{"id":"https://openalex.org/W7155984035","doi":"https://doi.org/10.1145/3774904.3792155","title":"FeedGuard: Online Critic-Guided Reinforcement Learning with Privacy-Preserving Feedback for Recommendation","display_name":"FeedGuard: Online Critic-Guided Reinforcement Learning with Privacy-Preserving Feedback for Recommendation","publication_year":2026,"publication_date":"2026-04-12","ids":{"openalex":"https://openalex.org/W7155984035","doi":"https://doi.org/10.1145/3774904.3792155"},"language":null,"primary_location":{"id":"doi:10.1145/3774904.3792155","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3774904.3792155","pdf_url":null,"source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the ACM Web Conference 2026","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://doi.org/10.1145/3774904.3792155","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5101547334","display_name":"Mengying Zhu","orcid":"https://orcid.org/0000-0002-9343-5729"},"institutions":[{"id":"https://openalex.org/I109935558","display_name":"Ningbo University","ror":"https://ror.org/03et85d35","country_code":"CN","type":"education","lineage":["https://openalex.org/I109935558"]},{"id":"https://openalex.org/I76130692","display_name":"Zhejiang University","ror":"https://ror.org/00a2xv884","country_code":"CN","type":"education","lineage":["https://openalex.org/I76130692"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Mengying Zhu","raw_affiliation_strings":["School of Software Technology, Zhejiang University, Ningbo, China"],"raw_orcid":"https://orcid.org/0000-0002-9343-5729","affiliations":[{"raw_affiliation_string":"School of Software Technology, Zhejiang University, Ningbo, China","institution_ids":["https://openalex.org/I109935558","https://openalex.org/I76130692"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5104332213","display_name":"Feiyue Chen","orcid":null},"institutions":[{"id":"https://openalex.org/I109935558","display_name":"Ningbo University","ror":"https://ror.org/03et85d35","country_code":"CN","type":"education","lineage":["https://openalex.org/I109935558"]},{"id":"https://openalex.org/I76130692","display_name":"Zhejiang University","ror":"https://ror.org/00a2xv884","country_code":"CN","type":"education","lineage":["https://openalex.org/I76130692"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Feiyue Chen","raw_affiliation_strings":["School of Software Technology, Zhejiang University, Ningbo, China"],"raw_orcid":"https://orcid.org/0009-0007-2290-1247","affiliations":[{"raw_affiliation_string":"School of Software Technology, Zhejiang University, Ningbo, China","institution_ids":["https://openalex.org/I109935558","https://openalex.org/I76130692"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5014984879","display_name":"Lifan Jiang","orcid":"https://orcid.org/0009-0003-6090-639X"},"institutions":[{"id":"https://openalex.org/I109935558","display_name":"Ningbo University","ror":"https://ror.org/03et85d35","country_code":"CN","type":"education","lineage":["https://openalex.org/I109935558"]},{"id":"https://openalex.org/I76130692","display_name":"Zhejiang University","ror":"https://ror.org/00a2xv884","country_code":"CN","type":"education","lineage":["https://openalex.org/I76130692"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Lifan Jiang","raw_affiliation_strings":["School of Software Technology, Zhejiang University, Ningbo, China"],"raw_orcid":"https://orcid.org/0009-0008-1197-195X","affiliations":[{"raw_affiliation_string":"School of Software Technology, Zhejiang University, Ningbo, China","institution_ids":["https://openalex.org/I109935558","https://openalex.org/I76130692"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5046974812","display_name":"Mengyuan Yang","orcid":"https://orcid.org/0000-0003-3418-711X"},"institutions":[{"id":"https://openalex.org/I76130692","display_name":"Zhejiang University","ror":"https://ror.org/00a2xv884","country_code":"CN","type":"education","lineage":["https://openalex.org/I76130692"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Mengyuan Yang","raw_affiliation_strings":["Zhejiang University, Hangzhou, China"],"raw_orcid":"https://orcid.org/0000-0003-3418-711X","affiliations":[{"raw_affiliation_string":"Zhejiang University, Hangzhou, China","institution_ids":["https://openalex.org/I76130692"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101976531","display_name":"Yangyang Wu","orcid":"https://orcid.org/0000-0001-9531-0906"},"institutions":[{"id":"https://openalex.org/I109935558","display_name":"Ningbo University","ror":"https://ror.org/03et85d35","country_code":"CN","type":"education","lineage":["https://openalex.org/I109935558"]},{"id":"https://openalex.org/I76130692","display_name":"Zhejiang University","ror":"https://ror.org/00a2xv884","country_code":"CN","type":"education","lineage":["https://openalex.org/I76130692"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yangyang