{"id":"https://openalex.org/W4409918354","doi":"https://doi.org/10.1145/3733620.3733635","title":"Reservoir Sampling over Joins","display_name":"Reservoir Sampling over Joins","publication_year":2025,"publication_date":"2025-04-28","ids":{"openalex":"https://openalex.org/W4409918354","doi":"https://doi.org/10.1145/3733620.3733635"},"language":"en","primary_location":{"id":"doi:10.1145/3733620.3733635","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3733620.3733635","pdf_url":null,"source":{"id":"https://openalex.org/S47508943","display_name":"ACM SIGMOD Record","issn_l":"0163-5808","issn":["0163-5808","1943-5835"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319798","host_organization_name":"Association for Computing Machinery","host_organization_lineage":["https://openalex.org/P4310319798"],"host_organization_lineage_names":["Association for Computing Machinery"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ACM SIGMOD Record","raw_type":"journal-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/A5090917255","display_name":"Binyang Dai","orcid":"https://orcid.org/0009-0000-5438-7288"},"institutions":[{"id":"https://openalex.org/I200769079","display_name":"Hong Kong University of Science and Technology","ror":"https://ror.org/00q4vv597","country_code":"HK","type":"education","lineage":["https://openalex.org/I200769079"]}],"countries":["HK"],"is_corresponding":false,"raw_author_name":"Binyang Dai","raw_affiliation_strings":["HKUST"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"HKUST","institution_ids":["https://openalex.org/I200769079"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5034417920","display_name":"Xiao Hu","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":false,"raw_author_name":"Xiao Hu","raw_affiliation_strings":["University of Waterloo"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Waterloo","institution_ids":["https://openalex.org/I151746483"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5009196125","display_name":"Ke Yi","orcid":"https://orcid.org/0000-0002-2178-3716"},"institutions":[{"id":"https://openalex.org/I200769079","display_name":"Hong Kong University of Science and Technology","ror":"https://ror.org/00q4vv597","country_code":"HK","type":"education","lineage":["https://openalex.org/I200769079"]}],"countries":["HK"],"is_corresponding":false,"raw_author_name":"Ke Yi","raw_affiliation_strings":["HKUST"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"HKUST","institution_ids":["https://openalex.org/I200769079"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.10282783,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"54","issue":"1","first_page":"70","last_page":"78"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11801","display_name":"Reservoir Engineering and Simulation Methods","score":0.9962999820709229,"subfield":{"id":"https://openalex.org/subfields/2212","display_name":"Ocean Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},"topics":[{"id":"https://openalex.org/T11801","display_name":"Reservoir Engineering and Simulation Methods","score":0.9962999820709229,"subfield":{"id":"https://openalex.org/subfields/2212","display_name":"Ocean Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T10635","display_name":"Hydraulic Fracturing and Reservoir Analysis","score":0.9656999707221985,"subfield":{"id":"https://openalex.org/subfields/2210","display_name":"Mechanical Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T12761","display_name":"Data Stream Mining Techniques","score":0.9641000032424927,"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":0.9208879470825195},{"id":"https://openalex.org/keywords/sampling","display_name":"Sampling (signal processing)","score":0.6207414865493774},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.40682584047317505},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.08747321367263794},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.04291200637817383}],"concepts":[{"id":"https://openalex.org/C2778692605","wikidata":"https://www.wikidata.org/wiki/Q4041866","display_name":"Joins","level":2,"score":0.9208879470825195},{"id":"https://openalex.org/C140779682","wikidata":"https://www.wikidata.org/wiki/Q210868","display_name":"Sampling (signal