{"id":"https://openalex.org/W4385764281","doi":"https://doi.org/10.24963/ijcai.2023/728","title":"Learning Discrete Representations via Constrained Clustering for Effective and Efficient Dense Retrieval (Extended Abstract)","display_name":"Learning Discrete Representations via Constrained Clustering for Effective and Efficient Dense Retrieval (Extended Abstract)","publication_year":2023,"publication_date":"2023-08-01","ids":{"openalex":"https://openalex.org/W4385764281","doi":"https://doi.org/10.24963/ijcai.2023/728"},"language":"en","primary_location":{"id":"doi:10.24963/ijcai.2023/728","is_oa":true,"landing_page_url":"http://dx.doi.org/10.24963/ijcai.2023/728","pdf_url":"https://www.ijcai.org/proceedings/2023/0728.pdf","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Thirty-Second International Joint Conference on Artificial Intelligence","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://www.ijcai.org/proceedings/2023/0728.pdf","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5023520034","display_name":"Jingtao Zhan","orcid":"https://orcid.org/0000-0002-7253-5245"},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jingtao Zhan","raw_affiliation_strings":["Department of Computer Science and Technology, Beijing National Research Center for Information Science and Technology, Tsinghua University, Beijing 100084, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science and Technology, Beijing National Research Center for Information Science and Technology, Tsinghua University, Beijing 100084, China","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5072119199","display_name":"Jiaxin Mao","orcid":"https://orcid.org/0000-0002-9257-5498"},"institutions":[{"id":"https://openalex.org/I78988378","display_name":"Renmin University of China","ror":"https://ror.org/041pakw92","country_code":"CN","type":"education","lineage":["https://openalex.org/I78988378"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jiaxin Mao","raw_affiliation_strings":["Beijing Key Laboratory of Big Data Management and Analysis Methods, Gaoling School of Artificial Intelligence, Renmin University of China, Beijing 100872, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Beijing Key Laboratory of Big Data Management and Analysis Methods, Gaoling School of Artificial Intelligence, Renmin University of China, Beijing 100872, China","institution_ids":["https://openalex.org/I78988378"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100668121","display_name":"Yiqun Liu","orcid":"https://orcid.org/0000-0002-0140-4512"},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Yiqun Liu","raw_affiliation_strings":["Department of Computer Science and Technology, Beijing National Research Center for Information Science and Technology, Tsinghua University, Beijing 100084, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science and Technology, Beijing National Research Center for Information Science and Technology, Tsinghua University, Beijing 100084, China","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5088621320","display_name":"Jiafeng Guo","orcid":"https://orcid.org/0000-0002-9509-8674"},"institutions":[{"id":"https://openalex.org/I19820366","display_name":"Chinese Academy of Sciences","ror":"https://ror.org/034t30j35","country_code":"CN","type":"government","lineage":["https://openalex.org/I19820366"]},{"id":"https://openalex.org/I4210090176","display_name":"Institute of Computing Technology","ror":"https://ror.org/0090r4d87","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210090176"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jiafeng Guo","raw_affiliation_strings":["CAS Key Lab of Network Data Science and Technology, Institute of Computing Technology, Chinese Academy of Sciences, Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"CAS Key Lab of Network Data Science and Technology, Institute of Computing Technology, Chinese Academy of Sciences, Beijing, China","institution_ids":["https://openalex.org/I4210090176","https://openalex.org/I19820366"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100402925","display_name":"Min Zhang","orcid":"https://orcid.org/0000-0002-6059-3798"},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Min Zhang","raw_affiliation_strings":["Department of Computer Science and Technology, Beijing National Research Center for Information Science and Technology, Tsinghua University, Beijing 100084, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science and Technology, Beijing National Research Center for Information Science and Technology, Tsinghua University, Beijing 100084, China","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100760812","display_name":"Shaoping Ma","orcid":"https://orcid.org/0000-0002-8762-8268"},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Shaoping Ma","raw_affiliation_strings":["Department of Computer Science and Technology, Beijing National Research Center for Information Science and Technology, Tsinghua University, Beijing 100084, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science and Technology, Beijing National Research Center for Information Science and Technology, Tsinghua University, Beijing 100084, China","institution_ids":["https://openalex.org/I99065089"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5100668121"],"corresponding_institution_ids":["https://openalex.org/I99065089"],"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":"6504","last_page":"6508"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10627","display_name":"Advanced Image and Video Retrieval Techniques","score":0.9998000264167786,"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"}},"topics":[{"id":"https://openalex.org/T10627","display_name":"Advanced Image and Video Retrieval Techniques","score":0.9998000264167786,"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/T10824","display_name":"Image Retrieval and Classification Techniques","score":0.9987999796867371,"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/T11307","display_name":"Domain Adaptation and Few-Shot Learning","score":0.994700014591217,"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":0.7028772830963135},{"id":"https://openalex.org/keywords/cluster-analysis","display_name":"Cluster analysis","score":0.6924084424972534},{"id":"https://openalex.org/keywords/quantization","display_name":"Quantization (signal processing)","score":0.561151385307312},{"id":"https://openalex.org/keywords/vector-quantization","display_name":"Vector quantization","score":0.5584015250205994},{"id":"https://openalex.org/keywords/search-engine-indexing","display_name":"Search engine indexing","score":0.5239714980125427},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4210798144340515},{"id":"https://openalex.org/keywords/constraint","display_name":"Constraint (computer-aided design)","score":0.4151774048805237},{"id":"https://openalex.org/keywords/boosting","display_name":"Boosting (machine learning)","score":0.41042762994766235},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.3802870810031891},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.3195170760154724},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.20620307326316833}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7028772830963135},{"id":"https://openalex.org/C73555534","wikidata":"https://www.wikidata.org/wiki/Q622825","display_name":"Cluster analysis","level":2,"score":0.6924084424972534},{"id":"https://openalex.org/C28855332","wikidata":"https://www.wikidata.org/wiki/Q198099","display_name":"Quantization (signal processing)","level":2,"score":0.561151385307312},{"id":"https://openalex.org/C199833920","wikidata":"https://www.wikidata.org/wiki/Q612536","display_name":"Vector quantization","level":2,"score":0.5584015250205994},{"id":"https://openalex.org/C75165309","wikidata":"https://www.wikidata.org/wiki/Q2258979","display_name":"Search engine indexing","level":2,"score":0.5239714980125427},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4210798144340515},{"id":"https://openalex.org/C2776036281","wikidata":"https://www.wikidata.org/wiki/Q48769818","display_name":"Constraint (computer-aided design)","level":2,"score":0.4151774048805237},{"id":"https://openalex.org/C46686674","wikidata":"https://www.wikidata.org/wiki/Q466303","display_name":"Boosting (machine learning)","level":2,"score":0.41042762994766235},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3802870810031891},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.3195170760154724},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.20620307326316833},{"id":"https://openalex.org/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.24963/ijcai.2023/728","is_oa":true,"landing_page_url":"http://dx.doi.org/10.24963/ijcai.2023/728","pdf_url":"https://www.ijcai.org/proceedings/2023/0728.pdf","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Thirty-Second International Joint Conference on Artificial Intelligence","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.24963/ijcai.2023/728","is_oa":true,"landing_page_url":"http://dx.doi.org/10.24963/ijcai.2023/728","pdf_url":"https://www.ijcai.org/proceedings/2023/0728.pdf","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Thirty-Second International Joint Conference on Artificial Intelligence","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G3308505718","display_name":null,"funder_award_id":"61732008","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"},{"id":"https://openalex.org/F4320322392","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549"}],"has_content":{"grobid_xml":false,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4385764281.pdf"},"referenced_works_count":22,"referenced_works":["https://openalex.org/W1974647172","https://openalex.org/W2077815765","https://openalex.org/W2124509324","https://openalex.org/W2158131535","https://openalex.org/W2937036051","https://openalex.org/W2951534261","https://openalex.org/W2969473510","https://openalex.org/W2982096936","https://openalex.org/W3024786184","https://openalex.org/W3034439313","https://openalex.org/W3037128914","https://openalex.org/W3093955333","https://openalex.org/W3099700870","https://openalex.org/W3118668786","https://openalex.org/W3154755316","https://openalex.org/W3155895380","https://openalex.org/W3172119680","https://openalex.org/W3174203100","https://openalex.org/W3175111331","https://openalex.org/W3209791570","https://openalex.org/W4251326898","https://openalex.org/W4298323699"],"related_works":["https://openalex.org/W2125652721","https://openalex.org/W1540371141","https://openalex.org/W4231274751","https://openalex.org/W1549363203","https://openalex.org/W2154063878","https://openalex.org/W2556012038","https://openalex.org/W1489772951","https://openalex.org/W1538046993","https://openalex.org/W2571255492","https://openalex.org/W3209251257"],"abstract_inverted_index":{"Dense":[0],"Retrieval~(DR)":[1],"has":[2],"achieved":[3],"state-of-the-art":[4],"first-stage":[5],"ranking":[6],"effectiveness.":[7],"However,":[8],"the":[9,19,28,56,83,91,98],"efficiency":[10],"of":[11,23,115,121],"most":[12],"existing":[13,116],"DR":[14],"models":[15,74,118],"is":[16],"limited":[17],"by":[18],"large":[20],"memory":[21,124],"cost":[22],"storing":[24],"dense":[25],"vectors":[26],"and":[27,55,65,126],"time-consuming":[29],"nearest":[30],"neighbor":[31],"search~(NNS)":[32],"in":[33,119],"vector":[34],"space.":[35],"Therefore,":[36],"we":[37],"present":[38],"RepCONC,":[39],"a":[40,77,112],"novel":[41],"retrieval":[42,117,122],"model":[43],"that":[44,97,108],"learns":[45],"discrete":[46,62],"Representations":[47],"via":[48],"CONstrained":[49],"Clustering.":[50],"RepCONC":[51,109],"jointly":[52],"trains":[53],"dual-encoders":[54],"Product":[57],"Quantization~(PQ)":[58],"method":[59],"to":[60,86],"learn":[61],"document":[63,84],"representations":[64],"enables":[66],"fast":[67],"approximate":[68],"NNS":[69],"with":[70],"compact":[71],"indexes.":[72],"It":[73],"quantization":[75,92],"as":[76],"constrained":[78],"clustering":[79,100],"process,":[80],"which":[81],"requires":[82],"embeddings":[85],"be":[87],"uniformly":[88],"clustered":[89],"around":[90],"centroids.":[93],"We":[94],"theoretically":[95],"demonstrate":[96],"uniform":[99],"constraint":[101],"facilitates":[102],"representation":[103],"distinguishability.":[104],"Extensive":[105],"experiments":[106],"show":[107],"substantially":[110],"outperforms":[111],"wide":[113],"range":[114],"terms":[120],"effectiveness,":[123],"efficiency,":[125],"time":[127],"efficiency.":[128]},"counts_by_year":[],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}