{"id":"https://openalex.org/W4295789422","doi":"https://doi.org/10.1109/tkde.2022.3206441","title":"A Learned Index for Exact Similarity Search in Metric Spaces","display_name":"A Learned Index for Exact Similarity Search in Metric Spaces","publication_year":2022,"publication_date":"2022-09-14","ids":{"openalex":"https://openalex.org/W4295789422","doi":"https://doi.org/10.1109/tkde.2022.3206441"},"language":"en","primary_location":{"id":"doi:10.1109/tkde.2022.3206441","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tkde.2022.3206441","pdf_url":null,"source":{"id":"https://openalex.org/S30698027","display_name":"IEEE Transactions on Knowledge and Data Engineering","issn_l":"1041-4347","issn":["1041-4347","1558-2191","2326-3865"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320439","host_organization_name":"IEEE Computer Society","host_organization_lineage":["https://openalex.org/P4310320439","https://openalex.org/P4310319808"],"host_organization_lineage_names":["IEEE Computer Society","Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Knowledge and Data Engineering","raw_type":"journal-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":false,"oa_status":"closed","oa_url":null,"any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5039607869","display_name":"Yao Tian","orcid":null},"institutions":[{"id":"https://openalex.org/I200769079","display_name":"Hong Kong University of Science and Technology","ror":"https://ror.org/00q4vv597","country_code":"HK","type":"education","lineage":["https://openalex.org/I200769079"]}],"countries":["HK"],"is_corresponding":false,"raw_author_name":"Yao Tian","raw_affiliation_strings":["Department of Computer Science and Engineering, Hong Kong University of Science and Technology, Kowloon, Hong Kong","Department of Computer Science and Engineering, Hong Kong University of Science and Technology, Clear Water Bay, Kowloon, Hong Kong"],"raw_orcid":"https://orcid.org/0000-0001-6876-5059","affiliations":[{"raw_affiliation_string":"Department of Computer Science and Engineering, Hong Kong University of Science and Technology, Kowloon, Hong Kong","institution_ids":["https://openalex.org/I200769079"]},{"raw_affiliation_string":"Department of Computer Science and Engineering, Hong Kong University of Science and Technology, Clear Water Bay, Kowloon, Hong Kong","institution_ids":["https://openalex.org/I200769079"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5041554185","display_name":"Tingyun Yan","orcid":null},"institutions":[{"id":"https://openalex.org/I37987034","display_name":"Guangzhou University","ror":"https://ror.org/05ar8rn06","country_code":"CN","type":"education","lineage":["https://openalex.org/I37987034"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Tingyun Yan","raw_affiliation_strings":["Cyberspace Institute of Advanced Technology, Guangzhou University, Guangzhou, Guangdong, China","Cyberspace Institute of Advanced Technology, Guangzhou University, Guangzhou, China"],"raw_orcid":"https://orcid.org/0000-0002-7487-657X","affiliations":[{"raw_affiliation_string":"Cyberspace Institute of Advanced Technology, Guangzhou University, Guangzhou, Guangdong, China","institution_ids":["https://openalex.org/I37987034"]},{"raw_affiliation_string":"Cyberspace Institute of Advanced Technology, Guangzhou University, Guangzhou, China","institution_ids":["https://openalex.org/I37987034"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5069448247","display_name":"Xi Zhao","orcid":"https://orcid.org/0000-0002-3240-8225"},"institutions":[{"id":"https://openalex.org/I200769079","display_name":"Hong Kong University of Science and Technology","ror":"https://ror.org/00q4vv597","country_code":"HK","type":"education","lineage":["https://openalex.org/I200769079"]}],"countries":["HK"],"is_corresponding":false,"raw_author_name":"Xi Zhao","raw_affiliation_strings":["Department of Computer Science and Engineering, Hong Kong University of Science and Technology, Kowloon, Hong Kong","Department of Computer Science and Engineering, Hong Kong University of Science and Technology, Clear Water Bay, Kowloon, Hong Kong"],"raw_orcid":"https://orcid.org/0000-0002-3240-8225","affiliations":[{"raw_affiliation_string":"Department of Computer Science and Engineering, Hong Kong University of Science and Technology, Kowloon, Hong Kong","institution_ids":["https://openalex.org/I200769079"]},{"raw_affiliation_string":"Department of Computer Science and Engineering, Hong Kong University of Science and Technology, Clear Water Bay, Kowloon, Hong