{"id":"https://openalex.org/W7133338326","doi":"https://doi.org/10.48550/arxiv.2603.00632","title":"Stop Treating Collisions Equally: Qualification-Aware Semantic ID Learning for Recommendation at Industrial Scale","display_name":"Stop Treating Collisions Equally: Qualification-Aware Semantic ID Learning for Recommendation at Industrial Scale","publication_year":2026,"publication_date":"2026-02-28","ids":{"openalex":"https://openalex.org/W7133338326","doi":"https://doi.org/10.48550/arxiv.2603.00632"},"language":null,"primary_location":{"id":"doi:10.48550/arxiv.2603.00632","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2603.00632","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":"article"},"type":"preprint","indexed_in":["datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://doi.org/10.48550/arxiv.2603.00632","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5127906737","display_name":"Zheng Hu","orcid":null},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Hu, Zheng","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5127999128","display_name":"Yuxin Chen","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Chen, Yuxin","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5128026887","display_name":"Yongsen Pan","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Pan, Yongsen","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5127983179","display_name":"Xu Yuan","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yuan, Xu","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5073373856","display_name":"Yuting Yin","orcid":"https://orcid.org/0000-0003-0182-5330"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yin, Yuting","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5128011714","display_name":"Daoyuan Wang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Wang, Daoyuan","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5128029173","display_name":"Boyang Xia","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Xia, Boyang","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5111319795","display_name":"Zefei Luo","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Luo, Zefei","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":null,"display_name":"Wang, Hongyang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Wang, Hongyang","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5123203564","display_name":"Songhao Ni","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Ni, Songhao","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5113112805","display_name":"Dongxu Liang","orcid":"https://orcid.org/0009-0004-6373-5298"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Liang, Dongxu","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5128004073","display_name":"Jun Wang (5906)","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Wang, Jun","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5128025033","display_name":"Shimin Cai","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Cai, Shimin","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5127953082","display_name":"Tao Zhou","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zhou, Tao","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5127975087","display_name":"Fuji Ren","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Ren, Fuji","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5127923667","display_name":"Wenwu Ou","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Ou, Wenwu","raw_affiliation_strings":[],"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":16,"corresponding_author_ids":["https://openalex.org/A5127906737"],"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":0.5982000231742859,"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":0.5982000231742859,"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/T11273","display_name":"Advanced Graph Neural Networks","score":0.05620000138878822,"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/T11714","display_name":"Multimodal Machine Learning Applications","score":0.03819999843835831,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"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/encoder","display_name":"Encoder","score":0.5378000140190125},{"id":"https://openalex.org/keywords/redundancy","display_name":"Redundancy (engineering)","score":0.4851999878883362},{"id":"https://openalex.org/keywords/margin","display_name":"Margin (machine learning)","score":0.45649999380111694},{"id":"https://openalex.org/keywords/semantics","display_name":"Semantics (computer science)","score":0.39649999141693115},{"id":"https://openalex.org/keywords/abstraction","display_name":"Abstraction","score":0.37689998745918274},{"id":"https://openalex.org/keywords/ranking","display_name":"Ranking (information retrieval)","score":0.3675999939441681},{"id":"https://openalex.org/keywords/range","display_name":"Range (aeronautics)","score":0.34290000796318054},{"id":"https://openalex.org/keywords/generative-grammar","display_name":"Generative grammar","score":0.3264000117778778},{"id":"https://openalex.org/keywords/generative-model","display_name":"Generative model","score":0.3221000134944916}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6945000290870667},{"id":"https://openalex.org/C118505674","wikidata":"https://www.wikidata.org/wiki/Q42586063","display_name":"Encoder","level":2,"score":0.5378000140190125},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5072000026702881},{"id":"https://openalex.org/C152124472","wikidata":"https://www.wikidata.org/wiki/Q1204361","display_name":"Redundancy (engineering)","level":2,"score":0.4851999878883362},{"id":"https://openalex.org/C774472","wikidata":"https://www.wikidata.org/wiki/Q6760393","display_name":"Margin (machine learning)","level":2,"score":0.45649999380111694},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.39649999141693115},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.38199999928474426},{"id":"https://openalex.org/C124304363","wikidata":"https://www.wikidata.org/wiki/Q673661","display_name":"Abstraction","level":2,"score":0.37689998745918274},{"id":"https://openalex.org/C189430467","wikidata":"https://www.wikidata.org/wiki/Q7293293","display_name":"Ranking (information retrieval)","level":2,"score":0.3675999939441681},{"id":"https://openalex.org/C204323151","wikidata":"https://www.wikidata.org/wiki/Q905424","display_name":"Range (aeronautics)","level":2,"score":0.34290000796318054},{"id":"https://openalex.org/C39890363","wikidata":"https://www.wikidata.org/wiki/Q36108","display_name":"Generative grammar","level":2,"score":0.3264000117778778},{"id":"https://openalex.org/C167966045","wikidata":"https://www.wikidata.org/wiki/Q5532625","display_name":"Generative model","level":3,"score":0.3221000134944916},{"id":"https://openalex.org/C101738243","wikidata":"https://www.wikidata.org/wiki/Q786435","display_name":"Autoencoder","level":3,"score":0.31949999928474426},{"id":"https://openalex.org/C59404180","wikidata":"https://www.wikidata.org/wiki/Q17013334","display_name":"Feature learning","level":2,"score":0.3125999867916107},{"id":"https://openalex.org/C12725497","wikidata":"https://www.wikidata.org/wiki/Q810247","display_name":"Baseline (sea)","level":2,"score":0.29420000314712524},{"id":"https://openalex.org/C2778755073","wikidata":"https://www.wikidata.org/wiki/Q10858537","display_name":"Scale (ratio)","level":2,"score":0.2921999990940094},{"id":"https://openalex.org/C118930307","wikidata":"https://www.wikidata.org/wiki/Q600590","display_name":"Tuple","level":2,"score":0.29170000553131104},{"id":"https://openalex.org/C99844830","wikidata":"https://www.wikidata.org/wiki/Q102441924","display_name":"Scaling","level":2,"score":0.2913999855518341},{"id":"https://openalex.org/C90312973","wikidata":"https://www.wikidata.org/wiki/Q7449052","display_name":"Semantic data model","level":2,"score":0.29100000858306885},{"id":"https://openalex.org/C130318100","wikidata":"https://www.wikidata.org/wiki/Q2268914","display_name":"Semantic similarity","level":2,"score":0.2802000045776367},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.2770000100135803},{"id":"https://openalex.org/C121704057","wikidata":"https://www.wikidata.org/wiki/Q352070","display_name":"Collision","level":2,"score":0.2736999988555908},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.26649999618530273},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.26440000534057617},{"id":"https://openalex.org/C198942812","wikidata":"https://www.wikidata.org/wiki/Q496618","display_name":"Semantic