{"id":"https://openalex.org/W2901487151","doi":"https://doi.org/10.1145/3291992.3291993","title":"The Potential of Learned Index Structures for Index Compression","display_name":"The Potential of Learned Index Structures for Index Compression","publication_year":2018,"publication_date":"2018-12-04","ids":{"openalex":"https://openalex.org/W2901487151","doi":"https://doi.org/10.1145/3291992.3291993","mag":"2901487151"},"language":"en","primary_location":{"id":"doi:10.1145/3291992.3291993","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3291992.3291993","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 23rd Australasian Document Computing Symposium","raw_type":"proceedings-article"},"type":"preprint","indexed_in":["arxiv","crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/1811.06678","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5002072527","display_name":"Harrie Oosterhuis","orcid":"https://orcid.org/0000-0002-0458-9233"},"institutions":[{"id":"https://openalex.org/I887064364","display_name":"University of Amsterdam","ror":"https://ror.org/04dkp9463","country_code":"NL","type":"education","lineage":["https://openalex.org/I887064364"]}],"countries":["NL"],"is_corresponding":true,"raw_author_name":"Harrie Oosterhuis","raw_affiliation_strings":["University of Amsterdam"],"affiliations":[{"raw_affiliation_string":"University of Amsterdam","institution_ids":["https://openalex.org/I887064364"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5070937840","display_name":"J. Shane Culpepper","orcid":"https://orcid.org/0000-0002-1902-9087"},"institutions":[{"id":"https://openalex.org/I4210095297","display_name":"MIT University","ror":"https://ror.org/00v140q16","country_code":"MK","type":"education","lineage":["https://openalex.org/I4210095297"]},{"id":"https://openalex.org/I82951845","display_name":"RMIT University","ror":"https://ror.org/04ttjf776","country_code":"AU","type":"education","lineage":["https://openalex.org/I82951845"]}],"countries":["AU","MK"],"is_corresponding":false,"raw_author_name":"J. Shane Culpepper","raw_affiliation_strings":["RMIT University"],"affiliations":[{"raw_affiliation_string":"RMIT University","institution_ids":["https://openalex.org/I4210095297","https://openalex.org/I82951845"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5031439294","display_name":"Maarten de Rijke","orcid":"https://orcid.org/0000-0002-1086-0202"},"institutions":[{"id":"https://openalex.org/I887064364","display_name":"University of Amsterdam","ror":"https://ror.org/04dkp9463","country_code":"NL","type":"education","lineage":["https://openalex.org/I887064364"]}],"countries":["NL"],"is_corresponding":false,"raw_author_name":"Maarten de Rijke","raw_affiliation_strings":["University of Amsterdam"],"affiliations":[{"raw_affiliation_string":"University of Amsterdam","institution_ids":["https://openalex.org/I887064364"]}]}],"institutions":[],"countries_distinct_count":3,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5002072527"],"corresponding_institution_ids":["https://openalex.org/I887064364"],"apc_list":null,"apc_paid":null,"fwci":2.8735,"has_fulltext":false,"cited_by_count":19,"citation_normalized_percentile":{"value":0.92886321,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":94,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"4"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11269","display_name":"Algorithms and Data Compression","score":0.9990000128746033,"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":0.9990000128746033,"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/T11106","display_name":"Data Management and Algorithms","score":0.9976999759674072,"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/T12016","display_name":"Web Data Mining and Analysis","score":0.9933000206947327,"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/inverted-index","display_name":"Inverted index","score":0.9146580696105957},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8182326555252075},{"id":"https://openalex.org/keywords/search-engine-indexing","display_name":"Search engine indexing","score":0.7642251253128052},{"id":"https://openalex.org/keywords/bloom-filter","display_name":"Bloom filter","score":0.754780650138855},{"id":"https://openalex.org/keywords/index","display_name":"Index (typography)","score":0.691459059715271},{"id":"https://openalex.org/keywords/hash-function","display_name":"Hash function","score":0.6444189548492432},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.538121223449707},{"id":"https://openalex.org/keywords/word","display_name":"Word (group theory)","score":0.5040284991264343},{"id":"https://openalex.org/keywords/identifier","display_name":"Identifier","score":0.4976406395435333},{"id":"https://openalex.org/keywords/key","display_name":"Key (lock)","score":0.4936762750148773},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.47651994228363037},{"id":"https://openalex.org/keywords/tree","display_name":"Tree (set theory)","score":0.44046175479888916},{"id":"https://openalex.org/keywords/term","display_name":"Term (time)","score":0.4255366921424866},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.19032645225524902},{"id":"https://openalex.org/keywords/world-wide-web","display_name":"World Wide Web","score":0.1484335958957672},{"id":"https://openalex.org/keywords/computer-network","display_name":"Computer network","score":0.08009287714958191}],"concepts":[{"id":"https://openalex.org/C130590232","wikidata":"https://www.wikidata.org/wiki/Q1671754","display_name":"Inverted index","level":3,"score":0.9146580696105957},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8182326555252075},{"id":"https://openalex.org/C75165309","wikidata":"https://www.wikidata.org/wiki/Q2258979","display_name":"Search engine indexing","level":2,"score":0.7642251253128052},{"id":"https://openalex.org/C147224247","wikidata":"https://www.wikidata.org/wiki/Q885373","display_name":"Bloom filter","level":2,"score":0.754780650138855},{"id":"https://openalex.org/C2777382242","wikidata":"https://www.wikidata.org/wiki/Q6017816","display_name":"Index (typography)","level":2,"score":0.691459059715271},{"id":"https://openalex.org/C99138194","wikidata":"https://www.wikidata.org/wiki/Q183427","display_name":"Hash function","level":2,"score":0.6444189548492432},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.538121223449707},{"id":"https://openalex.org/C90805587","wikidata":"https://www.wikidata.org/wiki/Q10944557","display_name":"Word (group theory)","level":2,"score":0.5040284991264343},{"id":"https://openalex.org/C154504017","wikidata":"https://www.wikidata.org/wiki/Q853614","display_name":"Identifier","level":2,"score":0.4976406395435333},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.4936762750148773},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.47651994228363037},{"id":"https://openalex.org/C113174947","wikidata":"https://www.wikidata.org/wiki/Q2859736","display_name":"Tree (set theory)","level":2,"score":0.44046175479888916},{"id":"https://openalex.org/C61797465","wikidata":"https://www.wikidata.org/wiki/Q1188986","display_name":"Term (time)","level":2,"score":0.4255366921424866},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.19032645225524902},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.1484335958957672},{"id":"https://openalex.org/C31258907","wikidata":"https://www.wikidata.org/wiki/Q1301371","display_name":"Computer network","level":1,"score":0.08009287714958191},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","level":1,"score":0.0},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","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/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.0}],"mesh":[],"locations_count":5,"locations":[{"id":"doi:10.1145/3291992.3291993","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3291992.3291993","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 23rd Australasian Document Computing Symposium","raw_type":"proceedings-article"},{"id":"pmh:oai:dare.uva.nl:openaire_cris_publications/53b9166c-349d-4886-b805-ecb52cacddd6","is_oa":false,"landing_page_url":"https://handle.uba.uva.nl/personal/pure/en/publications/the-potential-of-learned-index-structures-for-index-compression(53b9166c-349d-4886-b805-ecb52cacddd6).html","pdf_url":null,"source":{"id":"https://openalex.org/S4306400088","display_name":"UvA-DARE (University of Amsterdam)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I887064364","host_organization_name":"University of Amsterdam","host_organization_lineage":["https://openalex.org/I887064364"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Oosterhuis, H, Culpepper, J S & de Rijke, M 2018, The Potential of Learned Index Structures for Index Compression. in B Koopman, A Trotman & P Thomas (eds), ADCS 2018 : proceedings of the 23rd Australasian Document Computing Symposium : Dunedin, New Zealand, December 11-12, 2018., 7, New York, NY, 23rd Australasian Document Computing Symposium , Dunedin, New Zealand, 11/12/18. https://doi.org/10.1145/3291992.3291993","raw_type":"info:eu-repo/semantics/publishedVersion"},{"id":"pmh:oai:arXiv.org:1811.06678","is_oa":true,"landing_page_url":"http://arxiv.org/abs/1811.06678","pdf_url":"https://arxiv.org/pdf/1811.06678","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":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"pmh:oai:figshare.com:article/27584139","is_oa":true,"landing_page_url":null,"pdf_url":null,"source":{"id":"https://openalex.org/S4377196282","display_name":"Figshare","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I4210132348","host_organization_name":"Figshare (United