{"id":"https://openalex.org/W3163308175","doi":"https://doi.org/10.1145/3464509.3464885","title":"LEA: A Learned Encoding Advisor for Column Stores","display_name":"LEA: A Learned Encoding Advisor for Column Stores","publication_year":2021,"publication_date":"2021-06-18","ids":{"openalex":"https://openalex.org/W3163308175","doi":"https://doi.org/10.1145/3464509.3464885","mag":"3163308175"},"language":"en","primary_location":{"id":"doi:10.1145/3464509.3464885","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3464509.3464885","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3464509.3464885","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Fourth Workshop in Exploiting AI Techniques for Data Management","raw_type":"proceedings-article"},"type":"preprint","indexed_in":["arxiv","crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://dl.acm.org/doi/pdf/10.1145/3464509.3464885","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5000773824","display_name":"Lujing Cen","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Lujing Cen","raw_affiliation_strings":["MIT, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"MIT, USA","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5046188245","display_name":"Andreas Kipf","orcid":"https://orcid.org/0000-0003-3463-0564"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Andreas Kipf","raw_affiliation_strings":["MIT, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"MIT, USA","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5025731013","display_name":"Ryan Marcus","orcid":"https://orcid.org/0000-0002-1279-1124"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Ryan Marcus","raw_affiliation_strings":["MIT CSAIL, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"MIT CSAIL, USA","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5034086130","display_name":"Tim Kraska","orcid":"https://orcid.org/0009-0003-2414-2759"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Tim Kraska","raw_affiliation_strings":["MIT, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"MIT, USA","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":4,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":2.6695,"has_fulltext":true,"cited_by_count":8,"citation_normalized_percentile":{"value":0.91251076,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":90,"max":97},"biblio":{"volume":null,"issue":null,"first_page":"32","last_page":"35"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12720","display_name":"Multimedia Communication and Technology","score":0.9901000261306763,"subfield":{"id":"https://openalex.org/subfields/3312","display_name":"Sociology and Political Science"},"field":{"id":"https://openalex.org/fields/33","display_name":"Social Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},"topics":[{"id":"https://openalex.org/T12720","display_name":"Multimedia Communication and Technology","score":0.9901000261306763,"subfield":{"id":"https://openalex.org/subfields/3312","display_name":"Sociology and Political Science"},"field":{"id":"https://openalex.org/fields/33","display_name":"Social Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},{"id":"https://openalex.org/T10317","display_name":"Advanced Database Systems and Queries","score":0.9761999845504761,"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"}},{"id":"https://openalex.org/T11181","display_name":"Advanced Data Storage Technologies","score":0.9577000141143799,"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/column","display_name":"Column (typography)","score":0.7854508757591248},{"id":"https://openalex.org/keywords/encoding","display_name":"Encoding (memory)","score":0.7322897911071777},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6354473829269409},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.22385987639427185},{"id":"https://openalex.org/keywords/computer-network","display_name":"Computer network","score":0.1622958481311798}],"concepts":[{"id":"https://openalex.org/C2780551164","wikidata":"https://www.wikidata.org/wiki/Q2306599","display_name":"Column (typography)","level":3,"score":0.7854508757591248},{"id":"https://openalex.org/C125411270","wikidata":"https://www.wikidata.org/wiki/Q18653","display_name":"Encoding (memory)","level":2,"score":0.7322897911071777},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6354473829269409},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.22385987639427185},{"id":"https://openalex.org/C31258907","wikidata":"https://www.wikidata.org/wiki/Q1301371","display_name":"Computer network","level":1,"score":0.1622958481311798},{"id":"https://openalex.org/C126042441","wikidata":"https://www.wikidata.org/wiki/Q1324888","display_name":"Frame (networking)","level":2,"score":0.0}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1145/3464509.3464885","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3464509.3464885","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3464509.3464885","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Fourth Workshop in Exploiting AI Techniques for Data Management","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2105.08830","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2105.08830","pdf_url":"https://arxiv.org/pdf/2105.08830","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:dspace.mit.edu:1721.1/143733","is_oa":true,"landing_page_url":"https://hdl.handle.net/1721.1/143733","pdf_url":null,"source":{"id":"https://openalex.org/S4306400425","display_name":"DSpace@MIT (Massachusetts Institute of Technology)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I63966007","host_organization_name":"Massachusetts Institute of Technology","host_organization_lineage":["https://openalex.org/I63966007"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by-nc","license_id":"https://openalex.org/licenses/cc-by-nc","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"ACM","raw_type":"http://purl.org/eprint/type/ConferencePaper"}],"best_oa_location":{"id":"doi:10.1145/3464509.3464885","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3464509.3464885","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3464509.3464885","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Fourth Workshop in Exploiting AI Techniques for Data Management","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G7647474342","display_name":null,"funder_award_id":"FA8750-19-2-1000","funder_id":"https://openalex.org/F4320332467","funder_display_name":"U.S. Air Force"}],"funders":[{"id":"https://openalex.org/F4320306076","display_name":"National Science Foundation","ror":"https://ror.org/021nxhr62"},{"id":"https://openalex.org/F4320332467","display_name":"U.S. Air Force","ror":"https://ror.org/006gmme17"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W3163308175.pdf","grobid_xml":"https://content.openalex.org/works/W3163308175.grobid-xml"},"referenced_works_count":10,"referenced_works":["https://openalex.org/W1553825122","https://openalex.org/W2003580796","https://openalex.org/W2160068753","https://openalex.org/W2181616869","https://openalex.org/W2798964386","https://openalex.org/W2801200039","https://openalex.org/W2889252017","https://openalex.org/W2948513753","https://openalex.org/W3021961968","https://openalex.org/W4252112525"],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2899084033","https://openalex.org/W2748952813","https://openalex.org/W2390279801","https://openalex.org/W4391913857","https://openalex.org/W2358668433","https://openalex.org/W4396701345","https://openalex.org/W2376932109","https://openalex.org/W2001405890","https://openalex.org/W4396696052"],"abstract_inverted_index":{"Data":[0],"warehouses":[1],"organize":[2],"data":[3],"in":[4],"a":[5,18,33,38],"columnar":[6],"format":[7],"to":[8],"enable":[9],"faster":[10],"scans":[11],"and":[12,28,53],"better":[13],"compression.":[14],"Modern":[15],"systems":[16],"offer":[17],"variety":[19],"of":[20],"column":[21,40],"encodings":[22],"that":[23,45],"can":[24],"reduce":[25],"storage":[26],"footprint":[27],"improve":[29],"query":[30,51],"performance.":[31],"Selecting":[32],"good":[34],"encoding":[35],"scheme":[36],"for":[37],"particular":[39],"is":[41],"an":[42],"optimization":[43],"problem":[44],"depends":[46],"on":[47],"the":[48,50,54],"data,":[49],"workload,":[52],"underlying":[55],"hardware.":[56]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":3},{"year":2023,"cited_by_count":1},{"year":2022,"cited_by_count":1},{"year":2021,"cited_by_count":2}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}