{"id":"https://openalex.org/W2135196372","doi":"https://doi.org/10.1145/1514894.1514907","title":"Optimal splitters for database partitioning with size bounds","display_name":"Optimal splitters for database partitioning with size bounds","publication_year":2009,"publication_date":"2009-03-23","ids":{"openalex":"https://openalex.org/W2135196372","doi":"https://doi.org/10.1145/1514894.1514907","mag":"2135196372"},"language":"en","primary_location":{"id":"doi:10.1145/1514894.1514907","is_oa":true,"landing_page_url":"https://doi.org/10.1145/1514894.1514907","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/1514894.1514907","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 12th International Conference on Database Theory","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://dl.acm.org/doi/pdf/10.1145/1514894.1514907","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5021663937","display_name":"Kenneth A. Ross","orcid":"https://orcid.org/0000-0001-9397-6990"},"institutions":[{"id":"https://openalex.org/I78577930","display_name":"Columbia University","ror":"https://ror.org/00hj8s172","country_code":"US","type":"education","lineage":["https://openalex.org/I78577930"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Kenneth A. Ross","raw_affiliation_strings":["Columbia University, New York, NY","Columbia University, New York, NY;"],"affiliations":[{"raw_affiliation_string":"Columbia University, New York, NY","institution_ids":["https://openalex.org/I78577930"]},{"raw_affiliation_string":"Columbia University, New York, NY;","institution_ids":["https://openalex.org/I78577930"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5016572616","display_name":"John Cieslewicz","orcid":"https://orcid.org/0000-0002-1074-6223"},"institutions":[{"id":"https://openalex.org/I78577930","display_name":"Columbia University","ror":"https://ror.org/00hj8s172","country_code":"US","type":"education","lineage":["https://openalex.org/I78577930"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"John Cieslewicz","raw_affiliation_strings":["Columbia University, New York, NY","Columbia University, New York, NY;"],"affiliations":[{"raw_affiliation_string":"Columbia University, New York, NY","institution_ids":["https://openalex.org/I78577930"]},{"raw_affiliation_string":"Columbia University, New York, NY;","institution_ids":["https://openalex.org/I78577930"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5021663937"],"corresponding_institution_ids":["https://openalex.org/I78577930"],"apc_list":null,"apc_paid":null,"fwci":2.5,"has_fulltext":true,"cited_by_count":16,"citation_normalized_percentile":{"value":0.89338284,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"98","last_page":"110"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11106","display_name":"Data Management and Algorithms","score":1.0,"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":1.0,"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/T10317","display_name":"Advanced Database Systems and Queries","score":0.9991000294685364,"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/T11269","display_name":"Algorithms and Data Compression","score":0.9976999759674072,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/joins","display_name":"Joins","score":0.8704030513763428},{"id":"https://openalex.org/keywords/sorting","display_name":"Sorting","score":0.7256983518600464},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.667273223400116},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.6246634125709534},{"id":"https://openalex.org/keywords/sort","display_name":"sort","score":0.5635815858840942},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.4452659487724304},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.3750166594982147},{"id":"https://openalex.org/keywords/theoretical-computer-science","display_name":"Theoretical computer science","score":0.3362712264060974},{"id":"https://openalex.org/keywords/database","display_name":"Database","score":0.26467078924179077}],"concepts":[{"id":"https://openalex.org/C2778692605","wikidata":"https://www.wikidata.org/wiki/Q4041866","display_name":"Joins","level":2,"score":0.8704030513763428},{"id":"https://openalex.org/C111696304","wikidata":"https://www.wikidata.org/wiki/Q2303697","display_name":"Sorting","level":2,"score":0.7256983518600464},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.667273223400116},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.6246634125709534},{"id":"https://openalex.org/C88548561","wikidata":"https://www.wikidata.org/wiki/Q347599","display_name":"sort","level":2,"score":0.5635815858840942},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.4452659487724304},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.3750166594982147},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.3362712264060974},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.26467078924179077},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0}],"mesh":[],"locations_count":5,"locations":[{"id":"doi:10.1145/1514894.1514907","is_oa":true,"landing_page_url":"https://doi.org/10.1145/1514894.1514907","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/1514894.1514907","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 12th International Conference on Database Theory","raw_type":"proceedings-article"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.218.9151","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.218.9151","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www.cs.columbia.edu/~kar/pubsk/splitters.pdf","raw_type":"text"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.377.1920","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.377.1920","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www.edbt.org/Proceedings/2009-StPetersburg/icdt/papers/p0098-Ross.pdf","raw_type":"text"},{"id":"pmh:oai:academiccommons.columbia.edu:10.7916/D87W6M2S","is_oa":false,"landing_page_url":"https://doi.org/10.7916/D87W6M2S","pdf_url":null,"source":{"id":"https://openalex.org/S4306402601","display_name":"Columbia