{"id":"https://openalex.org/W4402043003","doi":"https://doi.org/10.14778/3681954.3682010","title":"LITS: An Optimized Learned Index for Strings","display_name":"LITS: An Optimized Learned Index for Strings","publication_year":2024,"publication_date":"2024-07-01","ids":{"openalex":"https://openalex.org/W4402043003","doi":"https://doi.org/10.14778/3681954.3682010"},"language":"en","primary_location":{"id":"doi:10.14778/3681954.3682010","is_oa":false,"landing_page_url":"https://doi.org/10.14778/3681954.3682010","pdf_url":null,"source":{"id":"https://openalex.org/S4210226185","display_name":"Proceedings of the VLDB Endowment","issn_l":"2150-8097","issn":["2150-8097"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319798","host_organization_name":"Association for Computing Machinery","host_organization_lineage":["https://openalex.org/P4310319798"],"host_organization_lineage_names":["Association for Computing Machinery"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the VLDB Endowment","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/A5100743976","display_name":"Yifan Yang","orcid":"https://orcid.org/0000-0002-8986-191X"},"institutions":[{"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"]},{"id":"https://openalex.org/I4210165038","display_name":"University of Chinese Academy of Sciences","ror":"https://ror.org/05qbk4x57","country_code":"CN","type":"education","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210165038"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yifan Yang","raw_affiliation_strings":["SKLP, ACS, Institute of Computing Technology, CAS, University of Chinese Academy of Sciences"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"SKLP, ACS, Institute of Computing Technology, CAS, University of Chinese Academy of Sciences","institution_ids":["https://openalex.org/I4210090176","https://openalex.org/I4210165038"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5101499113","display_name":"Shimin Chen","orcid":"https://orcid.org/0009-0000-1043-6236"},"institutions":[{"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"]},{"id":"https://openalex.org/I4210165038","display_name":"University of Chinese Academy of Sciences","ror":"https://ror.org/05qbk4x57","country_code":"CN","type":"education","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210165038"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Shimin Chen","raw_affiliation_strings":["SKLP, ACS, Institute of Computing Technology, CAS, University of Chinese Academy of Sciences"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"SKLP, ACS, Institute of Computing Technology, CAS, University of Chinese Academy of Sciences","institution_ids":["https://openalex.org/I4210090176","https://openalex.org/I4210165038"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":3.3342,"has_fulltext":false,"cited_by_count":12,"citation_normalized_percentile":{"value":0.93120464,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":97,"max":100},"biblio":{"volume":"17","issue":"11","first_page":"3415","last_page":"3427"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11269","display_name":"Algorithms and Data Compression","score":0.9961000084877014,"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"}},"topics":[{"id":"https://openalex.org/T11269","display_name":"Algorithms and Data Compression","score":0.9961000084877014,"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/T12326","display_name":"Network Packet Processing and Optimization","score":0.9930999875068665,"subfield":{"id":"https://openalex.org/subfields/1708","display_name":"Hardware and Architecture"},"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":0.9926999807357788,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/string","display_name":"String (physics)","score":0.7780480980873108},{"id":"https://openalex.org/keywords/hash-table","display_name":"Hash table","score":0.7411900758743286},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7346855401992798},{"id":"https://openalex.org/keywords/prefix","display_name":"Prefix","score":0.7139935493469238},{"id":"https://openalex.org/keywords/hash-function","display_name":"Hash function","score":0.6661891341209412},{"id":"https://openalex.org/keywords/index","display_name":"Index (typography)","score":0.5148500800132751},{"id":"https://openalex.org/keywords/table","display_name":"Table (database)","score":0.48087719082832336},{"id":"https://openalex.org/keywords/integer","display_name":"Integer (computer science)","score":0.4542650580406189},{"id":"https://openalex.org/keywords/trie","display_name":"Trie","score":0.4471830427646637},{"id":"https://openalex.org/keywords/data-structure","display_name":"Data structure","score":0.43891578912734985},{"id":"https://openalex.org/keywords/node","display_name":"Node (physics)","score":0.4253651201725006},{"id":"https://openalex.org/keywords/exploit","display_name":"Exploit","score":0.41855114698410034},{"id":"https://openalex.org/keywords/point","display_name":"Point (geometry)","score":0.4107096791267395},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.3883669972419739},{"id":"https://openalex.org/keywords/theoretical-computer-science","display_name":"Theoretical computer science","score":0.34654778242111206},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.3416743278503418},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.19547316431999207},{"id":"https://openalex.org/keywords/computer-security","display_name":"Computer security","score":0.08853745460510254},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.08170592784881592},{"id":"https://openalex.org/keywords/operating-system","display_name":"Operating system","score":0.07738113403320312}],"concepts":[{"id":"https://openalex.org/C157486923","wikidata":"https://www.wikidata.org/wiki/Q1376436","display_name":"String (physics)","level":2,"score":0.7780480980873108},{"id":"https://openalex.org/C67388219","wikidata":"https://www.wikidata.org/wiki/Q207440","display_name":"Hash table","level":3,"score":0.7411900758743286},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7346855401992798},{"id":"https://openalex.org/C141603448","wikidata":"https://www.wikidata.org/wiki/Q134830","display_name":"Prefix","level":2,"score":0.7139935493469238},{"id":"https://openalex.org/C99138194","wikidata":"https://www.wikidata.org/wiki/Q183427","display_name":"Hash function","level":2,"score":0.6661891341209412},{"id":"https://openalex.org/C2777382242","wikidata":"https://www.wikidata.org/wiki/Q6017816","display_name":"Index (typography)","level":2,"score":0.5148500800132751},{"id":"https://openalex.org/C45235069","wikidata":"https://www.wikidata.org/wiki/Q278425","display_name":"Table (database)","level":2,"score":0.48087719082832336},{"id":"https://openalex.org/C97137487","wikidata":"https://www.wikidata.org/wiki/Q729138","display_name":"Integer (computer science)","level":2,"score":0.4542650580406189},{"id":"https://openalex.org/C190290938","wikidata":"https://www.wikidata.org/wiki/Q387015","display_name":"Trie","level":3,"score":0.4471830427646637},{"id":"https://openalex.org/C162319229","wikidata":"https://www.wikidata.org/wiki/Q175263","display_name":"Data structure","level":2,"score":0.43891578912734985},{"id":"https://openalex.org/C62611344","wikidata":"https://www.wikidata.org/wiki/Q1062658","display_name":"Node (physics)","level":2,"score":0.4253651201725006},{"id":"https://openalex.org/C165696696","wikidata":"https://www.wikidata.org/wiki/Q11287","display_name":"Exploit","level":2,"score":0.41855114698410034},{"id":"https://openalex.org/C28719098","wikidata":"https://www.wikidata.org/wiki/Q44946","display_name":"Point (geometry)","level":2,"score":0.4107096791267395},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.3883669972419739},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.34654778242111206},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.3416743278503418},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.19547316431999207},{"id":"https://openalex.org/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","level":1,"score":0.08853745460510254},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.08170592784881592},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.07738113403320312},{"id":"https://openalex.org/C37914503","wikidata":"https://www.wikidata.org/wiki/Q156495","display_name":"Mathematical physics","level":1,"score":0.0},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0},{"id":"https://openalex.org/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","level":1,"score":0.0},{"id":"https://openalex.org/C66938386","wikidata":"https://www.wikidata.org/wiki/Q633538","display_name":"Structural