processing)","level":3,"score":0.6207414865493774},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.40682584047317505},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.08747321367263794},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.04291200637817383},{"id":"https://openalex.org/C106131492","wikidata":"https://www.wikidata.org/wiki/Q3072260","display_name":"Filter (signal processing)","level":2,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1145/3733620.3733635","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3733620.3733635","pdf_url":null,"source":{"id":"https://openalex.org/S47508943","display_name":"ACM SIGMOD Record","issn_l":"0163-5808","issn":["0163-5808","1943-5835"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319798","host_organization_name":"Association for Computing Machinery","host_organization_lineage":["https://openalex.org/P4310319798"],"host_organization_lineage_names":["Association for Computing Machinery"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ACM SIGMOD Record","raw_type":"journal-article"},{"id":"pmh:oai:repository.hkust.edu.hk:1783.1-138352","is_oa":false,"landing_page_url":"http://repository.hkust.edu.hk/ir/Record/1783.1-138352","pdf_url":null,"source":{"id":"https://openalex.org/S4306401796","display_name":"Rare & Special e-Zone (The Hong Kong University of Science and Technology)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I200769079","host_organization_name":"Hong Kong University of Science and Technology","host_organization_lineage":["https://openalex.org/I200769079"],"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":"Article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":14,"referenced_works":["https://openalex.org/W1964857063","https://openalex.org/W2027002571","https://openalex.org/W2104498537","https://openalex.org/W2119885577","https://openalex.org/W2146492010","https://openalex.org/W2752908210","https://openalex.org/W2798499404","https://openalex.org/W3013303285","https://openalex.org/W3030381022","https://openalex.org/W3032788150","https://openalex.org/W4241185933","https://openalex.org/W4379135629","https://openalex.org/W4379135714","https://openalex.org/W6998509810"],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2899084033","https://openalex.org/W2748952813","https://openalex.org/W2088925915","https://openalex.org/W2382891957","https://openalex.org/W2393491644","https://openalex.org/W2067184662","https://openalex.org/W3047837489","https://openalex.org/W2622139626","https://openalex.org/W2133660117"],"abstract_inverted_index":{"Sampling":[0],"over":[1,58,135,148,160],"joins":[2,59],"is":[3],"a":[4,22,55,104,112,120,127,130],"fundamental":[5],"task":[6],"in":[7],"large-scale":[8],"data":[9,147],"analytics.":[10],"Instead":[11],"of":[12,25,51,163],"computing":[13],"the":[14,26,49,61,67,83,87,92,100,153,161,164],"full":[15],"join":[16,27,84,93,150],"results,":[17],"which":[18],"could":[19],"be":[20,72,96],"massive,":[21],"uniform":[23],"sample":[24,57],"results":[28,155],"would":[29],"suffice":[30],"for":[31,107,133],"many":[32],"purposes,":[33],"such":[34],"as":[35,91],"answering":[36],"analytical":[37],"queries":[38],"or":[39],"training":[40],"machine":[41],"learning":[42],"models.":[43],"In":[44],"this":[45,69,108],"paper,":[46],"we":[47],"study":[48],"problem":[50,70,88,109],"how":[52],"to":[53],"maintain":[54],"random":[56],"while":[60],"tuples":[62],"are":[63,119],"streaming":[64],"in.":[65],"Without":[66],"join,":[68],"can":[71,95],"solved":[73],"by":[74],"some":[75],"simple":[76],"and":[77,129,145,152],"classical":[78],"reservoir":[79,122],"sampling":[80,123,134],"algorithms.":[81],"However,":[82],"operator":[85],"makes":[86],"significantly":[89],"harder,":[90],"size":[94],"polynomially":[97],"larger":[98],"than":[99],"input.":[101],"We":[102,137],"present":[103],"new":[105],"algorithm":[106,124],"that":[110,125],"achieves":[111],"near-linear":[113],"complexity.":[114],"The":[115],"key":[116],"technical":[117],"components":[118],"generalized":[121],"supports":[126],"predicate,":[128],"dynamic":[131],"index":[132],"joins.":[136],"also":[138],"conduct":[139],"extensive":[140],"experiments":[141],"on":[142],"both":[143],"graph":[144],"relational":[146],"various":[149],"queries,":[151],"experimental":[154],"demonstrate":[156],"significant":[157],"performance":[158],"improvement":[159],"state":[162],"art.":[165]},"counts_by_year":[],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}