{"id":"https://openalex.org/W3029187551","doi":"https://doi.org/10.1145/3318464.3389734","title":"DeepSqueeze: Deep Semantic Compression for Tabular Data","display_name":"DeepSqueeze: Deep Semantic Compression for Tabular Data","publication_year":2020,"publication_date":"2020-05-29","ids":{"openalex":"https://openalex.org/W3029187551","doi":"https://doi.org/10.1145/3318464.3389734","mag":"3029187551"},"language":"en","primary_location":{"id":"doi:10.1145/3318464.3389734","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3318464.3389734","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2020 ACM SIGMOD International Conference on Management of Data","raw_type":"proceedings-article"},"type":"conference-paper","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/A5041887663","display_name":"Amir Ilkhechi","orcid":null},"institutions":[{"id":"https://openalex.org/I27804330","display_name":"Brown University","ror":"https://ror.org/05gq02987","country_code":"US","type":"education","lineage":["https://openalex.org/I27804330"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Amir Ilkhechi","raw_affiliation_strings":["Brown University, Providence, RI, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Brown University, Providence, RI, USA","institution_ids":["https://openalex.org/I27804330"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5054370671","display_name":"Andrew Crotty","orcid":"https://orcid.org/0000-0002-8544-0982"},"institutions":[{"id":"https://openalex.org/I27804330","display_name":"Brown University","ror":"https://ror.org/05gq02987","country_code":"US","type":"education","lineage":["https://openalex.org/I27804330"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Andrew Crotty","raw_affiliation_strings":["Brown University, Providence, RI, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Brown University, Providence, RI, USA","institution_ids":["https://openalex.org/I27804330"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5039470845","display_name":"Alex Galakatos","orcid":null},"institutions":[{"id":"https://openalex.org/I27804330","display_name":"Brown University","ror":"https://ror.org/05gq02987","country_code":"US","type":"education","lineage":["https://openalex.org/I27804330"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Alex Galakatos","raw_affiliation_strings":["Brown University, Providence, RI, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Brown University, Providence, RI, USA","institution_ids":["https://openalex.org/I27804330"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5015640245","display_name":"Yicong Mao","orcid":null},"institutions":[{"id":"https://openalex.org/I27804330","display_name":"Brown University","ror":"https://ror.org/05gq02987","country_code":"US","type":"education","lineage":["https://openalex.org/I27804330"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Yicong Mao","raw_affiliation_strings":["Brown University, Providence, RI, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Brown University, Providence, RI, USA","institution_ids":["https://openalex.org/I27804330"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5085780174","display_name":"Grace Fan","orcid":null},"institutions":[{"id":"https://openalex.org/I27804330","display_name":"Brown University","ror":"https://ror.org/05gq02987","country_code":"US","type":"education","lineage":["https://openalex.org/I27804330"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Grace Fan","raw_affiliation_strings":["Brown University, Providence, RI, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Brown University, Providence, RI, USA","institution_ids":["https://openalex.org/I27804330"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5032560121","display_name":"Xiran Shi","orcid":null},"institutions":[{"id":"https://openalex.org/I27804330","display_name":"Brown University","ror":"https://ror.org/05gq02987","country_code":"US","type":"education","lineage":["https://openalex.org/I27804330"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Xiran Shi","raw_affiliation_strings":["Brown University, Providence, RI, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Brown University, Providence, RI, USA","institution_ids":["https://openalex.org/I27804330"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5109862110","display_name":"U\u011fur \u00c7etintemel","orcid":null},"institutions":[{"id":"https://openalex.org/I27804330","display_name":"Brown University","ror":"https://ror.org/05gq02987","country_code":"US","type":"education","lineage":["https://openalex.org/I27804330"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Ugur