{"id":"https://openalex.org/W7154236810","doi":"https://doi.org/10.48550/arxiv.2604.11440","title":"R3-VAE: Reference Vector-Guided Rating Residual Quantization VAE for Generative Recommendation","display_name":"R3-VAE: Reference Vector-Guided Rating Residual Quantization VAE for Generative Recommendation","publication_year":2026,"publication_date":"2026-04-13","ids":{"openalex":"https://openalex.org/W7154236810","doi":"https://doi.org/10.48550/arxiv.2604.11440"},"language":null,"primary_location":{"id":"doi:10.48550/arxiv.2604.11440","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2604.11440","pdf_url":null,"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":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Preprint"},"type":"preprint","indexed_in":["datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://doi.org/10.48550/arxiv.2604.11440","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5133575104","display_name":"Qiang Wan","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Wan, Qiang","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5133609549","display_name":"Ze Yang","orcid":"https://orcid.org/0009-0005-4121-8422"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yang, Ze","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5133587913","display_name":"Dawei Yang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yang, Dawei","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5051415080","display_name":"Ying Fan","orcid":"https://orcid.org/0000-0002-2925-507X"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Fan, Ying","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5133557217","display_name":"Xin Yan","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yan, Xin","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5133610729","display_name":"Siyang Liu","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Liu, Siyang","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":null,"display_name":"Liu, Yicong","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Liu, Yicong","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":null,"display_name":"Zhang, Chenwei","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zhang, Chenwei","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":null,"display_name":"Xu, Wei","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Xu, Wei","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":null,"display_name":"Qin, Jiahao","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Qin, Jiahao","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":null,"display_name":"Wang, Ke","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Wang, Ke","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10203","display_name":"Recommender Systems and Techniques","score":0.8992000222206116,"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":0.8992000222206116,"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/T12026","display_name":"Explainable Artificial Intelligence (XAI)","score":0.014700000174343586,"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":0.008799999952316284,"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/residual","display_name":"Residual","score":0.5383999943733215},{"id":"https://openalex.org/keywords/estimator","display_name":"Estimator","score":0.40779998898506165},{"id":"https://openalex.org/keywords/codebook","display_name":"Codebook","score":0.39250001311302185},{"id":"https://openalex.org/keywords/recommender-system","display_name":"Recommender system","score":0.38589999079704285},{"id":"https://openalex.org/keywords/vector-quantization","display_name":"Vector quantization","score":0.36910000443458557},{"id":"https://openalex.org/keywords/generative-grammar","display_name":"Generative grammar","score":0.3637999892234802},{"id":"https://openalex.org/keywords/performance-improvement","display_name":"Performance improvement","score":0.3476000130176544},{"id":"https://openalex.org/keywords/regularization","display_name":"Regularization (linguistics)","score":0.3458999991416931}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7445999979972839},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5442000031471252},{"id":"https://openalex.org/C155512373","wikidata":"https://www.wikidata.org/wiki/Q287450","display_name":"Residual","level":2,"score":0.5383999943733215},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.5051000118255615},{"id":"https://openalex.org/C185429906","wikidata":"https://www.wikidata.org/wiki/Q1130160","display_name":"Estimator","level":2,"score":0.40779998898506165},{"id":"https://openalex.org/C127759330","wikidata":"https://www.wikidata.org/wiki/Q637416","display_name":"Codebook","level":2,"score":0.39250001311302185},{"id":"https://openalex.org/C557471498","wikidata":"https://www.wikidata.org/wiki/Q554950","display_name":"Recommender system","level":2,"score":0.38589999079704285},{"id":"https://openalex.org/C199833920","wikidata":"https://www.wikidata.org/wiki/Q612536","display_name":"Vector quantization","level":2,"score":0.36910000443458557},{"id":"https://openalex.org/C39890363","wikidata":"https://www.wikidata.org/wiki/Q36108","display_name":"Generative grammar","level":2,"score":0.3637999892234802},{"id":"https://openalex.org/C2778915421","wikidata":"https://www.wikidata.org/wiki/Q3643177","display_name":"Performance