Wu","raw_affiliation_strings":["School of Software Technology, Zhejiang University, Ningbo, China"],"raw_orcid":"https://orcid.org/0000-0001-9531-0906","affiliations":[{"raw_affiliation_string":"School of Software Technology, Zhejiang University, Ningbo, China","institution_ids":["https://openalex.org/I109935558","https://openalex.org/I76130692"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5076835003","display_name":"Guanjie Cheng","orcid":"https://orcid.org/0000-0003-2080-3903"},"institutions":[{"id":"https://openalex.org/I109935558","display_name":"Ningbo University","ror":"https://ror.org/03et85d35","country_code":"CN","type":"education","lineage":["https://openalex.org/I109935558"]},{"id":"https://openalex.org/I76130692","display_name":"Zhejiang University","ror":"https://ror.org/00a2xv884","country_code":"CN","type":"education","lineage":["https://openalex.org/I76130692"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Guanjie Cheng","raw_affiliation_strings":["School of Software Technology, Zhejiang University, Ningbo, China"],"raw_orcid":"https://orcid.org/0000-0003-2080-3903","affiliations":[{"raw_affiliation_string":"School of Software Technology, Zhejiang University, Ningbo, China","institution_ids":["https://openalex.org/I109935558","https://openalex.org/I76130692"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5074603286","display_name":"Xiaolin Zheng","orcid":"https://orcid.org/0000-0001-5483-0366"},"institutions":[{"id":"https://openalex.org/I76130692","display_name":"Zhejiang University","ror":"https://ror.org/00a2xv884","country_code":"CN","type":"education","lineage":["https://openalex.org/I76130692"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xiaolin Zheng","raw_affiliation_strings":["Zhejiang University, Hangzhou, China"],"raw_orcid":"https://orcid.org/0000-0001-5483-0366","affiliations":[{"raw_affiliation_string":"Zhejiang University, Hangzhou, China","institution_ids":["https://openalex.org/I76130692"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.4480754,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"650","last_page":"661"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10203","display_name":"Recommender Systems and Techniques","score":0.44449999928474426,"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":0.44449999928474426,"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/T11519","display_name":"Digital Mental Health Interventions","score":0.07599999755620956,"subfield":{"id":"https://openalex.org/subfields/3202","display_name":"Applied Psychology"},"field":{"id":"https://openalex.org/fields/32","display_name":"Psychology"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},{"id":"https://openalex.org/T10764","display_name":"Privacy-Preserving Technologies in Data","score":0.055799998342990875,"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":0.8428999781608582},{"id":"https://openalex.org/keywords/leverage","display_name":"Leverage (statistics)","score":0.7092000246047974},{"id":"https://openalex.org/keywords/differential-privacy","display_name":"Differential privacy","score":0.657800018787384},{"id":"https://openalex.org/keywords/online-learning","display_name":"Online learning","score":0.555899977684021},{"id":"https://openalex.org/keywords/recommender-system","display_name":"Recommender system","score":0.4230000078678131},{"id":"https://openalex.org/keywords/information-privacy","display_name":"Information privacy","score":0.3865000009536743},{"id":"https://openalex.org/keywords/key","display_name":"Key (lock)","score":0.36500000953674316}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.8428999781608582},{"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/C153083717","wikidata":"https://www.wikidata.org/wiki/Q6535263","display_name":"Leverage (statistics)","level":2,"score":0.7092000246047974},{"id":"https://openalex.org/C23130292","wikidata":"https://www.wikidata.org/wiki/Q5275358","display_name":"Differential privacy","level":2,"score":0.657800018787384},{"id":"https://openalex.org/C2986087404","wikidata":"https://www.wikidata.org/wiki/Q15946010","display_name":"Online learning","level":2,"score":0.555899977684021},{"id":"https://openalex.org/C557471498","wikidata":"https://www.wikidata.org/wiki/Q554950","display_name":"Recommender system","level":2,"score":0.4230000078678131},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.4009999930858612},{"id":"https://openalex.org/C123201435","wikidata":"https://www.wikidata.org/wiki/Q456632","display_name":"Information privacy","level":2,"score":0.3865000009536743},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.36500000953674316},{"id":"https://openalex.org/C13662910","wikidata":"https://www.wikidata.org/wiki/Q193139","display_name":"Trajectory","level":2,"score":0.3447999954223633},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.30239999294281006},{"id":"https://openalex.org/C2777851325","wikidata":"https://www.wikidata.org/wiki/Q7094102","display_name":"Online