{"id":"https://openalex.org/W4284712454","doi":"https://doi.org/10.1145/3477495.3532015","title":"Locality-Sensitive State-Guided Experience Replay Optimization for Sparse Rewards in Online Recommendation","display_name":"Locality-Sensitive State-Guided Experience Replay Optimization for Sparse Rewards in Online Recommendation","publication_year":2022,"publication_date":"2022-07-06","ids":{"openalex":"https://openalex.org/W4284712454","doi":"https://doi.org/10.1145/3477495.3532015"},"language":"en","primary_location":{"id":"doi:10.1145/3477495.3532015","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3477495.3532015","pdf_url":null,"source":{"id":"https://openalex.org/S4363608773","display_name":"Proceedings of the 45th International ACM SIGIR Conference on Research and Development in Information Retrieval","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 45th International ACM SIGIR Conference on Research and Development in Information Retrieval","raw_type":"proceedings-article"},"type":"conference-paper","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/A5057487706","display_name":"Xiaocong Chen","orcid":"https://orcid.org/0000-0002-8849-4943"},"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":["University of New South Wales, Sydney, NSW, Australia"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of New South Wales, Sydney, NSW, Australia","institution_ids":["https://openalex.org/I31746571"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5052731721","display_name":"Lina Yao","orcid":"https://orcid.org/0000-0002-4149-839X"},"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":["University of New South Wales, Sydney, NSW, Australia"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of New South Wales, Sydney, NSW, Australia","institution_ids":["https://openalex.org/I31746571"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5021827617","display_name":"Julian McAuley","orcid":"https://orcid.org/0000-0003-0955-7588"},"institutions":[{"id":"https://openalex.org/I36258959","display_name":"University of California San Diego","ror":"https://ror.org/0168r3w48","country_code":"US","type":"education","lineage":["https://openalex.org/I36258959"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Julian McAuley","raw_affiliation_strings":["University of California, San Diego, San Diego, CA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of California, San Diego, San Diego, CA, USA","institution_ids":["https://openalex.org/I36258959"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5075938343","display_name":"Weili Guan","orcid":"https://orcid.org/0000-0002-5658-5509"},"institutions":[{"id":"https://openalex.org/I56590836","display_name":"Monash University","ror":"https://ror.org/02bfwt286","country_code":"AU","type":"education","lineage":["https://openalex.org/I56590836"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Weili Guan","raw_affiliation_strings":["Monash University, Melbourne, VIC, Australia"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Monash University, Melbourne, VIC, Australia","institution_ids":["https://openalex.org/I56590836"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5034967388","display_name":"Xiaojun Chang","orcid":"https://orcid.org/0000-0002-7778-8807"},"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":"Xiaojun Chang","raw_affiliation_strings":["University of Technology Sydney, Sydney, NSW, Australia"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Technology Sydney, Sydney, NSW, Australia","institution_ids":["https://openalex.org/I114017466"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5076107706","display_name":"Xianzhi Wang","orcid":"https://orcid.org/0000-0001-9582-3445"},"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":["University of Technology Sydney, Sydney, NSW, Australia"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Technology Sydney, Sydney, NSW, Australia","institution_ids":["https://openalex.org/I114017466"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":4,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":3.2661,"has_fulltext":false,"cited_by_count":14,"citation_normalized_percentile":{"value":0.93594975,"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":"1316","last_page":"1325"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10203","display_name":"Recommender Systems and Techniques","score":0.9986000061035156,"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":0.9986000061035156,"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":0.9984999895095825,"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/T11478","display_name":"Caching and Content Delivery","score":0.994700014591217,"subfield":{"id":"https://openalex.org/subfields/1705","display_name":"Computer Networks and Communications"},"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":0.8499621748924255},{"id":"https://openalex.org/keywords/recommender-system","display_name":"Recommender system","score":0.8163150548934937},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.7209118008613586},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.6787723302841187},{"id":"https://openalex.org/keywords/locality","display_name":"Locality","score":0.6440434455871582},{"id":"https://openalex.org/keywords/state-space","display_name":"State space","score":0.4461537003517151},{"id":"https://openalex.org/keywords/salient","display_name":"Salient","score":0.44607335329055786},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.41324082016944885},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.409148633480072}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8499621748924255},{"id":"https://openalex.org/C557471498","wikidata":"https://www.wikidata.org/wiki/Q554950","display_name":"Recommender