name":"Recommender system","score":0.5204684734344482},{"id":"https://openalex.org/keywords/adversarial-system","display_name":"Adversarial system","score":0.5014948844909668},{"id":"https://openalex.org/keywords/key","display_name":"Key (lock)","score":0.4561227858066559},{"id":"https://openalex.org/keywords/graph","display_name":"Graph","score":0.43295732140541077},{"id":"https://openalex.org/keywords/longest-path-problem","display_name":"Longest path problem","score":0.4282182455062866},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.4235849380493164},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4065757095813751},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.34457480907440186},{"id":"https://openalex.org/keywords/theoretical-computer-science","display_name":"Theoretical computer science","score":0.3406805396080017},{"id":"https://openalex.org/keywords/shortest-path-problem","display_name":"Shortest path problem","score":0.323222815990448}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8124535083770752},{"id":"https://openalex.org/C153083717","wikidata":"https://www.wikidata.org/wiki/Q6535263","display_name":"Leverage (statistics)","level":2,"score":0.7514538764953613},{"id":"https://openalex.org/C2987255567","wikidata":"https://www.wikidata.org/wiki/Q33002955","display_name":"Knowledge graph","level":2,"score":0.6223940849304199},{"id":"https://openalex.org/C2777735758","wikidata":"https://www.wikidata.org/wiki/Q817765","display_name":"Path (computing)","level":2,"score":0.6072592735290527},{"id":"https://openalex.org/C557471498","wikidata":"https://www.wikidata.org/wiki/Q554950","display_name":"Recommender system","level":2,"score":0.5204684734344482},{"id":"https://openalex.org/C37736160","wikidata":"https://www.wikidata.org/wiki/Q1801315","display_name":"Adversarial system","level":2,"score":0.5014948844909668},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.4561227858066559},{"id":"https://openalex.org/C132525143","wikidata":"https://www.wikidata.org/wiki/Q141488","display_name":"Graph","level":2,"score":0.43295732140541077},{"id":"https://openalex.org/C1465435","wikidata":"https://www.wikidata.org/wiki/Q2916352","display_name":"Longest path problem","level":4,"score":0.4282182455062866},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.4235849380493164},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4065757095813751},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.34457480907440186},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.3406805396080017},{"id":"https://openalex.org/C22590252","wikidata":"https://www.wikidata.org/wiki/Q1058754","display_name":"Shortest path problem","level":3,"score":0.323222815990448},{"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/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0},{"id":"https://openalex.org/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3397271.3401171","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3397271.3401171","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 43rd International ACM SIGIR Conference on Research and Development in Information Retrieval","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":42,"referenced_works":["https://openalex.org/W1677182931","https://openalex.org/W1750205245","https://openalex.org/W2004617458","https://openalex.org/W2051228319","https://openalex.org/W2075010670","https://openalex.org/W2100677568","https://openalex.org/W2119717200","https://openalex.org/W2126159342","https://openalex.org/W2134584261","https://openalex.org/W2138108551","https://openalex.org/W2140310134","https://openalex.org/W2152184085","https://openalex.org/W2283196293","https://openalex.org/W2434014514","https://openalex.org/W2743159750","https://openalex.org/W2745413481","https://openalex.org/W2767724106","https://openalex.org/W2788295351","https://openalex.org/W2792839191","https://openalex.org/W2799544270","https://openalex.org/W2801992635","https://openalex.org/W2809162153","https://openalex.org/W2893775232","https://openalex.org/W2897405591","https://openalex.org/W2903340942","https://openalex.org/W2905101140","https://openalex.org/W2911778742","https://openalex.org/W2912664727","https://openalex.org/W2949553967","https://openalex.org/W2950275995","https://openalex.org/W2951625652","https://openalex.org/W2951626319","https://openalex.org/W2954822858","https://openalex.org/W2963561234","https://openalex.org/W2964157711","https://openalex.org/W2966349618","https://openalex.org/W3034328025","https://openalex.org/W3098087397","https://openalex.org/W3099726771","https://openalex.org/W3102778384","https://openalex.org/W3102899483","https://openalex.org/W6600577311"],"related_works":["https://openalex.org/W2776102956","https://openalex.org/W4382866750","https://openalex.org/W4293167680","https://openalex.org/W4387185483","https://openalex.org/W616034966","https://openalex.org/W2018146256","https://openalex.org/W2022506245","https://openalex.org/W4399175858","https://openalex.org/W2040572217","https://openalex.org/W2799386402"],"abstract_inverted_index":{"Knowledge":[0],"graphs":[1,16],"have":[2],"been":[3],"widely":[4],"adopted":[5],"to":[6,43,52,74,88],"improve":[7],"recommendation":[8,37,137],"accuracy.":[9],"The":[10,70],"multi-hop":[11],"user-item":[12],"connections":[13],"on":[14,28,119],"knowledge":[15,98],"also":[17,106],"endow":[18],"reasoning":[19,27,100],"about":[20],"why":[21],"an":[22,108],"item":[23],"is":[24,30,73],"recommended.":[25],"However,":[26],"paths":[29],"a":[31,96],"complex":[32],"combinatorial":[33],"optimization":[34],"problem.":[35],"Traditional":[36],"methods":[38,42],"usually":[39],"adopt":[40],"brute-force":[41],"find":[44],"feasible":[45],"paths,":[46],"which":[47],"results":[48],"in":[49],"issues":[50,62],"related":[51],"convergence":[53],"and":[54,83,134,139],"explainability.":[55,140],"In":[56,92],"this":[57],"paper,":[58],"we":[59,94],"address":[60],"these":[61,86],"by":[63],"better":[64,136],"supervising":[65],"the":[66,114,131],"path":[67,77,90,116],"finding":[68],"process.":[69],"key":[71],"idea":[72],"extract":[75],"imperfect":[76],"demonstrations":[78,87],"with":[79],"minimum":[80],"labeling":[81],"efforts":[82],"effectively":[84],"leverage":[85],"guide":[89],"finding.":[91,117],"particular,":[93],"design":[95],"demonstration-based":[97],"graph":[99],"framework":[101],"for":[102,113],"explainable":[103],"recommendation.":[104],"We":[105],"propose":[107],"ADversarial":[109],"Actor-Critic":[110],"(ADAC)":[111],"model":[112],"demonstration-guided":[115],"Experiments":[118],"three":[120],"real-world":[121],"benchmarks":[122],"show":[123],"that":[124],"our":[125],"method":[126],"converges":[127],"more":[128],"quickly":[129],"than":[130],"state-of-the-art":[132],"baseline":[133],"achieves":[135],"accuracy":[138]},"counts_by_year":[{"year":2026,"cited_by_count":3},{"year":2025,"cited_by_count":16},{"year":2024,"cited_by_count":12},{"year":2023,"cited_by_count":23},{"year":2022,"cited_by_count":31},{"year":2021,"cited_by_count":26},{"year":2020,"cited_by_count":3}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}