model","level":2,"score":0.2809000015258789},{"id":"https://openalex.org/C3017597292","wikidata":"https://www.wikidata.org/wiki/Q25052250","display_name":"Privacy protection","level":2,"score":0.27880001068115234},{"id":"https://openalex.org/C67203356","wikidata":"https://www.wikidata.org/wiki/Q1321905","display_name":"Reinforcement","level":2,"score":0.2766000032424927},{"id":"https://openalex.org/C108827166","wikidata":"https://www.wikidata.org/wiki/Q175975","display_name":"Internet privacy","level":1,"score":0.27300000190734863},{"id":"https://openalex.org/C2776291640","wikidata":"https://www.wikidata.org/wiki/Q2912517","display_name":"Value (mathematics)","level":2,"score":0.271699994802475},{"id":"https://openalex.org/C12298181","wikidata":"https://www.wikidata.org/wiki/Q7246814","display_name":"Proactive learning","level":5,"score":0.26330000162124634},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.26260000467300415},{"id":"https://openalex.org/C125014702","wikidata":"https://www.wikidata.org/wiki/Q4680749","display_name":"Adaptive learning","level":2,"score":0.2624000012874603}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3774904.3792155","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3774904.3792155","pdf_url":null,"source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the ACM Web Conference 2026","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.1145/3774904.3792155","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3774904.3792155","pdf_url":null,"source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the ACM Web Conference 2026","raw_type":"proceedings-article"},"sustainable_development_goals":[{"score":0.7831025123596191,"id":"https://metadata.un.org/sdg/16","display_name":"Peace, Justice and strong institutions"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":20,"referenced_works":["https://openalex.org/W1557833142","https://openalex.org/W1968563228","https://openalex.org/W2562337727","https://openalex.org/W2744999500","https://openalex.org/W2963654596","https://openalex.org/W2971641579","https://openalex.org/W2984100107","https://openalex.org/W3018102029","https://openalex.org/W3137510859","https://openalex.org/W3153968589","https://openalex.org/W4205228770","https://openalex.org/W4226307069","https://openalex.org/W4285015060","https://openalex.org/W4285268639","https://openalex.org/W4312221817","https://openalex.org/W4319303175","https://openalex.org/W4382239956","https://openalex.org/W4391473131","https://openalex.org/W4393159899","https://openalex.org/W4394007749"],"related_works":[],"abstract_inverted_index":{"Reinforcement":[0],"learning-based":[1],"recommendation":[2,128],"systems":[3],"(RLRS)":[4],"are":[5],"increasingly":[6],"favored":[7],"for":[8,39,59],"their":[9],"ability":[10],"to":[11],"leverage":[12],"online":[13,62,90,143],"interactive":[14],"feedback,":[15,45],"enabling":[16],"adaptive":[17],"and":[18,32,49,64,96,109,130,142],"personalized":[19],"decision-making.":[20],"In":[21,67],"this":[22,68],"setting,":[23],"user":[24],"feedback":[25,103],"serves":[26],"as":[27],"both":[28,140],"a":[29,73,115],"behavioral":[30],"signal":[31],"an":[33],"optimization":[34],"target,":[35],"making":[36],"it":[37],"essential":[38],"policy":[40],"learning.":[41],"However,":[42],"collecting":[43],"such":[44],"e.g.,":[46],"clicks,":[47],"ratings,":[48],"engagement":[50],"traces,":[51],"raises":[52],"serious":[53],"privacy":[54,65,99,121,148],"concerns,":[55],"posing":[56],"critical":[57],"challenges":[58],"value":[60],"estimation,":[61],"adaptation,":[63],"protection.":[66],"paper,":[69],"we":[70],"propose":[71],"FeedGuard,":[72],"critic-guided":[74],"reinforcement":[75],"learning":[76,108],"framework":[77],"with":[78,92,150],"privacy-preserving":[79],"feedback.":[80],"FeedGuard":[81,136],"enhances":[82],"trajectory":[83],"modeling":[84],"via":[85,105],"critic":[86],"guidance,":[87],"enables":[88],"joint":[89],"fine-tuning":[91],"effective":[93],"exploration\u2013exploitation":[94],"tradeoffs,":[95],"enforces":[97],"end-to-end":[98],"protection":[100],"across":[101],"the":[102,131],"lifecycle":[104],"split":[106],"federated":[107],"differential":[110,120],"privacy.":[111],"We":[112],"further":[113],"provide":[114],"formal":[116],"analysis":[117],"of":[118],"its":[119],"guarantees.":[122],"Extensive":[123],"experiments":[124],"on":[125],"four":[126],"public":[127],"datasets":[129],"VirtualTB":[132],"platform":[133],"show":[134],"that":[135],"performs":[137],"well":[138],"in":[139],"offline":[141],"settings,":[144],"while":[145],"maintaining":[146],"rigorous":[147],"guarantees":[149],"minimal":[151],"degradation.":[152]},"counts_by_year":[],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2026-04-28T00:00:00"}