Kong","institution_ids":["https://openalex.org/I200769079"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5022265290","display_name":"Kai Huang","orcid":null},"institutions":[{"id":"https://openalex.org/I200769079","display_name":"Hong Kong University of Science and Technology","ror":"https://ror.org/00q4vv597","country_code":"HK","type":"education","lineage":["https://openalex.org/I200769079"]}],"countries":["HK"],"is_corresponding":false,"raw_author_name":"Kai Huang","raw_affiliation_strings":["Department of Computer Science and Engineering, Hong Kong University of Science and Technology, Kowloon, Hong Kong","Department of Computer Science and Engineering, Hong Kong University of Science and Technology, Clear Water Bay, Kowloon, Hong Kong"],"raw_orcid":"https://orcid.org/0000-0003-3204-7949","affiliations":[{"raw_affiliation_string":"Department of Computer Science and Engineering, Hong Kong University of Science and Technology, Kowloon, Hong Kong","institution_ids":["https://openalex.org/I200769079"]},{"raw_affiliation_string":"Department of Computer Science and Engineering, Hong Kong University of Science and Technology, Clear Water Bay, Kowloon, Hong Kong","institution_ids":["https://openalex.org/I200769079"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5011384237","display_name":"Xiaofang Zhou","orcid":"https://orcid.org/0000-0001-6343-1455"},"institutions":[{"id":"https://openalex.org/I200769079","display_name":"Hong Kong University of Science and Technology","ror":"https://ror.org/00q4vv597","country_code":"HK","type":"education","lineage":["https://openalex.org/I200769079"]}],"countries":["HK"],"is_corresponding":false,"raw_author_name":"Xiaofang Zhou","raw_affiliation_strings":["Department of Computer Science and Engineering, Hong Kong University of Science and Technology, Kowloon, Hong Kong","Department of Computer Science and Engineering, Hong Kong University of Science and Technology, Clear Water Bay, Kowloon, Hong Kong"],"raw_orcid":"https://orcid.org/0000-0001-6343-1455","affiliations":[{"raw_affiliation_string":"Department of Computer Science and Engineering, Hong Kong University of Science and Technology, Kowloon, Hong Kong","institution_ids":["https://openalex.org/I200769079"]},{"raw_affiliation_string":"Department of Computer Science and Engineering, Hong Kong University of Science and Technology, Clear Water Bay, Kowloon, Hong Kong","institution_ids":["https://openalex.org/I200769079"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":2.4364,"has_fulltext":false,"cited_by_count":25,"citation_normalized_percentile":{"value":0.8949005,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":99},"biblio":{"volume":"35","issue":"8","first_page":"7624","last_page":"7638"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11106","display_name":"Data Management and Algorithms","score":0.9998999834060669,"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/T11106","display_name":"Data Management and Algorithms","score":0.9998999834060669,"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"}},{"id":"https://openalex.org/T10538","display_name":"Data Mining Algorithms and Applications","score":0.9966999888420105,"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/T10317","display_name":"Advanced Database Systems and Queries","score":0.9922999739646912,"subfield":{"id":"https://openalex.org/subfields/1705","display_name":"Computer Networks and Communications"},"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/search-engine-indexing","display_name":"Search engine indexing","score":0.784533679485321},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7820675373077393},{"id":"https://openalex.org/keywords/nearest-neighbor-search","display_name":"Nearest neighbor search","score":0.6463677883148193},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.6168398261070251},{"id":"https://openalex.org/keywords/cluster-analysis","display_name":"Cluster analysis","score":0.5792890787124634},{"id":"https://openalex.org/keywords/metric","display_name":"Metric (unit)","score":0.532973051071167},{"id":"https://openalex.org/keywords/metric-space","display_name":"Metric space","score":0.5140522718429565},{"id":"https://openalex.org/keywords/database-index","display_name":"Database index","score":0.4914771318435669},{"id":"https://openalex.org/keywords/similarity","display_name":"Similarity (geometry)","score":0.45776039361953735},{"id":"https://openalex.org/keywords/index","display_name":"Index (typography)","score":0.43576785922050476},{"id":"https://openalex.org/keywords/range-query","display_name":"Range query (database)","score":0.42162904143333435},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.3605092763900757},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.21575549244880676},{"id":"https://openalex.org/keywords/search-engine","display_name":"Search engine","score":0.2123132050037384},{"id":"https://openalex.org/keywords/web-search-query","display_name":"Web search query","score":0.18104732036590576},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.12112385034561157},{"id":"https://openalex.org/keywords/web-query-classification","display_name":"Web query classification","score":0.11659157276153564}],"concepts":[{"id":"https://openalex.org/C75165309","wikidata":"https://www.wikidata.org/wiki/Q2258979","display_name":"Search engine indexing","level":2,"score":0.784533679485321},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7820675373077393},{"id":"https://openalex.org/C116738811","wikidata":"https://www.wikidata.org/wiki/Q608751","display_name":"Nearest neighbor search","level":2,"score":0.6463677883148193},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.6168398261070251},{"id":"https://openalex.org/C73555534","wikidata":"https://www.wikidata.org/wiki/Q622825","display_name":"Cluster analysis","level":2,"score":0.5792890787124634},{"id":"https://openalex.org/C176217482","wikidata":"https://www.wikidata.org/wiki/Q860554","display_name":"Metric (unit)","level":2,"score":0.532973051071167},{"id":"https://openalex.org/C198043062","wikidata":"https://www.wikidata.org/wiki/Q180953","display_name":"Metric space","level":2,"score":0.5140522718429565},{"id":"https://openalex.org/C59276292","wikidata":"https://www.wikidata.org/wiki/Q580427","display_name":"Database index","level":3,"score":0.4914771318435669},{"id":"https://openalex.org/C103278499","wikidata":"https://www.wikidata.org/wiki/Q254465","display_name":"Similarity (geometry)","level":3,"score":0.45776039361953735},{"id":"https://openalex.org/C2777382242","wikidata":"https://www.wikidata.org/wiki/Q6017816","display_name":"Index (typography)","level":2,"score":0.43576785922050476},{"id":"https://openalex.org/C136736807","wikidata":"https://www.wikidata.org/wiki/Q818943","display_name":"Range query (database)","level":5,"score":0.42162904143333435},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.3605092763900757},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.21575549244880676},{"id":"https://openalex.org/C97854310","wikidata":"https://www.wikidata.org/wiki/Q19541","display_name":"Search engine","level":2,"score":0.2123132050037384},{"id":"https://openalex.org/C164120249","wikidata":"https://www.wikidata.org/wiki/Q995982","display_name":"Web search query","level":3,"score":0.18104732036590576},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.12112385034561157},{"id":"https://openalex.org/C118689300","wikidata":"https://www.wikidata.org/wiki/Q7978614","display_name":"Web query classification","level":4,"score":0.11659157276153564},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.0},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.0},{"id":"https://openalex.org/C21547014","wikidata":"https://www.wikidata.org/wiki/Q1423657","display_name":"Operations management","level":1,"score":0.0},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/tkde.2022.3206441","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tkde.2022.3206441","pdf_url":null,"source":{"id":"https://openalex.org/S30698027","display_name":"IEEE Transactions on Knowledge and Data Engineering","issn_l":"1041-4347","issn":["1041-4347","1558-2191","2326-3865"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320439","host_organization_name":"IEEE Computer Society","host_organization_lineage":["https://openalex.org/P4310320439","https://openalex.org/P4310319808"],"host_organization_lineage_names":["IEEE Computer Society","Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Knowledge and Data Engineering","raw_type":"journal-article"},{"id":"pmh:oai:repository.hkust.edu.hk:1783.1-121624","is_oa":false,"landing_page_url":"http://repository.hkust.edu.hk/ir/Record/1783.1-121624","pdf_url":null,"source":{"id":"https://openalex.org/S4306401796","display_name":"Rare & Special e-Zone (The Hong Kong University of Science and Technology)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I200769079","host_organization_name":"Hong Kong University of Science and