{"id":"https://openalex.org/W7118852444","doi":"https://doi.org/10.1145/3787855","title":"Reservoir Sampling over Joins","display_name":"Reservoir Sampling over Joins","publication_year":2026,"publication_date":"2026-01-07","ids":{"openalex":"https://openalex.org/W7118852444","doi":"https://doi.org/10.1145/3787855"},"language":"en","primary_location":{"id":"doi:10.1145/3787855","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3787855","pdf_url":null,"source":{"id":"https://openalex.org/S90119964","display_name":"ACM Transactions on Database Systems","issn_l":"0362-5915","issn":["0362-5915","1557-4644"],"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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ACM Transactions on Database Systems","raw_type":"journal-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"hybrid","oa_url":"https://doi.org/10.1145/3787855","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"]},{"id":"https://openalex.org/I889458895","display_name":"University of Hong Kong","ror":"https://ror.org/02zhqgq86","country_code":"HK","type":"education","lineage":["https://openalex.org/I889458895"]}],"countries":["HK"],"is_corresponding":false,"raw_author_name":"Binyang Dai","raw_affiliation_strings":["The Hong Kong University of Science and Technology School of Engineering"],"raw_orcid":"https://orcid.org/0009-0000-5438-7288","affiliations":[{"raw_affiliation_string":"The Hong Kong University of Science and Technology School of Engineering","institution_ids":["https://openalex.org/I200769079","https://openalex.org/I889458895"]}]},{"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":["Computer Science, University of Waterloo"],"raw_orcid":"https://orcid.org/0000-0002-7890-665X","affiliations":[{"raw_affiliation_string":"Computer Science, University of Waterloo","institution_ids":["https://openalex.org/I151746483"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5122253664","display_name":"Ke Yi","orcid":null},"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"]},{"id":"https://openalex.org/I889458895","display_name":"University of Hong Kong","ror":"https://ror.org/02zhqgq86","country_code":"HK","type":"education","lineage":["https://openalex.org/I889458895"]}],"countries":["HK"],"is_corresponding":false,"raw_author_name":"Ke Yi","raw_affiliation_strings":["The Hong Kong University of Science and Technology School of Engineering"],"raw_orcid":"https://orcid.org/0000-0002-2178-3716","affiliations":[{"raw_affiliation_string":"The Hong Kong University of Science and Technology School of Engineering","institution_ids":["https://openalex.org/I200769079","https://openalex.org/I889458895"]}]}],"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":0.03480399,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"51","issue":"2","first_page":"1","last_page":"35"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12611","display_name":"Neural Networks and Reservoir Computing","score":0.19020000100135803,"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/T12611","display_name":"Neural Networks and Reservoir Computing","score":0.19020000100135803,"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/T12205","display_name":"Time Series Analysis and Forecasting","score":0.17100000381469727,"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/T11273","display_name":"Advanced Graph Neural Networks","score":0.08659999817609787,"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":0.9517999887466431},{"id":"https://openalex.org/keywords/tuple","display_name":"Tuple","score":0.8601999878883362},{"id":"https://openalex.org/keywords/join","display_name":"Join (topology)","score":0.6891999840736389},{"id":"https://openalex.org/keywords/sampling","display_name":"Sampling (signal processing)","score":0.5837000012397766},{"id":"https://openalex.org/keywords/graph","display_name":"Graph","score":0.5719000101089478},{"id":"https://openalex.org/keywords/operator","display_name":"Operator (biology)","score":0.5503000020980835},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.5468999743461609}],"concepts":[{"id":"https://openalex.org/C2778692605","wikidata":"https://www.wikidata.org/wiki/Q4041866","display_name":"Joins","level":2,"score":0.9517999887466431},{"id":"https://openalex.org/C118930307","wikidata":"https://www.wikidata.org/wiki/Q600590","display_name":"Tuple","level":2,"score":0.8601999878883362},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8583999872207642},{"id":"https://openalex.org/C2776124973","wikidata":"https://www.wikidata.org/wiki/Q3183033","display_name":"Join (topology)","level":2,"score":0.6891999840736389},{"id":"https://openalex.org/C140779682","wikidata":"https://www.wikidata.org/wiki/Q210868","display_name":"Sampling (signal processing)","level":3,"score":0.5837000012397766},{"id":"https://openalex.org/C132525143","wikidata":"https://www.wikidata.org/wiki/Q141488","display_name":"Graph","level":2,"score":0.5719000101089478},{"id":"https://openalex.org/C17020691","wikidata":"https://www.wikidata.org/wiki/Q139677","display_name":"Operator (biology)","level":5,"score":0.5503000020980835},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.5468999743461609},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.489300012588501},{"id":"https://openalex.org/C198531522","wikidata":"https://www.wikidata.org/wiki/Q485146","display_name":"Sample (material)","level":2,"score":0.4675000011920929},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.42570000886917114},{"id":"https://openalex.org/C20353970","wikidata":"https://www.wikidata.org/wiki/Q1056998","display_name":"Simple random sample","level":3,"score":0.41839998960494995},{"id":"https://openalex.org/C5655090","wikidata":"https://www.wikidata.org/wiki/Q192588","display_name":"Relational database","level":2,"score":0.40529999136924744},{"id":"https://openalex.org/C2780586882","wikidata":"https://www.wikidata.org/wiki/Q7520643","display_name":"Simple (philosophy)","level":2,"score":0.34369999170303345},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.3416000008583069},{"id":"https://openalex.org/C48103436","wikidata":"https://www.wikidata.org/wiki/Q599031","display_name":"State (computer science)","level":2,"score":0.3019999861717224},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.27459999918937683},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.2694999873638153},{"id":"https://openalex.org/C138827492","wikidata":"https://www.wikidata.org/wiki/Q6661985","display_name":"Data processing","level":2,"score":0.2578999996185303},{"id":"https://openalex.org/C88230418","wikidata":"https://www.wikidata.org/wiki/Q131476","display_name":"Graph theory","level":2,"score":0.2522999942302704}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3787855","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3787855","pdf_url":null,"source":{"id":"https://openalex.org/S90119964","display_name":"ACM Transactions on Database Systems","issn_l":"0362-5915","issn":["0362-5915","1557-4644"],"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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ACM Transactions on Database Systems","raw_type":"journal-article"}],"best_oa_location":{"id":"doi:10.1145/3787855","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3787855","pdf_url":null,"source":{"id":"https://openalex.org/S90119964","display_name":"ACM Transactions on Database Systems","issn_l":"0362-5915","issn":["0362-5915","1557-4644"],"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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ACM Transactions on Database Systems","raw_type":"journal-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":16,"referenced_works":["https://openalex.org/W1579803282","https://openalex.org/W2094308804","https://openalex.org/W2119885577","https://openalex.org/W2146492010","https://openalex.org/W2592257482","https://openalex.org/W2798499404","https://openalex.org/W2798659310","https://openalex.org/W3028618047","https://openalex.org/W3028842054","https://openalex.org/W3030381022","https://openalex.org/W3032788150","https://openalex.org/W4214495955","https://openalex.org/W4237172715","https://openalex.org/W4241185933","https://openalex.org/W4379135629","https://openalex.org/W4379135714"],"related_works":[],"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],"article,":[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":"2026-01-08T00:00:00"}