{"id":"https://openalex.org/W4396843764","doi":"https://doi.org/10.1145/3589335.3651558","title":"Discrete Semantic Tokenization for Deep CTR Prediction","display_name":"Discrete Semantic Tokenization for Deep CTR Prediction","publication_year":2024,"publication_date":"2024-05-12","ids":{"openalex":"https://openalex.org/W4396843764","doi":"https://doi.org/10.1145/3589335.3651558"},"language":"en","primary_location":{"id":"doi:10.1145/3589335.3651558","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3589335.3651558","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3589335.3651558","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Companion Proceedings of the ACM Web Conference 2024","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://dl.acm.org/doi/pdf/10.1145/3589335.3651558","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5019877925","display_name":"Qijiong Liu","orcid":"https://orcid.org/0000-0001-6087-383X"},"institutions":[{"id":"https://openalex.org/I14243506","display_name":"Hong Kong Polytechnic University","ror":"https://ror.org/0030zas98","country_code":"HK","type":"education","lineage":["https://openalex.org/I14243506"]}],"countries":["HK"],"is_corresponding":true,"raw_author_name":"Qijiong Liu","raw_affiliation_strings":["PolyU, Hong Kong, China"],"affiliations":[{"raw_affiliation_string":"PolyU, Hong Kong, China","institution_ids":["https://openalex.org/I14243506"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5017709678","display_name":"Hengchang Hu","orcid":"https://orcid.org/0000-0001-7847-0641"},"institutions":[{"id":"https://openalex.org/I165932596","display_name":"National University of Singapore","ror":"https://ror.org/01tgyzw49","country_code":"SG","type":"education","lineage":["https://openalex.org/I165932596"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Hengchang Hu","raw_affiliation_strings":["National University of Singapore, Singapore, Singapore"],"affiliations":[{"raw_affiliation_string":"National University of Singapore, Singapore, Singapore","institution_ids":["https://openalex.org/I165932596"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5055470301","display_name":"Jiahao Wu","orcid":"https://orcid.org/0000-0002-4085-5295"},"institutions":[{"id":"https://openalex.org/I14243506","display_name":"Hong Kong Polytechnic University","ror":"https://ror.org/0030zas98","country_code":"HK","type":"education","lineage":["https://openalex.org/I14243506"]}],"countries":["HK"],"is_corresponding":false,"raw_author_name":"Jiahao Wu","raw_affiliation_strings":["PolyU, Hong Kong, China"],"affiliations":[{"raw_affiliation_string":"PolyU, Hong Kong, China","institution_ids":["https://openalex.org/I14243506"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5048669373","display_name":"Jieming Zhu","orcid":"https://orcid.org/0000-0002-5666-8320"},"institutions":[{"id":"https://openalex.org/I2250955327","display_name":"Huawei Technologies (China)","ror":"https://ror.org/00cmhce21","country_code":"CN","type":"company","lineage":["https://openalex.org/I2250955327"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jieming Zhu","raw_affiliation_strings":["Huawei Noah's Ark Lab, Shenzhen, China"],"affiliations":[{"raw_affiliation_string":"Huawei Noah's Ark Lab, Shenzhen, China","institution_ids":["https://openalex.org/I2250955327"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5066305082","display_name":"Min\u2010Yen Kan","orcid":"https://orcid.org/0000-0001-8507-3716"},"institutions":[{"id":"https://openalex.org/I165932596","display_name":"National University of Singapore","ror":"https://ror.org/01tgyzw49","country_code":"SG","type":"education","lineage":["https://openalex.org/I165932596"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Min-Yen Kan","raw_affiliation_strings":["National University of Singapore, Singapore, Singapore"],"affiliations":[{"raw_affiliation_string":"National University of Singapore, Singapore, Singapore","institution_ids":["https://openalex.org/I165932596"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5101981128","display_name":"Xiao-Ming Wu","orcid":"https://orcid.org/0000-0002-3130-0554"},"institutions":[{"id":"https://openalex.org/I14243506","display_name":"Hong Kong Polytechnic University","ror":"https://ror.org/0030zas98","country_code":"HK","type":"education","lineage":["https://openalex.org/I14243506"]}],"countries":["HK"],"is_corresponding":false,"raw_author_name":"Xiao-Ming Wu","raw_affiliation_strings":["PolyU, Hong Kong, Hong Kong"],"affiliations":[{"raw_affiliation_string":"PolyU, Hong Kong, Hong Kong","institution_ids":["https://openalex.org/I14243506"]}]}],"institutions":[],"countries_distinct_count":3,"institutions_distinct_count":6,"corresponding_author_ids":["https://openalex.org/A5019877925"],"corresponding_institution_ids":["https://openalex.org/I14243506"],"apc_list":null,"apc_paid":null,"fwci":2.4266,"has_fulltext":false,"cited_by_count":6,"citation_normalized_percentile":{"value":0.88570118,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"919","last_page":"922"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12422","display_name":"Radiomics