Technology","host_organization_lineage":["https://openalex.org/I200769079"],"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":"Article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G2074007050","display_name":"\u9762\u5411\u5927\u89c4\u6a21\u79fb\u52a8\u4fe1\u4ee4\u8f68\u8ff9\u7684\u7cbe\u7ec6\u5316\u68c0\u7d22\u4e0e\u5173\u8054\u5206\u6790\u6280\u672f\u7814\u7a76","funder_award_id":"62072125","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"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":41,"referenced_works":["https://openalex.org/W139098497","https://openalex.org/W144859072","https://openalex.org/W1499117135","https://openalex.org/W1981561414","https://openalex.org/W1994655805","https://openalex.org/W1996881001","https://openalex.org/W2001496424","https://openalex.org/W2009233076","https://openalex.org/W2038044292","https://openalex.org/W2073583237","https://openalex.org/W2077612644","https://openalex.org/W2125101937","https://openalex.org/W2134174893","https://openalex.org/W2139263797","https://openalex.org/W2151135734","https://openalex.org/W2153233077","https://openalex.org/W2157092487","https://openalex.org/W2166741129","https://openalex.org/W2345132233","https://openalex.org/W2739676512","https://openalex.org/W2913631065","https://openalex.org/W2962771342","https://openalex.org/W2967734741","https://openalex.org/W3013691234","https://openalex.org/W3020084632","https://openalex.org/W3029532343","https://openalex.org/W3029564598","https://openalex.org/W3081786030","https://openalex.org/W3098304379","https://openalex.org/W3106489949","https://openalex.org/W3107842002","https://openalex.org/W3135300167","https://openalex.org/W3192388590","https://openalex.org/W4242221949","https://openalex.org/W4308288549","https://openalex.org/W6629520646","https://openalex.org/W6682969285","https://openalex.org/W6759199104","https://openalex.org/W6775525759","https://openalex.org/W6776833399","https://openalex.org/W6791517003"],"related_works":["https://openalex.org/W1949910768","https://openalex.org/W2254397067","https://openalex.org/W2405216906","https://openalex.org/W924614198","https://openalex.org/W1505866794","https://openalex.org/W1882921205","https://openalex.org/W1480566255","https://openalex.org/W2013685631","https://openalex.org/W1519492375","https://openalex.org/W2593823386"],"abstract_inverted_index":{"Indexing":[0],"is":[1,92,108],"an":[2,53],"effective":[3],"way":[4],"to":[5,33,51,78,139],"support":[6,79],"efficient":[7,42,80],"query":[8,44,82],"processing":[9,45,83,154],"in":[10,46,84],"large":[11],"databases.":[12],"Recently":[13],"the":[14,89,128,141,179],"concept":[15],"oflearned":[16],"index,":[17],"which":[18],"replaces":[19],"or":[20],"complements":[21],"traditional":[22,185],"index":[23,166],"structures":[24],"with":[25,168,184],"machine":[26],"learning":[27,135],"models,":[28],"has":[29],"been":[30],"actively":[31],"explored":[32],"reduce":[34],"storage":[35],"and":[36,41,75,127,157,164,175,187],"search":[37],"costs.":[38],"However,":[39],"accurate":[40],"similarity":[43,81],"high-dimensional":[47],"metric":[48,85],"spaces":[49],"remains":[50],"be":[52],"open":[54],"challenge.":[55],"In":[56,87],"this":[57],"paper,":[58],"we":[59],"propose":[60],"a":[61,101,112],"novel":[62],"indexing":[63],"approach":[64],"called":[65],"LIMS":[66,182],"that":[67,97],"uses":[68],"data":[69,72,91,104,121,145],"clustering,":[70],"pivot-based":[71],"transformation":[73],"techniques":[74],"learned":[76,189],"indexes":[77,186],"spaces.":[86],"LIMS,":[88,163],"underlying":[90],"partitioned":[93],"into":[94,124],"clusters":[95],"such":[96],"each":[98,118,144],"cluster":[99],"follows":[100],"relatively":[102],"uniform":[103],"distribution.":[105],"Data":[106],"redistribution":[107],"achieved":[109],"by":[110],"utilizing":[111],"small":[113],"number":[114],"of":[115,143,181],"pivots":[116],"for":[117,153,165],"cluster.":[119],"Similar":[120],"are":[122,131,137,151],"mapped":[123,129],"compact":[125],"regions":[126],"values":[130],"totally":[132],"ordinal.":[133],"Machine":[134],"models":[136],"developed":[138],"approximate":[140],"position":[142],"record":[146],"on":[147,162,173],"disk.":[148],"Efficient":[149],"algorithms":[150],"designed":[152],"range":[155],"queries":[156,160],"nearest":[158],"neighbor":[159],"based":[161],"maintenance":[167],"dynamic":[169],"updates.":[170],"Extensive":[171],"experiments":[172],"real-world":[174],"synthetic":[176],"datasets":[177],"demonstrate":[178],"superiority":[180],"compared":[183],"state-of-the-art":[188],"indexes.":[190]},"counts_by_year":[{"year":2026,"cited_by_count":4},{"year":2025,"cited_by_count":9},{"year":2024,"cited_by_count":7},{"year":2023,"cited_by_count":4},{"year":2022,"cited_by_count":1}],"updated_date":"2026-07-29T09:40:50.615796","created_date":"2025-10-10T00:00:00"}