{"id":"https://openalex.org/W4414448031","doi":"https://doi.org/10.1145/3746252.3761579","title":"Progressive Semantic Residual Quantization for Multimodal-Joint Interest Modeling in Music Recommendation","display_name":"Progressive Semantic Residual Quantization for Multimodal-Joint Interest Modeling in Music Recommendation","publication_year":2025,"publication_date":"2025-11-08","ids":{"openalex":"https://openalex.org/W4414448031","doi":"https://doi.org/10.1145/3746252.3761579"},"language":"en","primary_location":{"id":"doi:10.1145/3746252.3761579","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3746252.3761579","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 34th ACM International Conference on Information and Knowledge Management","raw_type":"proceedings-article"},"type":"preprint","indexed_in":["arxiv","crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2508.20359","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5016188113","display_name":"Shijia Wang","orcid":"https://orcid.org/0000-0001-9170-1889"},"institutions":[{"id":"https://openalex.org/I4210091137","display_name":"NetEase (China)","ror":"https://ror.org/00fp6fj05","country_code":"CN","type":"company","lineage":["https://openalex.org/I4210091137"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Shijia Wang","raw_affiliation_strings":["NetEase Cloud Music, Hangzhou, China"],"raw_orcid":"https://orcid.org/0000-0001-9170-1889","affiliations":[{"raw_affiliation_string":"NetEase Cloud Music, Hangzhou, China","institution_ids":["https://openalex.org/I4210091137"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Tianpei Ouyang","orcid":"https://orcid.org/0009-0006-9868-0367"},"institutions":[{"id":"https://openalex.org/I50760025","display_name":"Hangzhou Dianzi University","ror":"https://ror.org/0576gt767","country_code":"CN","type":"education","lineage":["https://openalex.org/I50760025"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Tianpei Ouyang","raw_affiliation_strings":["NetEase Cloud Music, Hangzhou, China and Hangzhou Dianzi University, Hangzhou, China"],"raw_orcid":"https://orcid.org/0009-0006-9868-0367","affiliations":[{"raw_affiliation_string":"NetEase Cloud Music, Hangzhou, China and Hangzhou Dianzi University, Hangzhou, China","institution_ids":["https://openalex.org/I50760025"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5064541131","display_name":"Qiang Xiao","orcid":"https://orcid.org/0000-0002-3940-5449"},"institutions":[{"id":"https://openalex.org/I4210091137","display_name":"NetEase (China)","ror":"https://ror.org/00fp6fj05","country_code":"CN","type":"company","lineage":["https://openalex.org/I4210091137"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Qiang Xiao","raw_affiliation_strings":["NetEase Cloud Music, Hangzhou, China"],"raw_orcid":"https://orcid.org/0000-0002-3940-5449","affiliations":[{"raw_affiliation_string":"NetEase Cloud Music, Hangzhou, China","institution_ids":["https://openalex.org/I4210091137"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5043738330","display_name":"Dongjing Wang","orcid":"https://orcid.org/0000-0003-2152-0446"},"institutions":[{"id":"https://openalex.org/I50760025","display_name":"Hangzhou Dianzi University","ror":"https://ror.org/0576gt767","country_code":"CN","type":"education","lineage":["https://openalex.org/I50760025"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Dongjing Wang","raw_affiliation_strings":["Hangzhou Dianzi University, Hangzhou, China"],"raw_orcid":"https://orcid.org/0000-0003-2152-0446","affiliations":[{"raw_affiliation_string":"Hangzhou Dianzi University, Hangzhou, China","institution_ids":["https://openalex.org/I50760025"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5113901942","display_name":"Yong-Wang Ren","orcid":"https://orcid.org/0009-0009-2090-0974"},"institutions":[{"id":"https://openalex.org/I4210091137","display_name":"NetEase (China)","ror":"https://ror.org/00fp6fj05","country_code":"CN","type":"company","lineage":["https://openalex.org/I4210091137"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yintao Ren","raw_affiliation_strings":["NetEase Cloud Music, Hangzhou, China"],"raw_orcid":"https://orcid.org/0009-0009-2090-0974","affiliations":[{"raw_affiliation_string":"NetEase Cloud Music, Hangzhou, China","institution_ids":["https://openalex.org/I4210091137"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Songpei Xu","orcid":"https://orcid.org/0009-0004-9515-7226"},"institutions":[{"id":"https://openalex.org/I4210091137","display_name":"NetEase (China)","ror":"https://ror.org/00fp6fj05","country_code":"CN","type":"company","lineage":["https://openalex.org/I4210091137"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Songpei Xu","raw_affiliation_strings":["NetEase Cloud Music, Hangzhou, China"],"raw_orcid":"https://orcid.org/0009-0004-9515-7226","affiliations":[{"raw_affiliation_string":"NetEase Cloud