system","level":2,"score":0.8163150548934937},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.7209118008613586},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.6787723302841187},{"id":"https://openalex.org/C2779808786","wikidata":"https://www.wikidata.org/wiki/Q6664603","display_name":"Locality","level":2,"score":0.6440434455871582},{"id":"https://openalex.org/C72434380","wikidata":"https://www.wikidata.org/wiki/Q230930","display_name":"State space","level":2,"score":0.4461537003517151},{"id":"https://openalex.org/C2780719617","wikidata":"https://www.wikidata.org/wiki/Q1030752","display_name":"Salient","level":2,"score":0.44607335329055786},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.41324082016944885},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.409148633480072},{"id":"https://openalex.org/C205649164","wikidata":"https://www.wikidata.org/wiki/Q1071","display_name":"Geography","level":0,"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/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C13280743","wikidata":"https://www.wikidata.org/wiki/Q131089","display_name":"Geodesy","level":1,"score":0.0},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3477495.3532015","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3477495.3532015","pdf_url":null,"source":{"id":"https://openalex.org/S4363608773","display_name":"Proceedings of the 45th International ACM SIGIR Conference on Research and Development in Information Retrieval","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 45th 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":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":26,"referenced_works":["https://openalex.org/W2147717514","https://openalex.org/W2775482448","https://openalex.org/W2787933113","https://openalex.org/W2799544270","https://openalex.org/W2809162153","https://openalex.org/W2914272066","https://openalex.org/W2921980263","https://openalex.org/W2948345531","https://openalex.org/W2950275995","https://openalex.org/W2963561234","https://openalex.org/W2963619374","https://openalex.org/W2963654596","https://openalex.org/W2964048876","https://openalex.org/W2964108915","https://openalex.org/W2965512832","https://openalex.org/W2965870268","https://openalex.org/W2970971581","https://openalex.org/W2997914278","https://openalex.org/W2998202787","https://openalex.org/W3003416843","https://openalex.org/W3007094061","https://openalex.org/W3017289192","https://openalex.org/W3029587262","https://openalex.org/W3098551837","https://openalex.org/W3102899483","https://openalex.org/W3103141630"],"related_works":["https://openalex.org/W2968745142","https://openalex.org/W2809363009","https://openalex.org/W2369936857","https://openalex.org/W2348159088","https://openalex.org/W2045871438","https://openalex.org/W2499363748","https://openalex.org/W2350747448","https://openalex.org/W2368095327","https://openalex.org/W4319083788","https://openalex.org/W2729602312"],"abstract_inverted_index":{"Online":[0],"recommendation":[1],"requires":[2],"handling":[3],"rapidly":[4],"changing":[5],"user":[6,57],"preferences.":[7],"Deep":[8],"reinforcement":[9],"learning":[10,90],"(DRL)":[11],"is":[12,28,125,141,157],"an":[13,91],"effective":[14],"means":[15],"of":[16,40,71,82],"capturing":[17],"users'":[18],"dynamic":[19],"interest":[20],"during":[21],"interactions":[22],"with":[23,164],"recommender":[24,37,84],"systems.":[25],"Generally,":[26],"it":[27],"challenging":[29],"to":[30,67,78,100,127,143,159,196],"train":[31],"a":[32,98,106,137,153],"DRL":[33],"agent":[34,115],"in":[35,89,112],"online":[36,83,133],"systems":[38,85],"because":[39],"the":[41,46,69,79,114,118,129,146,171,175,185],"sparse":[42,72],"rewards":[43],"caused":[44],"by":[45],"large":[47],"action":[48],"space":[49,186],"(e.g.,":[50],"candidate":[51],"item":[52],"space)":[53],"and":[54,86,121,124,152,177,183],"comparatively":[55],"fewer":[56],"interactions.":[58],"Leveraging":[59],"experience":[60,109,149,181,199],"replay":[61,110,160,182,200],"(ER)":[62],"has":[63],"been":[64],"extensively":[65],"studied":[66],"conquer":[68],"issue":[70],"rewards.":[73],"However,":[74],"they":[75],"adapt":[76],"poorly":[77],"complex":[80],"environment":[81],"are":[87],"inefficient":[88],"optimal":[92,130],"strategy":[93,156],"from":[94],"past":[95],"experience.":[96],"As":[97],"step":[99],"filling":[101],"this":[102],"gap,":[103],"we":[104],"propose":[105],"novel":[107],"state-aware":[108],"model,":[111],"which":[113],"selectively":[116,144],"discovers":[117],"most":[119,147],"relevant":[120],"salient":[122],"experiences":[123,163],"guided":[126],"find":[128],"policy":[131],"for":[132],"recommendations.":[134],"In":[135],"particular,":[136],"locality-sensitive":[138],"hashing":[139],"method":[140,173],"proposed":[142,172],"retain":[145],"meaningful":[148],"at":[150],"scale":[151],"prioritized":[154],"reward-driven":[155],"designed":[158],"more":[161],"valuable":[162],"higher":[165],"chance.":[166],"We":[167],"formally":[168],"show":[169],"that":[170],"guarantees":[174],"upper":[176],"lower":[178],"bound":[179],"on":[180],"optimizes":[184],"complexity,":[187],"as":[188,190],"well":[189],"empirically":[191],"demonstrate":[192],"our":[193],"model's":[194],"superiority":[195],"several":[197],"existing":[198],"methods":[201],"over":[202],"three":[203],"benchmark":[204],"simulation":[205],"platforms.":[206]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":4},{"year":2023,"cited_by_count":6},{"year":2022,"cited_by_count":1}],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}