improvement","level":2,"score":0.3476000130176544},{"id":"https://openalex.org/C2776135515","wikidata":"https://www.wikidata.org/wiki/Q17143721","display_name":"Regularization (linguistics)","level":2,"score":0.3458999991416931},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.33399999141693115},{"id":"https://openalex.org/C120936955","wikidata":"https://www.wikidata.org/wiki/Q2155640","display_name":"Empirical research","level":2,"score":0.3222000002861023},{"id":"https://openalex.org/C28855332","wikidata":"https://www.wikidata.org/wiki/Q198099","display_name":"Quantization (signal processing)","level":2,"score":0.31709998846054077},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.313400000333786},{"id":"https://openalex.org/C130318100","wikidata":"https://www.wikidata.org/wiki/Q2268914","display_name":"Semantic similarity","level":2,"score":0.2919999957084656},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.2840000092983246},{"id":"https://openalex.org/C21569690","wikidata":"https://www.wikidata.org/wiki/Q94702","display_name":"Collaborative filtering","level":3,"score":0.2727000117301941},{"id":"https://openalex.org/C175291020","wikidata":"https://www.wikidata.org/wiki/Q1156822","display_name":"Offset (computer science)","level":2,"score":0.2565000057220459},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.2529999911785126}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.48550/arxiv.2604.11440","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2604.11440","pdf_url":null,"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":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"doi:10.48550/arxiv.2604.11440","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2604.11440","pdf_url":null,"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":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Preprint"},"sustainable_development_goals":[{"display_name":"Peace, Justice and strong institutions","id":"https://metadata.un.org/sdg/16","score":0.6330843567848206}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Generative":[0],"Recommendation":[1],"(GR)":[2],"has":[3],"gained":[4],"traction":[5],"for":[6,33,107],"its":[7],"merits":[8],"of":[9,164,216],"superior":[10],"performance":[11],"and":[12,56,60,75,128,132,140,168,178,185,199,233],"cold-start":[13],"capability.":[14],"As":[15],"the":[16,53,108,125,213,230],"vital":[17],"role":[18],"in":[19,166,170,197,203,220,223,236],"GR,":[20],"Semantic":[21,138],"Identifiers":[22],"(SIDs)":[23],"represent":[24],"item":[25,214],"semantics":[26],"through":[27,52],"discrete":[28],"tokens.":[29],"However,":[30],"current":[31],"techniques":[32],"SID":[34,63,135],"generation":[35],"based":[36],"on":[37,71,151,189],"vector":[38,100],"quantization":[39],"face":[40],"two":[41,134],"main":[42],"challenges:":[43],"(i)":[44,97],"training":[45,74,126,184],"instability,":[46],"stemming":[47],"from":[48],"insufficient":[49],"gradient":[50],"propagation":[51],"straight-through":[54],"estimator":[55],"sensitivity":[57,113],"to":[58,114,123,211],"initialization;":[59,115],"(ii)":[61,116],"inefficient":[62],"quality":[64],"assessment,":[65],"where":[66],"industrial":[67],"practice":[68],"still":[69],"depends":[70],"costly":[72],"GR":[73,183],"A/B":[76,187],"testing.":[77],"To":[78],"address":[79],"these":[80],"challenges,":[81],"we":[82,181,208],"propose":[83],"Reference":[84],"Vector-Guided":[85],"Rating":[86],"Residual":[87],"Quantization":[88],"VAE":[89],"(R3-VAE).":[90],"This":[91],"framework":[92],"incorporates":[93],"three":[94,173],"key":[95],"innovations:":[96],"a":[98,104,117,194,200],"reference":[99],"that":[101,155],"functions":[102],"as":[103,144],"semantic":[105],"anchor":[106],"initial":[109],"features,":[110],"thereby":[111],"mitigating":[112],"dot":[118],"product-based":[119],"rating":[120],"mechanism":[121],"designed":[122],"stabilize":[124],"process":[127],"prevent":[129],"codebook":[130],"collapse;":[131],"(iii)":[133],"evaluation":[136],"metrics,":[137],"Cohesion":[139],"Preference":[141],"Discrimination,":[142],"serving":[143],"regularization":[145],"terms":[146],"during":[147],"training.":[148],"Empirical":[149],"results":[150],"six":[152],"benchmarks":[153],"demonstrate":[154],"R3-VAE":[156,210],"outperforms":[157],"state-of-the-art":[158],"methods,":[159],"achieving":[160],"an":[161],"average":[162],"improvement":[163,196],"14.5%":[165],"Recall@10":[167],"15.5%":[169],"NDCG@10":[171],"across":[172],"public":[174],"datasets":[175],"(Beauty,":[176],"Sports,":[177],"Toys).":[179],"Furthermore,":[180],"perform":[182],"online":[186],"tests":[188],"Toutiao.":[190],"Our":[191],"method":[192],"achieves":[193],"1.62%":[195],"MRR":[198],"0.83%":[201],"gain":[202],"StayTime/U":[204],"versus":[205],"baselines.":[206],"Additionally,":[207],"employ":[209],"replace":[212],"ID":[215],"CTR":[217],"model,":[218],"resulting":[219],"significant":[221],"improvements":[222],"content":[224],"cold":[225],"start":[226],"by":[227],"15.36%,":[228],"corroborating":[229],"strong":[231],"applicability":[232],"business":[234],"value":[235],"industry-scale":[237],"recommendation":[238],"scenarios.":[239]},"counts_by_year":[],"updated_date":"2026-07-01T06:00:48.157686","created_date":"2026-04-15T00:00:00"}