Cetintemel","raw_affiliation_strings":["Brown University, Providence, RI, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Brown University, Providence, RI, USA","institution_ids":["https://openalex.org/I27804330"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I27804330"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":28,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1733","last_page":"1746"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11269","display_name":"Algorithms and Data Compression","score":0.9997000098228455,"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":0.9997000098228455,"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/T11181","display_name":"Advanced Data Storage Technologies","score":0.9988999962806702,"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/T10054","display_name":"Parallel Computing and Optimization Techniques","score":0.9933000206947327,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/lossy-compression","display_name":"Lossy compression","score":0.8283127546310425},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.804938793182373},{"id":"https://openalex.org/keywords/leverage","display_name":"Leverage (statistics)","score":0.7715439200401306},{"id":"https://openalex.org/keywords/data-compression","display_name":"Data compression","score":0.6938676834106445},{"id":"https://openalex.org/keywords/tuple","display_name":"Tuple","score":0.6435016989707947},{"id":"https://openalex.org/keywords/compression","display_name":"Compression (physics)","score":0.6236913800239563},{"id":"https://openalex.org/keywords/encoding","display_name":"Encoding (memory)","score":0.6084320545196533},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.48598989844322205},{"id":"https://openalex.org/keywords/external-data-representation","display_name":"External Data Representation","score":0.4305286705493927},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.4239412248134613},{"id":"https://openalex.org/keywords/compression-ratio","display_name":"Compression ratio","score":0.42050665616989136},{"id":"https://openalex.org/keywords/theoretical-computer-science","display_name":"Theoretical computer science","score":0.35823532938957214},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3428059220314026},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.34071844816207886},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.08468785881996155}],"concepts":[{"id":"https://openalex.org/C165021410","wikidata":"https://www.wikidata.org/wiki/Q55564","display_name":"Lossy compression","level":2,"score":0.8283127546310425},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.804938793182373},{"id":"https://openalex.org/C153083717","wikidata":"https://www.wikidata.org/wiki/Q6535263","display_name":"Leverage (statistics)","level":2,"score":0.7715439200401306},{"id":"https://openalex.org/C78548338","wikidata":"https://www.wikidata.org/wiki/Q2493","display_name":"Data compression","level":2,"score":0.6938676834106445},{"id":"https://openalex.org/C118930307","wikidata":"https://www.wikidata.org/wiki/Q600590","display_name":"Tuple","level":2,"score":0.6435016989707947},{"id":"https://openalex.org/C180016635","wikidata":"https://www.wikidata.org/wiki/Q2712821","display_name":"Compression (physics)","level":2,"score":0.6236913800239563},{"id":"https://openalex.org/C125411270","wikidata":"https://www.wikidata.org/wiki/Q18653","display_name":"Encoding (memory)","level":2,"score":0.6084320545196533},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.48598989844322205},{"id":"https://openalex.org/C116409475","wikidata":"https://www.wikidata.org/wiki/Q1385056","display_name":"External Data Representation","level":2,"score":0.4305286705493927},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.4239412248134613},{"id":"https://openalex.org/C25797200","wikidata":"https://www.wikidata.org/wiki/Q828137","display_name":"Compression ratio","level":3,"score":0.42050665616989136},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.35823532938957214},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3428059220314026},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.34071844816207886},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.08468785881996155},{"id":"https://openalex.org/C171146098","wikidata":"https://www.wikidata.org/wiki/Q124192","display_name":"Automotive