property","level":2,"score":0.2630999982357025},{"id":"https://openalex.org/C2778572836","wikidata":"https://www.wikidata.org/wiki/Q380933","display_name":"Space (punctuation)","level":2,"score":0.25839999318122864},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.2581999897956848},{"id":"https://openalex.org/C48145219","wikidata":"https://www.wikidata.org/wiki/Q1335365","display_name":"Security token","level":2,"score":0.25040000677108765}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.48550/arxiv.2603.00632","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2603.00632","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":"article"}],"best_oa_location":{"id":"doi:10.48550/arxiv.2603.00632","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2603.00632","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":"article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Semantic":[0,93],"IDs":[1],"(SIDs)":[2],"are":[3,48,64],"compact":[4],"discrete":[5],"representations":[6],"derived":[7],"from":[8,79],"multimodal":[9],"item":[10],"features,":[11],"serving":[12],"as":[13],"a":[14,158,209,242],"unified":[15],"abstraction":[16],"for":[17],"ID-based":[18],"and":[19,110,140,172,219,240],"generative":[20],"recommendation.":[21],"However,":[22],"learning":[23,246],"high-quality":[24],"SIDs":[25,103],"remains":[26],"challenging":[27],"due":[28],"to":[29,41,150,162,228],"two":[30,121],"issues.":[31],"(1)":[32],"Collision":[33],"problem:":[34],"the":[35,112,137,192,234],"quantized":[36],"token":[37],"space":[38],"is":[39,238],"prone":[40],"collisions,":[42],"in":[43,57],"which":[44,126,145],"semantically":[45,73],"distinct":[46],"items":[47],"assigned":[49],"identical":[50],"or":[51,82],"overly":[52],"similar":[53],"SID":[54,129,197,245],"compositions,":[55],"resulting":[56],"semantic":[58],"entanglement.":[59],"(2)":[60],"Collision-signal":[61],"heterogeneity:":[62],"collisions":[63],"not":[65],"uniformly":[66],"harmful.":[67],"Some":[68],"reflect":[69],"genuine":[70],"conflicts":[71],"between":[72],"unrelated":[74],"items,":[75],"while":[76,195],"others":[77],"stem":[78],"benign":[80,148],"redundancy":[81],"systematic":[83],"data":[84,174],"effects.":[85],"To":[86],"address":[87],"these":[88],"challenges,":[89],"we":[90,231],"propose":[91],"Qualification-Aware":[92],"ID":[94],"Learning":[95],"(QuaSID),":[96],"an":[97,201],"end-to-end":[98],"framework":[99],"that":[100,233],"learns":[101],"collision-qualified":[102],"by":[104,115,189,217,226],"selectively":[105],"repelling":[106],"qualified":[107],"conflict":[108],"pairs":[109],"scaling":[111],"repulsion":[113,152,236],"strength":[114],"collision":[116],"severity.":[117],"QuaSID":[118,156,180,213],"consists":[119],"of":[120,244],"mechanisms:":[122],"Hamming-guided":[123],"Margin":[124],"Repulsion,":[125],"translates":[127],"low-Hamming":[128],"overlaps":[130,149],"into":[131,166],"explicit,":[132],"severity-scaled":[133],"geometric":[134],"constraints":[135],"on":[136,169,205,223],"encoder":[138],"space;":[139],"Conflict-Aware":[141],"Valid":[142],"Pair":[143],"Masking,":[144],"masks":[146],"protocol-induced":[147],"denoise":[151],"supervision.":[153],"In":[154,200],"addition,":[155],"incorporates":[157],"dual-tower":[159],"contrastive":[160],"objective":[161],"inject":[163],"collaborative":[164],"signals":[165],"tokenization.":[167],"Experiments":[168],"public":[170,178],"benchmarks":[171],"industrial":[173],"validate":[175],"QuaSID.":[176],"On":[177],"datasets,":[179],"consistently":[181],"outperforms":[182],"strong":[183],"baselines,":[184],"improving":[185],"top-K":[186],"ranking":[187,215],"quality":[188],"5.9%":[190],"over":[191],"best":[193],"baseline":[194],"increasing":[196],"composition":[198],"diversity.":[199],"online":[202],"A/B":[203],"test":[204],"Kuaishou":[206],"e-commerce":[207],"with":[208],"5%":[210],"traffic":[211],"split,":[212],"increases":[214],"GMV-S2":[216],"2.38%":[218],"improves":[220],"completed":[221],"orders":[222],"cold-start":[224],"retrieval":[225],"up":[227],"6.42%.":[229],"Finally,":[230],"show":[232],"proposed":[235],"loss":[237],"plug-and-play":[239],"enhances":[241],"range":[243],"frameworks":[247],"across":[248],"datasets.":[249]},"counts_by_year":[],"updated_date":"2026-04-21T08:09:41.155169","created_date":"2026-03-04T00:00:00"}