engineering","level":1,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"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":1,"locations":[{"id":"doi:10.14778/3681954.3682010","is_oa":false,"landing_page_url":"https://doi.org/10.14778/3681954.3682010","pdf_url":null,"source":{"id":"https://openalex.org/S4210226185","display_name":"Proceedings of the VLDB Endowment","issn_l":"2150-8097","issn":["2150-8097"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319798","host_organization_name":"Association for Computing Machinery","host_organization_lineage":["https://openalex.org/P4310319798"],"host_organization_lineage_names":["Association for Computing Machinery"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the VLDB Endowment","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":20,"referenced_works":["https://openalex.org/W1985229168","https://openalex.org/W2030062409","https://openalex.org/W2125901106","https://openalex.org/W2799221749","https://openalex.org/W2945486614","https://openalex.org/W2962771342","https://openalex.org/W2999149038","https://openalex.org/W3029541804","https://openalex.org/W3031206277","https://openalex.org/W3033065823","https://openalex.org/W3080797093","https://openalex.org/W3103567827","https://openalex.org/W3164254023","https://openalex.org/W4210798430","https://openalex.org/W4284974261","https://openalex.org/W4380433200","https://openalex.org/W4383749424","https://openalex.org/W4384303994","https://openalex.org/W4385071102","https://openalex.org/W6607998620"],"related_works":["https://openalex.org/W54192826","https://openalex.org/W2074308207","https://openalex.org/W2395357979","https://openalex.org/W2795037468","https://openalex.org/W1754202134","https://openalex.org/W1539167344","https://openalex.org/W3092113474","https://openalex.org/W2800763970","https://openalex.org/W59193048","https://openalex.org/W3092534692"],"abstract_inverted_index":{"Index":[0,107],"is":[1,37],"an":[2,116],"important":[3],"component":[4],"in":[5],"database":[6],"systems.":[7],"Learned":[8],"indexes":[9,45],"have":[10],"been":[11],"shown":[12],"to":[13,33,49,85,133,170],"outperform":[14,50],"traditional":[15,51],"tree-based":[16],"index":[17,101],"structures":[18,146],"for":[19,46,102,151,179],"fixed-sized":[20],"integer":[21],"or":[22],"floating":[23],"point":[24,153,180],"keys.":[25,92,137],"However,":[26],"the":[27,30,73,80,87],"application":[28],"of":[29,82,90],"learned":[31,44,83,100,118],"solution":[32],"variable-length":[34],"string":[35,52,91,103,136,162],"keys":[36,60],"under-researched.":[38],"Our":[39,157],"experiments":[40],"show":[41,165],"that":[42,166],"existing":[43],"strings":[47],"fail":[48],"indexes,":[53],"such":[54],"as":[55],"HOT":[56,176],"and":[57,63,66,77,112,127,144,154,172,177,182],"ART.":[58],"String":[59],"are":[61],"long":[62],"variable":[64],"sized,":[65],"often":[67],"contain":[68],"skewed":[69,88],"prefixes,":[70],"which":[71],"make":[72],"last-mile":[74],"search":[75],"expensive,":[76],"adversely":[78],"impact":[79],"capability":[81],"models":[84],"capture":[86],"distribution":[89],"In":[93],"this":[94],"paper,":[95],"we":[96],"propose":[97,115],"a":[98,121,128,148],"novel":[99],"keys,":[104],"LITS":[105,139,167],"(Learned":[106],"with":[108,147],"Hash-enhanced":[109,123],"Prefix":[110,124],"Table":[111,125],"Subtries).":[113],"We":[114],"optimized":[117],"model,":[119],"combining":[120],"global":[122],"(HPT)":[126],"per-node":[129],"local":[130],"linear":[131],"model":[132,150],"better":[134],"distinguish":[135],"Moreover,":[138],"exploits":[140],"compact":[141],"leaf":[142],"nodes":[143],"hybrid":[145],"PMSS":[149],"efficient":[152],"range":[155],"operations.":[156],"experimental":[158],"results":[159],"using":[160],"eleven":[161],"data":[163],"sets":[164],"achieves":[168],"up":[169],"2.43x":[171],"2.27x":[173],"improvement":[174],"over":[175],"ART":[178],"operations,":[181],"attains":[183],"comparable":[184],"scan":[185],"performance.":[186]},"counts_by_year":[{"year":2026,"cited_by_count":8},{"year":2025,"cited_by_count":4}],"updated_date":"2026-05-21T06:26:12.895304","created_date":"2025-10-10T00:00:00"}