engineering","level":1,"score":0.0},{"id":"https://openalex.org/C199539241","wikidata":"https://www.wikidata.org/wiki/Q7748","display_name":"Law","level":1,"score":0.0},{"id":"https://openalex.org/C94625758","wikidata":"https://www.wikidata.org/wiki/Q7163","display_name":"Politics","level":2,"score":0.0},{"id":"https://openalex.org/C192562407","wikidata":"https://www.wikidata.org/wiki/Q228736","display_name":"Materials science","level":0,"score":0.0},{"id":"https://openalex.org/C511840579","wikidata":"https://www.wikidata.org/wiki/Q12757","display_name":"Internal combustion engine","level":2,"score":0.0},{"id":"https://openalex.org/C118615104","wikidata":"https://www.wikidata.org/wiki/Q121416","display_name":"Discrete mathematics","level":1,"score":0.0},{"id":"https://openalex.org/C159985019","wikidata":"https://www.wikidata.org/wiki/Q181790","display_name":"Composite material","level":1,"score":0.0},{"id":"https://openalex.org/C17744445","wikidata":"https://www.wikidata.org/wiki/Q36442","display_name":"Political science","level":0,"score":0.0},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3318464.3389734","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3318464.3389734","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2020 ACM SIGMOD International Conference on Management of Data","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":21,"referenced_works":["https://openalex.org/W1990653637","https://openalex.org/W2006296837","https://openalex.org/W2018745370","https://openalex.org/W2022126655","https://openalex.org/W2024171325","https://openalex.org/W2031614119","https://openalex.org/W2054658115","https://openalex.org/W2060108852","https://openalex.org/W2107745473","https://openalex.org/W2122962290","https://openalex.org/W2123686039","https://openalex.org/W2146160048","https://openalex.org/W2154900736","https://openalex.org/W2294212155","https://openalex.org/W2443229613","https://openalex.org/W2581624817","https://openalex.org/W2593493485","https://openalex.org/W2604392022","https://openalex.org/W2732582420","https://openalex.org/W2765756720","https://openalex.org/W3100944407"],"related_works":["https://openalex.org/W2547124190","https://openalex.org/W4307097729","https://openalex.org/W3212420620","https://openalex.org/W2912174957","https://openalex.org/W2385628723","https://openalex.org/W2552401318","https://openalex.org/W3180760233","https://openalex.org/W108076602","https://openalex.org/W4384342390","https://openalex.org/W4220987233"],"abstract_inverted_index":{"With":[0],"the":[1,55,70,75],"rapid":[2],"proliferation":[3],"of":[4,69,131],"large":[5],"datasets,":[6],"efficient":[7],"data":[8,111,133],"compression":[9,17,52,100,130,141],"has":[10],"become":[11],"more":[12,86],"important":[13],"than":[14,87],"ever.":[15],"Columnar":[16],"techniques":[18],"(e.g.,":[19],"dictionary":[20],"encoding,":[21,23],"run-length":[22],"delta":[24],"encoding)":[25],"have":[26],"proved":[27],"highly":[28],"effective":[29],"for":[30,128],"tabular":[31,110],"data,":[32],"but":[33,77],"they":[34],"typically":[35],"compress":[36],"individual":[37],"columns":[38,71,90],"without":[39],"considering":[40],"potential":[41],"relationships":[42,63,84,108],"among":[43],"columns,":[44],"such":[45,62],"as":[46],"functional":[47],"dependencies":[48],"and":[49,134],"correlations.":[50],"Semantic":[51],"techniques,":[53],"on":[54],"other":[56],"hand,":[57],"are":[58],"designed":[59],"to":[60,64,73,115,118,149,161],"leverage":[61],"store":[65],"only":[66],"a":[67,88,92,97,119,156],"subset":[68],"necessary":[72],"infer":[74],"others,":[76],"existing":[78],"approaches":[79],"cannot":[80],"effectively":[81],"identify":[82],"complex":[83,107],"across":[85],"few":[89],"at":[91],"time.":[93],"We":[94],"propose":[95],"DeepSqueeze,":[96],"novel":[98],"semantic":[99],"framework":[101],"that":[102,151],"can":[103,153],"efficiently":[104],"capture":[105],"these":[106],"within":[109],"by":[112],"using":[113],"autoencoders":[114],"map":[116],"tuples":[117],"lower-dimensional":[120],"representation.":[121],"DeepSqueeze":[122,152],"also":[123],"supports":[124],"guaranteed":[125],"error":[126],"bounds":[127],"lossy":[129],"numerical":[132],"works":[135],"in":[136],"conjunction":[137],"with":[138],"common":[139],"columnar":[140],"formats.":[142],"Our":[143],"experimental":[144],"evaluation":[145],"uses":[146],"real-world":[147],"datasets":[148],"demonstrate":[150],"achieve":[154],"over":[155],"4x":[157],"size":[158],"reduction":[159],"compared":[160],"state-of-the-art":[162],"alternatives.":[163]},"counts_by_year":[{"year":2026,"cited_by_count":3},{"year":2025,"cited_by_count":5},{"year":2024,"cited_by_count":8},{"year":2023,"cited_by_count":5},{"year":2022,"cited_by_count":5},{"year":2021,"cited_by_count":2}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}