Kingdom)","host_organization_lineage":["https://openalex.org/I4210132348"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"Text"},{"id":"pmh:uvapub:oai:dare.uva.nl:publications/53b9166c-349d-4886-b805-ecb52cacddd6","is_oa":false,"landing_page_url":"https://dare.uva.nl/personal/pure/en/publications/the-potential-of-learned-index-structures-for-index-compression(53b9166c-349d-4886-b805-ecb52cacddd6).html","pdf_url":null,"source":{"id":"https://openalex.org/S4306401843","display_name":"Data Archiving and Networked Services (DANS)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1322597698","host_organization_name":"Royal Netherlands Academy of Arts and Sciences","host_organization_lineage":["https://openalex.org/I1322597698"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"ADCS 2018: proceedings of the 23rd Australasian Document Computing Symposium : Dunedin, New Zealand, December 11-12, 2018","raw_type":"info:eu-repo/semantics/conferencepaper"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:1811.06678","is_oa":true,"landing_page_url":"http://arxiv.org/abs/1811.06678","pdf_url":"https://arxiv.org/pdf/1811.06678","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":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G3943500150","display_name":null,"funder_award_id":"612.001.116","funder_id":"https://openalex.org/F4320321800","funder_display_name":"Nederlandse Organisatie voor Wetenschappelijk Onderzoek"}],"funders":[{"id":"https://openalex.org/F4320321800","display_name":"Nederlandse Organisatie voor Wetenschappelijk Onderzoek","ror":"https://ror.org/04jsz6e67"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":23,"referenced_works":["https://openalex.org/W1599458355","https://openalex.org/W1791987072","https://openalex.org/W1984614894","https://openalex.org/W1996930216","https://openalex.org/W2000431947","https://openalex.org/W2031302834","https://openalex.org/W2040852594","https://openalex.org/W2077789969","https://openalex.org/W2084965869","https://openalex.org/W2089455813","https://openalex.org/W2091379987","https://openalex.org/W2125203709","https://openalex.org/W2138662031","https://openalex.org/W2148212498","https://openalex.org/W2342707026","https://openalex.org/W2531355666","https://openalex.org/W2741632195","https://openalex.org/W2742124187","https://openalex.org/W2782730635","https://openalex.org/W2889286463","https://openalex.org/W2962771342","https://openalex.org/W3101622805","https://openalex.org/W3102704970"],"related_works":["https://openalex.org/W2227807207","https://openalex.org/W2606354411","https://openalex.org/W2370014100","https://openalex.org/W4287264924","https://openalex.org/W3137108924","https://openalex.org/W1852009617","https://openalex.org/W1979110442","https://openalex.org/W2042819006","https://openalex.org/W2170165007","https://openalex.org/W2156660460"],"abstract_inverted_index":{"Inverted":[0],"indexes":[1,44],"are":[2],"vital":[3],"in":[4,12,22,142,156],"providing":[5],"fast":[6],"key-word-based":[7],"search.":[8],"For":[9],"every":[10],"term":[11,25,35],"the":[13,24,53,125,135],"document":[14,116],"collection,":[15],"a":[16,111,165],"list":[17],"of":[18,20,55,118,144],"identifiers":[19],"documents":[21],"which":[23],"appears":[26],"is":[27],"stored,":[28],"along":[29],"with":[30],"auxiliary":[31],"information":[32],"such":[33,69,98,127],"as":[34,70],"frequency,":[36],"and":[37,73,82,122,159],"position":[38],"offsets.":[39],"While":[40],"very":[41],"effective,":[42],"inverted":[43,120,157],"have":[45,153],"large":[46],"memory":[47,145],"requirements":[48],"for":[49,168],"web-sized":[50],"collections.":[51],"Recently,":[52],"concept":[54],"learned":[56,63,76,112,151],"index":[57,67,77],"structures":[58,68,78],"was":[59],"introduced,":[60],"where":[61],"machine":[62],"models":[64,99,152],"replace":[65,115],"common":[66],"B-tree-indexes,":[71],"hash-indexes,":[72],"bloom-filters.":[74],"These":[75],"require":[79],"less":[80],"memory,":[81],"can":[83,114,139],"be":[84,101,140,164],"computationally":[85],"much":[86],"faster":[87],"than":[88],"their":[89],"traditional":[90],"counterparts.":[91],"In":[92],"this":[93,160],"paper,":[94],"we":[95,108,133],"consider":[96],"whether":[97],"may":[100],"applied":[102],"to":[103,163],"conjunctive":[104],"Boolean":[105],"querying.":[106],"First,":[107],"investigate":[109],"how":[110],"model":[113],"postings":[117],"an":[119,128],"index,":[121],"then":[123],"evaluate":[124,134],"compromises":[126],"approach":[129],"might":[130],"have.":[131],"Second,":[132],"potential":[136,155],"gains":[137],"that":[138,150],"achieved":[141],"terms":[143],"requirements.":[146],"Our":[147],"work":[148],"shows":[149],"great":[154],"indexing,":[158],"direction":[161],"seems":[162],"promising":[166],"area":[167],"future":[169],"research.":[170]},"counts_by_year":[{"year":2022,"cited_by_count":2},{"year":2021,"cited_by_count":7},{"year":2020,"cited_by_count":6},{"year":2019,"cited_by_count":4}],"updated_date":"2026-04-04T16:13:02.066488","created_date":"2020-11-23T00:00:00"}