Academic Commons (Columbia University)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I78577930","host_organization_name":"Columbia University","host_organization_lineage":["https://openalex.org/I78577930"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"Reports"},{"id":"doi:10.7916/d87w6m2s","is_oa":true,"landing_page_url":"https://doi.org/10.7916/d87w6m2s","pdf_url":null,"source":{"id":"https://openalex.org/S4306402601","display_name":"Columbia Academic Commons (Columbia University)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I78577930","host_organization_name":"Columbia University","host_organization_lineage":["https://openalex.org/I78577930"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"article-journal"}],"best_oa_location":{"id":"doi:10.1145/1514894.1514907","is_oa":true,"landing_page_url":"https://doi.org/10.1145/1514894.1514907","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/1514894.1514907","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 12th International Conference on Database Theory","raw_type":"proceedings-article"},"sustainable_development_goals":[{"display_name":"Reduced inequalities","score":0.5,"id":"https://metadata.un.org/sdg/10"}],"awards":[{"id":"https://openalex.org/G1374433839","display_name":"Cache-Aware Database Systems on Modern Multithreading Processors","funder_award_id":"0534389","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G7463018587","display_name":null,"funder_award_id":"IIS-0534389IIS-0534389","funder_id":"https://openalex.org/F4320337389","funder_display_name":"Division of Information and Intelligent Systems"}],"funders":[{"id":"https://openalex.org/F4320306076","display_name":"National Science Foundation","ror":"https://ror.org/021nxhr62"},{"id":"https://openalex.org/F4320306110","display_name":"U.S. Department of Homeland Security","ror":"https://ror.org/00jyr0d86"},{"id":"https://openalex.org/F4320337389","display_name":"Division of Information and Intelligent Systems","ror":"https://ror.org/053a2cp42"}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2135196372.pdf","grobid_xml":"https://content.openalex.org/works/W2135196372.grobid-xml"},"referenced_works_count":30,"referenced_works":["https://openalex.org/W161097227","https://openalex.org/W161142484","https://openalex.org/W1487093789","https://openalex.org/W1539580421","https://openalex.org/W1541142209","https://openalex.org/W1559974236","https://openalex.org/W1570320352","https://openalex.org/W1581406059","https://openalex.org/W1585614323","https://openalex.org/W1597532222","https://openalex.org/W1784244685","https://openalex.org/W1822348499","https://openalex.org/W1966648469","https://openalex.org/W1991271936","https://openalex.org/W1992730709","https://openalex.org/W2005188603","https://openalex.org/W2028660080","https://openalex.org/W2057843273","https://openalex.org/W2105175890","https://openalex.org/W2106642566","https://openalex.org/W2115032130","https://openalex.org/W2137516889","https://openalex.org/W2151310484","https://openalex.org/W2171903035","https://openalex.org/W2465756754","https://openalex.org/W3138367763","https://openalex.org/W4285719527","https://openalex.org/W6606450935","https://openalex.org/W6635650928","https://openalex.org/W6638337754"],"related_works":["https://openalex.org/W2088925915","https://openalex.org/W2382891957","https://openalex.org/W2095055219","https://openalex.org/W2482527088","https://openalex.org/W2362374543","https://openalex.org/W2116295091","https://openalex.org/W4319430205","https://openalex.org/W3121711078","https://openalex.org/W2085265870","https://openalex.org/W2348196682"],"abstract_inverted_index":{"Partitioning":[0,14],"is":[1,15,98,106],"an":[2,72,76],"important":[3],"step":[4],"in":[5,176],"several":[6],"database":[7],"algorithms,":[8],"including":[9],"sorting,":[10],"aggregation,":[11],"and":[12,35,56,86,104,153],"joins.":[13],"also":[16],"fundamental":[17],"for":[18,43,74],"dividing":[19],"work":[20,132],"into":[21,131],"equal-sized":[22],"(or":[23],"balanced)":[24],"parallel":[25],"subtasks.":[26],"In":[27],"this":[28],"paper,":[29],"we":[30],"aim":[31],"to":[32,62,121,164,171],"find,":[33],"materialize":[34],"maintain":[36],"a":[37,44,82,166,180],"set":[38,78,85,146,168],"of":[39,66,79,101,109,123,147,179],"partitioning":[40,49],"elements":[41],"(splitters)":[42],"data":[45,84,111,167],"set.":[46,112],"Unlike":[47],"traditional":[48],"elements,":[50],"our":[51],"splitters":[52,80,102,148,159],"define":[53],"both":[54],"inequality":[55,68],"equality":[57],"partitions,":[58],"which":[59],"allows":[60],"us":[61],"bound":[63],"the":[64,67,99,107,110,116,144,157,162,177],"size":[65,108],"partitions.":[69],"We":[70,113,138],"provide":[71],"algorithm":[73,117],"determining":[75],"optimal":[77,145],"from":[81],"sorted":[83],"show":[87,114],"that":[88,126,134,142,155],"it":[89],"has":[90],"time":[91,163],"complexity":[92],"O(k":[93],"lg2":[94],"N),":[95],"where":[96],"k":[97],"number":[100],"requested":[103],"N":[105],"how":[115],"can":[118,128,149,160],"be":[119,129,150],"extended":[120],"pairs":[122],"tables,":[124],"so":[125],"joins":[127],"partitioned":[130],"units":[133],"have":[135],"balanced":[136],"cost.":[137],"demonstrate":[139],"experimentally":[140],"(a)":[141],"finding":[143],"done":[151],"efficiently,":[152],"(b)":[154],"using":[156],"precomputed":[158],"improve":[161],"sort":[165],"by":[169],"up":[170],"76%,":[172],"with":[173],"particular":[174],"benefits":[175],"presence":[178],"few":[181],"heavy":[182],"hitters.":[183]},"counts_by_year":[{"year":2015,"cited_by_count":1},{"year":2014,"cited_by_count":4},{"year":2013,"cited_by_count":4},{"year":2012,"cited_by_count":3}],"updated_date":"2026-04-21T08:09:41.155169","created_date":"2025-10-10T00:00:00"}