Music, Hangzhou, China","institution_ids":["https://openalex.org/I4210091137"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5113362030","display_name":"D. GUO","orcid":null},"institutions":[{"id":"https://openalex.org/I4210091137","display_name":"NetEase (China)","ror":"https://ror.org/00fp6fj05","country_code":"CN","type":"company","lineage":["https://openalex.org/I4210091137"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Da Guo","raw_affiliation_strings":["NetEase Cloud Music, Hangzhou, China"],"raw_orcid":"https://orcid.org/0009-0001-1263-5383","affiliations":[{"raw_affiliation_string":"NetEase Cloud Music, Hangzhou, China","institution_ids":["https://openalex.org/I4210091137"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5031724904","display_name":"Chuanjiang Luo","orcid":"https://orcid.org/0009-0008-7022-8023"},"institutions":[{"id":"https://openalex.org/I4210091137","display_name":"NetEase (China)","ror":"https://ror.org/00fp6fj05","country_code":"CN","type":"company","lineage":["https://openalex.org/I4210091137"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Chuanjiang Luo","raw_affiliation_strings":["NetEase Cloud Music, Hangzhou, China"],"raw_orcid":"https://orcid.org/0009-0008-7022-8023","affiliations":[{"raw_affiliation_string":"NetEase Cloud Music, Hangzhou, China","institution_ids":["https://openalex.org/I4210091137"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":8,"corresponding_author_ids":["https://openalex.org/A5016188113"],"corresponding_institution_ids":["https://openalex.org/I4210091137"],"apc_list":null,"apc_paid":null,"fwci":3.4611,"has_fulltext":false,"cited_by_count":3,"citation_normalized_percentile":{"value":0.93141032,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":98,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"6119","last_page":"6127"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11309","display_name":"Music and Audio Processing","score":0.9959999918937683,"subfield":{"id":"https://openalex.org/subfields/1711","display_name":"Signal Processing"},"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/T11309","display_name":"Music and Audio Processing","score":0.9959999918937683,"subfield":{"id":"https://openalex.org/subfields/1711","display_name":"Signal Processing"},"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/semantic-similarity","display_name":"Semantic similarity","score":0.5011000037193298},{"id":"https://openalex.org/keywords/recommender-system","display_name":"Recommender system","score":0.4535999894142151},{"id":"https://openalex.org/keywords/quantization","display_name":"Quantization (signal processing)","score":0.44510000944137573},{"id":"https://openalex.org/keywords/semantic-computing","display_name":"Semantic computing","score":0.42419999837875366},{"id":"https://openalex.org/keywords/semantics","display_name":"Semantics (computer science)","score":0.4007999897003174},{"id":"https://openalex.org/keywords/residual","display_name":"Residual","score":0.38690000772476196},{"id":"https://openalex.org/keywords/lyrics","display_name":"Lyrics","score":0.383899986743927},{"id":"https://openalex.org/keywords/prefix","display_name":"Prefix","score":0.3752000033855438}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8212000131607056},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5354999899864197},{"id":"https://openalex.org/C130318100","wikidata":"https://www.wikidata.org/wiki/Q2268914","display_name":"Semantic similarity","level":2,"score":0.5011000037193298},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.45719999074935913},{"id":"https://openalex.org/C557471498","wikidata":"https://www.wikidata.org/wiki/Q554950","display_name":"Recommender system","level":2,"score":0.4535999894142151},{"id":"https://openalex.org/C28855332","wikidata":"https://www.wikidata.org/wiki/Q198099","display_name":"Quantization (signal processing)","level":2,"score":0.44510000944137573},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.4336000084877014},{"id":"https://openalex.org/C511149849","wikidata":"https://www.wikidata.org/wiki/Q7449051","display_name":"Semantic computing","level":3,"score":0.42419999837875366},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.4007999897003174},{"id":"https://openalex.org/C155512373","wikidata":"https://www.wikidata.org/wiki/Q287450","display_name":"Residual","level":2,"score":0.38690000772476196},{"id":"https://openalex.org/C2776436406","wikidata":"https://www.wikidata.org/wiki/Q602446","display_name":"Lyrics","level":2,"score":0.383899986743927},{"id":"https://openalex.org/C141603448","wikidata":"https://www.wikidata.org/wiki/Q134830","display_name":"Prefix","level":2,"score":0.3752000033855438},{"id":"https://openalex.org/C90312973","wikidata":"https://www.wikidata.org/wiki/Q7449052","display_name":"Semantic data model","level":2,"score":0.34290000796318054},{"id":"https://openalex.org/C85407183","wikidata":"https://www.wikidata.org/wiki/Q1045785","display_name":"Semantic