{"id":"https://openalex.org/W3176109148","doi":"https://doi.org/10.1145/3448016.3450572","title":"Index-Based Join Size Estimation Using Adaptive Sampling","display_name":"Index-Based Join Size Estimation Using Adaptive Sampling","publication_year":2021,"publication_date":"2021-06-09","ids":{"openalex":"https://openalex.org/W3176109148","doi":"https://doi.org/10.1145/3448016.3450572","mag":"3176109148"},"language":"en","primary_location":{"id":"doi:10.1145/3448016.3450572","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3448016.3450572","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2021 International Conference on Management of Data","raw_type":"proceedings-article"},"type":"article","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/A5041851830","display_name":"Sergiu Pocol","orcid":null},"institutions":[{"id":"https://openalex.org/I151746483","display_name":"University of Waterloo","ror":"https://ror.org/01aff2v68","country_code":"CA","type":"education","lineage":["https://openalex.org/I151746483"]}],"countries":["CA"],"is_corresponding":true,"raw_author_name":"Sergiu Pocol","raw_affiliation_strings":["University of Waterloo, Waterloo, ON, Canada"],"affiliations":[{"raw_affiliation_string":"University of Waterloo, Waterloo, ON, Canada","institution_ids":["https://openalex.org/I151746483"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":["https://openalex.org/A5041851830"],"corresponding_institution_ids":["https://openalex.org/I151746483"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.0729547,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":97,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"2932","last_page":"2933"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11106","display_name":"Data Management and Algorithms","score":0.9993000030517578,"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":0.9993000030517578,"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":0.9988999962806702,"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/T12761","display_name":"Data Stream Mining Techniques","score":0.9962000250816345,"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":0.9727514982223511},{"id":"https://openalex.org/keywords/cardinality","display_name":"Cardinality (data modeling)","score":0.8180176019668579},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7912375926971436},{"id":"https://openalex.org/keywords/join","display_name":"Join (topology)","score":0.7770034074783325},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.547161877155304},{"id":"https://openalex.org/keywords/independence","display_name":"Independence (probability theory)","score":0.5420457124710083},{"id":"https://openalex.org/keywords/index","display_name":"Index (typography)","score":0.4617244601249695},{"id":"https://openalex.org/keywords/estimation","display_name":"Estimation","score":0.4596630334854126},{"id":"https://openalex.org/keywords/table","display_name":"Table (database)","score":0.4451790153980255},{"id":"https://openalex.org/keywords/query-optimization","display_name":"Query optimization","score":0.4328831136226654},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.3821903169155121},{"id":"https://openalex.org/keywords/theoretical-computer-science","display_name":"Theoretical computer science","score":0.32682573795318604},{"id":"https://openalex.org/keywords/statistics","display_name":"Statistics","score":0.19534197449684143},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.13656362891197205},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.07572594285011292}],"concepts":[{"id":"https://openalex.org/C2778692605","wikidata":"https://www.wikidata.org/wiki/Q4041866","display_name":"Joins","level":2,"score":0.9727514982223511},{"id":"https://openalex.org/C87117476","wikidata":"https://www.wikidata.org/wiki/Q362383","display_name":"Cardinality (data modeling)","level":2,"score":0.8180176019668579},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7912375926971436},{"id":"https://openalex.org/C2776124973","wikidata":"https://www.wikidata.org/wiki/Q3183033","display_name":"Join (topology)","level":2,"score":0.7770034074783325},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.547161877155304},{"id":"https://openalex.org/C35651441","wikidata":"https://www.wikidata.org/wiki/Q625303","display_name":"Independence (probability theory)","level":2,"score":0.5420457124710083},{"id":"https://openalex.org/C2777382242","wikidata":"https://www.wikidata.org/wiki/Q6017816","display_name":"Index (typography)","level":2,"score":0.4617244601249695},{"id":"https://openalex.org/C96250715","wikidata":"https://www.wikidata.org/wiki/Q965330","display_name":"Estimation","level":2,"score":0.4596630334854126},{"id":"https://openalex.org/C45235069","wikidata":"https://www.wikidata.org/wiki/Q278425","display_name":"Table (database)","level":2,"score":0.4451790153980255},{"id":"https://openalex.org/C157692150","wikidata":"https://www.wikidata.org/wiki/Q2919848","display_name":"Query optimization","level":2,"score":0.4328831136226654},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.3821903169155121},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.32682573795318604},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.19534197449684143},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.13656362891197205},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.07572594285011292},{"id":"https://openalex.org/C187736073","wikidata":"https://www.wikidata.org/wiki/Q2920921","display_name":"Management","level":1,"score":0.0},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","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}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3448016.3450572","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3448016.3450572","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2021 International Conference on Management of Data","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":5,"referenced_works":["https://openalex.org/W2037192958","https://openalex.org/W2585664214","https://openalex.org/W2752189538","https://openalex.org/W2890276152","https://openalex.org/W3031692719"],"related_works":["https://openalex.org/W2393491644","https://openalex.org/W4206577045","https://openalex.org/W3086237447","https://openalex.org/W650102067","https://openalex.org/W2740404111","https://openalex.org/W1550806730","https://openalex.org/W1496672428","https://openalex.org/W2589740103","https://openalex.org/W1966967794","https://openalex.org/W1501284171"],"abstract_inverted_index":{"Cost-based":[0],"query":[1,13],"optimizers":[2,26],"rely":[3],"on":[4,22,58,84],"cardinality":[5,75],"estimates":[6,85,101],"of":[7,50,77,86,98,119],"intermediate":[8],"results":[9],"to":[10,65,70],"avoid":[11],"suboptimal":[12],"execution":[14],"plans.":[15],"However,":[16],"when":[17],"confronted":[18],"with":[19,61,80],"ad-hoc":[20],"queries":[21],"big":[23],"data,":[24],"said":[25],"can":[27,106],"produce":[28],"large":[29],"estimation":[30,44,118],"errors,":[31],"resulting":[32],"in":[33,36,102],"drastic":[34],"decreases":[35],"overall":[37],"performance.":[38],"Such":[39],"errors":[40],"occur":[41],"because":[42],"many":[43,81],"algorithms":[45],"for":[46],"joins":[47,82],"make":[48],"use":[49],"strong":[51],"independence":[52],"and":[53],"uniformity":[54],"assumptions.":[55],"Moreover,":[56],"equi-joins":[57],"skewed":[59],"data":[60],"filter":[62],"predicates":[63],"tend":[64],"cause":[66],"the":[67,74,87,96,117],"aforementioned":[68],"assumptions":[69],"fail":[71],"[2].":[72,110],"Since":[73],"estimate":[76],"a":[78,103],"result":[79],"depends":[83],"underlying":[88],"joins,":[89],"it":[90],"has":[91],"been":[92],"shown":[93],"that":[94],"improving":[95,116],"accuracy":[97],"join":[99,121],"size":[100],"\"bottom-up\"":[104],"order":[105],"significantly":[107],"improve":[108],"performance":[109],"Thus,":[111],"our":[112],"research":[113],"aims":[114],"at":[115],"two-table":[120],"sizes.":[122]},"counts_by_year":[{"year":2026,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}