{"id":"https://openalex.org/W2612705754","doi":"https://doi.org/10.1145/3035918.3064053","title":"Optimizing Iceberg Queries with Complex Joins","display_name":"Optimizing Iceberg Queries with Complex Joins","publication_year":2017,"publication_date":"2017-05-09","ids":{"openalex":"https://openalex.org/W2612705754","doi":"https://doi.org/10.1145/3035918.3064053","mag":"2612705754"},"language":"en","primary_location":{"id":"doi:10.1145/3035918.3064053","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3035918.3064053","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2017 ACM 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/A5047161300","display_name":"Brett Walenz","orcid":null},"institutions":[{"id":"https://openalex.org/I170897317","display_name":"Duke University","ror":"https://ror.org/00py81415","country_code":"US","type":"education","lineage":["https://openalex.org/I170897317"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Brett Walenz","raw_affiliation_strings":["Duke University, Durham, NC, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Duke University, Durham, NC, USA","institution_ids":["https://openalex.org/I170897317"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5110322079","display_name":"Sudeepa Roy","orcid":null},"institutions":[{"id":"https://openalex.org/I170897317","display_name":"Duke University","ror":"https://ror.org/00py81415","country_code":"US","type":"education","lineage":["https://openalex.org/I170897317"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Sudeepa Roy","raw_affiliation_strings":["Duke University, Durham, NC, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Duke University, Durham, NC, USA","institution_ids":["https://openalex.org/I170897317"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5058999081","display_name":"Jun Yang","orcid":"https://orcid.org/0000-0001-6615-3139"},"institutions":[{"id":"https://openalex.org/I170897317","display_name":"Duke University","ror":"https://ror.org/00py81415","country_code":"US","type":"education","lineage":["https://openalex.org/I170897317"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Jun Yang","raw_affiliation_strings":["Duke University, Durham, NC, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Duke University, Durham, NC, USA","institution_ids":["https://openalex.org/I170897317"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I170897317"],"apc_list":null,"apc_paid":null,"fwci":0.6991,"has_fulltext":false,"cited_by_count":8,"citation_normalized_percentile":{"value":0.6753523,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":96},"biblio":{"volume":null,"issue":null,"first_page":"1243","last_page":"1258"},"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":0.9998000264167786,"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/T10538","display_name":"Data Mining Algorithms and Applications","score":0.9962000250816345,"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/joins","display_name":"Joins","score":0.875298261642456},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8540762662887573},{"id":"https://openalex.org/keywords/memoization","display_name":"Memoization","score":0.7500545978546143},{"id":"https://openalex.org/keywords/pruning","display_name":"Pruning","score":0.6601154804229736},{"id":"https://openalex.org/keywords/exploit","display_name":"Exploit","score":0.5580939054489136},{"id":"https://openalex.org/keywords/iceberg","display_name":"Iceberg","score":0.5167312026023865},{"id":"https://openalex.org/keywords/sql","display_name":"SQL","score":0.4877065122127533},{"id":"https://openalex.org/keywords/tuple","display_name":"Tuple","score":0.478771835565567},{"id":"https://openalex.org/keywords/cache","display_name":"Cache","score":0.4441757798194885},{"id":"https://openalex.org/keywords/join","display_name":"Join (topology)","score":0.4197181165218353},{"id":"https://openalex.org/keywords/computation","display_name":"Computation","score":0.418316513299942},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.4061215817928314},{"id":"https://openalex.org/keywords/database","display_name":"Database","score":0.3634127974510193},{"id":"https://openalex.org/keywords/theoretical-computer-science","display_name":"Theoretical computer science","score":0.35802268981933594},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.20184674859046936},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.18901416659355164},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.10814210772514343}],"concepts":[{"id":"https://openalex.org/C2778692605","wikidata":"https://www.wikidata.org/wiki/Q4041866","display_name":"Joins","level":2,"score":0.875298261642456},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8540762662887573},{"id":"https://openalex.org/C79516417","wikidata":"https://www.wikidata.org/wiki/Q1376168","display_name":"Memoization","level":4,"score":0.7500545978546143},{"id":"https://openalex.org/C108010975","wikidata":"https://www.wikidata.org/wiki/Q500094","display_name":"Pruning","level":2,"score":0.6601154804229736},{"id":"https://openalex.org/C165696696","wikidata":"https://www.wikidata.org/wiki/Q11287","display_name":"Exploit","level":2,"score":0.5580939054489136},{"id":"https://openalex.org/C12481700","wikidata":"https://www.wikidata.org/wiki/Q47568","display_name":"Iceberg","level":3,"score":0.5167312026023865},{"id":"https://openalex.org/C510870499","wikidata":"https://www.wikidata.org/wiki/Q47607","display_name":"SQL","level":2,"score":0.4877065122127533},{"id":"https://openalex.org/C118930307","wikidata":"https://www.wikidata.org/wiki/Q600590","display_name":"Tuple","level":2,"score":0.478771835565567},{"id":"https://openalex.org/C115537543","wikidata":"https://www.wikidata.org/wiki/Q165596","display_name":"Cache","level":2,"score":0.4441757798194885},{"id":"https://openalex.org/C2776124973","wikidata":"https://www.wikidata.org/wiki/Q3183033","display_name":"Join (topology)","level":2,"score":0.4197181165218353},{"id":"https://openalex.org/C45374587","wikidata":"https://www.wikidata.org/wiki/Q12525525","display_name":"Computation","level":2,"score":0.418316513299942},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.4061215817928314},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.3634127974510193},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.35802268981933594},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.20184674859046936},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.18901416659355164},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.10814210772514343},{"id":"https://openalex.org/C42560504","wikidata":"https://www.wikidata.org/wiki/Q15419395","display_name":"Top-down parsing","level":3,"score":0.0},{"id":"https://openalex.org/C111368507","wikidata":"https://www.wikidata.org/wiki/Q43518","display_name":"Oceanography","level":1,"score":0.0},{"id":"https://openalex.org/C136894858","wikidata":"https://www.wikidata.org/wiki/Q213926","display_name":"Sea ice","level":2,"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/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"id":"https://openalex.org/C114614502","wikidata":"https://www.wikidata.org/wiki/Q76592","display_name":"Combinatorics","level":1,"score":0.0},{"id":"https://openalex.org/C127313418","wikidata":"https://www.wikidata.org/wiki/Q1069","display_name":"Geology","level":0,"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/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0},{"id":"https://openalex.org/C6557445","wikidata":"https://www.wikidata.org/wiki/Q173113","display_name":"Agronomy","level":1,"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/C53893814","wikidata":"https://www.wikidata.org/wiki/Q7378909","display_name":"Rule-based machine translation","level":2,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3035918.3064053","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3035918.3064053","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2017 ACM International Conference on Management of Data","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.6700000166893005,"id":"https://metadata.un.org/sdg/16","display_name":"Peace, Justice and strong institutions"}],"awards":[{"id":"https://openalex.org/G7446531716","display_name":"III: Medium: Collaborative Research: From Answering Questions to  Questioning Answers (and Questions)---Perturbation Analysis of  Database Queries","funder_award_id":"1408846","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"}],"funders":[{"id":"https://openalex.org/F4320306076","display_name":"National Science Foundation","ror":"https://ror.org/021nxhr62"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":26,"referenced_works":["https://openalex.org/W1506285740","https://openalex.org/W1535065114","https://openalex.org/W1540277706","https://openalex.org/W1570025952","https://openalex.org/W1761301028","https://openalex.org/W2003262311","https://openalex.org/W2004796840","https://openalex.org/W2064803206","https://openalex.org/W2085638007","https://openalex.org/W2092103580","https://openalex.org/W2103201239","https://openalex.org/W2113295349","https://openalex.org/W2116396741","https://openalex.org/W2122265344","https://openalex.org/W2122406210","https://openalex.org/W2139875914","https://openalex.org/W2144829796","https://openalex.org/W2250335649","https://openalex.org/W2548149136","https://openalex.org/W2999791986","https://openalex.org/W3003712253","https://openalex.org/W4205912915","https://openalex.org/W4246376997","https://openalex.org/W4248062460","https://openalex.org/W4250802407","https://openalex.org/W6651238488"],"related_works":["https://openalex.org/W2393491644","https://openalex.org/W4206577045","https://openalex.org/W3086237447","https://openalex.org/W650102067","https://openalex.org/W2016456293","https://openalex.org/W1550806730","https://openalex.org/W2589740103","https://openalex.org/W2172084996","https://openalex.org/W1966967794","https://openalex.org/W1501284171"],"abstract_inverted_index":{"Iceberg":[0],"queries,":[1],"commonly":[2],"used":[3],"for":[4,38,100],"decision":[5],"support,":[6],"find":[7],"groups":[8],"whose":[9],"aggregate":[10],"values":[11],"are":[12,22,29],"above":[13],"or":[14],"below":[15],"a":[16,36,40,62,140],"threshold.":[17],"In":[18],"practice,":[19],"iceberg":[20,48],"queries":[21,49],"often":[23],"posed":[24],"over":[25],"complex":[26,51],"joins":[27],"that":[28,82,113,133],"expensive":[30],"to":[31,64,80,87],"evaluate.":[32],"This":[33],"paper":[34],"proposes":[35],"framework":[37],"combining":[39],"number":[41],"of":[42,117],"techniques---a-priori,":[43],"memoization,":[44],"and":[45,58,71,92,131,139],"pruning---to":[46],"optimize":[47],"with":[50],"joins.":[52],"A-priori":[53],"pushes":[54],"partial":[55],"GROUP":[56],"BY":[57],"HAVING":[59],"condition":[60],"before":[61],"join":[63,73,94],"reduce":[65],"its":[66],"input":[67],"size.":[68],"Memoization":[69],"caches":[70],"reuses":[72],"computation":[74],"results.":[75],"Pruning":[76],"uses":[77],"cached":[78],"results":[79],"infer":[81],"certain":[83],"tuples":[84],"cannot":[85],"contribute":[86],"the":[88],"final":[89],"query":[90],"result,":[91],"short-circuits":[93],"computation.":[95],"We":[96,125],"formally":[97],"derive":[98],"conditions":[99],"correctly":[101],"applying":[102],"these":[103],"techniques.":[104],"Our":[105],"practical":[106],"rewrite":[107],"algorithm":[108],"produces":[109],"highly":[110],"efficient":[111],"SQL":[112],"can":[114],"exploit":[115],"combinations":[116],"optimization":[118],"opportunities":[119],"in":[120],"ways":[121],"previously":[122],"not":[123],"possible.":[124],"evaluate":[126],"our":[127],"PostgreSQL-based":[128],"implementation":[129],"experimentally":[130],"show":[132],"it":[134],"outperforms":[135],"both":[136],"baseline":[137],"PostgreSQL":[138],"commercial":[141],"database":[142],"system.":[143]},"counts_by_year":[{"year":2023,"cited_by_count":2},{"year":2022,"cited_by_count":1},{"year":2021,"cited_by_count":2},{"year":2019,"cited_by_count":2},{"year":2018,"cited_by_count":1}],"updated_date":"2026-08-06T08:24:18.245995","created_date":"2025-10-10T00:00:00"}