network","level":2,"score":0.3418000042438507},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.32910001277923584},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.2953999936580658},{"id":"https://openalex.org/C197914299","wikidata":"https://www.wikidata.org/wiki/Q18650","display_name":"Semantic memory","level":3,"score":0.2944999933242798},{"id":"https://openalex.org/C33954974","wikidata":"https://www.wikidata.org/wiki/Q486494","display_name":"Sensor fusion","level":2,"score":0.29330000281333923},{"id":"https://openalex.org/C67186912","wikidata":"https://www.wikidata.org/wiki/Q367664","display_name":"Data modeling","level":2,"score":0.26409998536109924},{"id":"https://openalex.org/C192209626","wikidata":"https://www.wikidata.org/wiki/Q190909","display_name":"Focus (optics)","level":2,"score":0.257999986410141},{"id":"https://openalex.org/C2781122975","wikidata":"https://www.wikidata.org/wiki/Q16928266","display_name":"Semantic feature","level":2,"score":0.25679999589920044},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.25380000472068787}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1145/3746252.3761579","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3746252.3761579","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 34th ACM International Conference on Information and Knowledge Management","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2508.20359","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2508.20359","pdf_url":"https://arxiv.org/pdf/2508.20359","source":{"id":"https://openalex.org/S4393918464","display_name":"ArXiv.org","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2508.20359","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2508.20359","pdf_url":"https://arxiv.org/pdf/2508.20359","source":{"id":"https://openalex.org/S4393918464","display_name":"ArXiv.org","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G5285785058","display_name":null,"funder_award_id":"LZ25F020010","funder_id":"https://openalex.org/F4320338464","funder_display_name":"Natural Science Foundation of Zhejiang Province"}],"funders":[{"id":"https://openalex.org/F4320338464","display_name":"Natural Science Foundation of Zhejiang Province","ror":"https://ror.org/01h0zpd94"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"In":[0,113,137],"music":[1,190],"recommendation":[2,108,209],"systems,":[3],"multimodal":[4,37,107,143],"interest":[5,97,144],"learning":[6],"is":[7,152],"pivotal,":[8],"which":[9],"allows":[10],"the":[11,114,133,138,156],"model":[12,142,157],"to":[13,72,90,141,154,158],"capture":[14,91,160],"nuanced":[15],"preferences,":[16],"including":[17],"textual":[18],"elements":[19],"such":[20,27],"as":[21,28],"lyrics":[22],"and":[23,31,75,126,163,193],"various":[24],"musical":[25],"attributes":[26],"different":[29],"instruments":[30],"melodies.":[32],"Recently,":[33],"methods":[34,49],"that":[35,174],"incorporate":[36],"content":[38,69],"features":[39],"through":[40],"semantic":[41,57,73,128,135],"IDs":[42,66,129],"have":[43],"achieved":[44],"promising":[45],"results.":[46],"However,":[47],"existing":[48],"suffer":[50],"from":[51,67],"two":[52,111],"critical":[53],"limitations:":[54],"1)":[55],"intra-modal":[56],"degradation,":[58],"where":[59,80],"residual-based":[60],"quantization":[61],"processes":[62],"gradually":[63],"decouple":[64],"discrete":[65],"original":[68],"semantics,":[70],"leading":[71],"drift;":[74],"2)":[76],"inter-modal":[77],"modeling":[78],"gaps,":[79],"traditional":[81],"fusion":[82],"strategies":[83],"either":[84],"overlook":[85],"modal-specific":[86,125,161],"details":[87],"or":[88],"fail":[89],"cross-modal":[92,165],"correlations,":[93],"hindering":[94],"comprehensive":[95],"user":[96],"modeling.":[98],"To":[99],"address":[100],"these":[101],"challenges,":[102],"we":[103],"propose":[104],"a":[105,147],"novel":[106],"framework":[109,176,181],"with":[110],"stages.":[112],"first":[115],"stage,":[116,140],"our":[117,175],"Progressive":[118],"Semantic":[119],"Residual":[120],"Quantization":[121],"(PSRQ)":[122],"method":[123],"generates":[124],"modal-joint":[127],"by":[130],"explicitly":[131],"preserving":[132],"prefix":[134],"feature.":[136],"second":[139],"of":[145,187],"users,":[146],"Multi-Codebook":[148],"Cross-Attention":[149],"(MCCA)":[150],"network":[151],"designed":[153],"enable":[155],"simultaneously":[159],"interests":[162],"perceive":[164],"correlations.":[166],"Extensive":[167],"experiments":[168],"on":[169,185],"multiple":[170],"real-world":[171],"datasets":[172],"demonstrate":[173],"outperforms":[177],"state-of-the-art":[178],"baselines.":[179],"This":[180],"has":[182],"been":[183],"deployed":[184],"one":[186],"China's":[188],"largest":[189],"streaming":[191],"platforms,":[192],"online":[194],"A/B":[195],"tests":[196],"confirm":[197],"significant":[198],"improvements":[199],"in":[200],"commercial":[201],"metrics,":[202],"underscoring":[203],"its":[204],"practical":[205],"value":[206],"for":[207],"industrial-scale":[208],"systems.":[210]},"counts_by_year":[{"year":2026,"cited_by_count":3}],"updated_date":"2026-05-21T09:19:25.381259","created_date":"2025-10-10T00:00:00"}