and Machine Learning in Medical Imaging","score":0.9955000281333923,"subfield":{"id":"https://openalex.org/subfields/2741","display_name":"Radiology, Nuclear Medicine and Imaging"},"field":{"id":"https://openalex.org/fields/27","display_name":"Medicine"},"domain":{"id":"https://openalex.org/domains/4","display_name":"Health Sciences"}},"topics":[{"id":"https://openalex.org/T12422","display_name":"Radiomics and Machine Learning in Medical Imaging","score":0.9955000281333923,"subfield":{"id":"https://openalex.org/subfields/2741","display_name":"Radiology, Nuclear Medicine and Imaging"},"field":{"id":"https://openalex.org/fields/27","display_name":"Medicine"},"domain":{"id":"https://openalex.org/domains/4","display_name":"Health Sciences"}},{"id":"https://openalex.org/T10052","display_name":"Medical Image Segmentation Techniques","score":0.9781000018119812,"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"}},{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","score":0.977400004863739,"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/computer-science","display_name":"Computer science","score":0.741597056388855},{"id":"https://openalex.org/keywords/lexical-analysis","display_name":"Lexical analysis","score":0.693231463432312},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5748691558837891},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.4839475452899933}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.741597056388855},{"id":"https://openalex.org/C176982825","wikidata":"https://www.wikidata.org/wiki/Q835922","display_name":"Lexical analysis","level":2,"score":0.693231463432312},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5748691558837891},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.4839475452899933}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3589335.3651558","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3589335.3651558","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3589335.3651558","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Companion Proceedings of the ACM Web Conference 2024","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.1145/3589335.3651558","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3589335.3651558","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3589335.3651558","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Companion Proceedings of the ACM Web Conference 2024","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4396843764.pdf"},"referenced_works_count":3,"referenced_works":["https://openalex.org/W2069870183","https://openalex.org/W2723293840","https://openalex.org/W4284681563"],"related_works":["https://openalex.org/W2748952813","https://openalex.org/W4300598845","https://openalex.org/W3204019825","https://openalex.org/W2601638452","https://openalex.org/W2285263069","https://openalex.org/W4319309671","https://openalex.org/W4376107815","https://openalex.org/W4319309603","https://openalex.org/W1599985958","https://openalex.org/W1748623649"],"abstract_inverted_index":{"Incorporating":[0],"item":[1,30,46,86],"content":[2],"information":[3],"into":[4,33,50,106],"click-through":[5],"rate":[6],"(CTR)":[7],"prediction":[8],"models":[9],"remains":[10],"a":[11,70,76,96,114],"challenge,":[12],"especially":[13],"with":[14,109],"the":[15,42,61,121,135],"time":[16,59],"and":[17,29,47,74,85,92,112,137],"space":[18,37,141],"constraints":[19],"of":[20,63,123,143],"industrial":[21],"scenarios.":[22],"The":[23],"content-encoding":[24],"paradigm,":[25],"which":[26],"integrates":[27],"user":[28,48,84],"encoders":[31],"directly":[32],"CTR":[34,146],"models,":[35],"prioritizes":[36],"over":[38],"time.":[39],"In":[40,65],"contrast,":[41],"embedding-based":[43],"paradigm":[44,73],"transforms":[45],"semantics":[49],"latent":[51],"embeddings,":[52],"subsequently":[53],"caching":[54],"them":[55],"to":[56,119],"optimize":[57],"processing":[58],"at":[60],"expense":[62],"space.":[64],"this":[66],"paper,":[67],"we":[68],"introduce":[69],"new":[71],"semantic-token":[72],"propose":[75],"discrete":[77,107],"semantic":[78],"tokenization":[79],"approach,":[80],"namely":[81],"UIST,":[82],"for":[83,145],"representation.":[87],"UIST":[88,101,144],"facilitates":[89],"swift":[90],"training":[91],"inference":[93,117],"while":[94],"maintaining":[95],"conservative":[97],"memory":[98],"footprint.":[99],"Specifically,":[100],"quantizes":[102],"dense":[103],"embedding":[104],"vectors":[105],"tokens":[108],"shorter":[110],"lengths":[111],"employs":[113],"hierarchical":[115],"mixture":[116],"module":[118],"weigh":[120],"contribution":[122],"each":[124],"user-item":[125],"token":[126],"pair.":[127],"Our":[128],"experimental":[129],"results":[130],"on":[131],"news":[132],"recommendation":[133],"showcase":[134],"effectiveness":[136],"efficiency":[138],"(about":[139],"200-fold":[140],"compression)":[142],"prediction.":[147]},"counts_by_year":[{"year":2025,"cited_by_count":5},{"year":2024,"cited_by_count":1}],"updated_date":"2026-03-27T05:58:40.876381","created_date":"2025-10-10T00:00:00"}