{"id":"https://openalex.org/W3097386436","doi":"https://doi.org/10.1145/3393527.3393534","title":"Improving Multi-set Query Processing Via a Learned Oracle","display_name":"Improving Multi-set Query Processing Via a Learned Oracle","publication_year":2020,"publication_date":"2020-05-22","ids":{"openalex":"https://openalex.org/W3097386436","doi":"https://doi.org/10.1145/3393527.3393534","mag":"3097386436"},"language":"en","primary_location":{"id":"doi:10.1145/3393527.3393534","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3393527.3393534","pdf_url":null,"source":{"id":"https://openalex.org/S4306523950","display_name":"Proceedings of the ACM Turing Celebration Conference - China","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the ACM Turing Celebration Conference - China","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/A5103229840","display_name":"Jingwen Cai","orcid":"https://orcid.org/0000-0003-2112-0047"},"institutions":[{"id":"https://openalex.org/I55022517","display_name":"Heilongjiang University","ror":"https://ror.org/04zyhq975","country_code":"CN","type":"education","lineage":["https://openalex.org/I55022517"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Jingwen Cai","raw_affiliation_strings":["Heilongjiang University, Harbin, China"],"affiliations":[{"raw_affiliation_string":"Heilongjiang University, Harbin, China","institution_ids":["https://openalex.org/I55022517"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100351700","display_name":"Wenbin He","orcid":"https://orcid.org/0000-0003-1700-6057"},"institutions":[{"id":"https://openalex.org/I55022517","display_name":"Heilongjiang University","ror":"https://ror.org/04zyhq975","country_code":"CN","type":"education","lineage":["https://openalex.org/I55022517"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Wenbin He","raw_affiliation_strings":["Heilongjiang University, Harbin, China"],"affiliations":[{"raw_affiliation_string":"Heilongjiang University, Harbin, China","institution_ids":["https://openalex.org/I55022517"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5072762520","display_name":"Li Yu","orcid":"https://orcid.org/0000-0002-0569-2267"},"institutions":[{"id":"https://openalex.org/I55022517","display_name":"Heilongjiang University","ror":"https://ror.org/04zyhq975","country_code":"CN","type":"education","lineage":["https://openalex.org/I55022517"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yu Li","raw_affiliation_strings":["Heilongjiang University, Harbin, China"],"affiliations":[{"raw_affiliation_string":"Heilongjiang University, Harbin, China","institution_ids":["https://openalex.org/I55022517"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101841009","display_name":"Xian Zhang","orcid":"https://orcid.org/0000-0001-7023-7351"},"institutions":[{"id":"https://openalex.org/I55022517","display_name":"Heilongjiang University","ror":"https://ror.org/04zyhq975","country_code":"CN","type":"education","lineage":["https://openalex.org/I55022517"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xian Zhang","raw_affiliation_strings":["Heilongjiang University, Harbin, China"],"affiliations":[{"raw_affiliation_string":"Heilongjiang University, Harbin, China","institution_ids":["https://openalex.org/I55022517"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100731288","display_name":"Lingli Li","orcid":"https://orcid.org/0000-0001-8898-5817"},"institutions":[{"id":"https://openalex.org/I55022517","display_name":"Heilongjiang University","ror":"https://ror.org/04zyhq975","country_code":"CN","type":"education","lineage":["https://openalex.org/I55022517"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Lingli Li","raw_affiliation_strings":["Heilongjiang University, Harbin, China"],"affiliations":[{"raw_affiliation_string":"Heilongjiang University, Harbin, China","institution_ids":["https://openalex.org/I55022517"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5103229840"],"corresponding_institution_ids":["https://openalex.org/I55022517"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.14092954,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"33","last_page":"37"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11106","display_name":"Data Management and Algorithms","score":0.9961000084877014,"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":0.9961000084877014,"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/T11478","display_name":"Caching and Content Delivery","score":0.9955999851226807,"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/T11273","display_name":"Advanced Graph Neural Networks","score":0.9908999800682068,"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/computer-science","display_name":"Computer science","score":0.8371410369873047},{"id":"https://openalex.org/keywords/oracle","display_name":"Oracle","score":0.778049111366272},{"id":"https://openalex.org/keywords/bloom-filter","display_name":"Bloom filter","score":0.6800408363342285},{"id":"https://openalex.org/keywords/sargable","display_name":"Sargable","score":0.6621123552322388},{"id":"https://openalex.org/keywords/query-optimization","display_name":"Query optimization","score":0.6322038769721985},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.6297823786735535},{"id":"https://openalex.org/keywords/hash-function","display_name":"Hash function","score":0.612829327583313},{"id":"https://openalex.org/keywords/query-expansion","display_name":"Query expansion","score":0.4911186397075653},{"id":"https://openalex.org/keywords/result-set","display_name":"Result set","score":0.4666946232318878},{"id":"https://openalex.org/keywords/web-query-classification","display_name":"Web query classification","score":0.4556979238986969},{"id":"https://openalex.org/keywords/online-aggregation","display_name":"Online aggregation","score":0.44354933500289917},{"id":"https://openalex.org/keywords/key","display_name":"Key (lock)","score":0.4357188642024994},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.42883551120758057},{"id":"https://openalex.org/keywords/theoretical-computer-science","display_name":"Theoretical computer science","score":0.4230678677558899},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.4140084981918335},{"id":"https://openalex.org/keywords/web-search-query","display_name":"Web search query","score":0.3654639720916748},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.27219516038894653},{"id":"https://openalex.org/keywords/search-engine","display_name":"Search engine","score":0.20774146914482117},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.10566717386245728}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8371410369873047},{"id":"https://openalex.org/C55166926","wikidata":"https://www.wikidata.org/wiki/Q2892946","display_name":"Oracle","level":2,"score":0.778049111366272},{"id":"https://openalex.org/C147224247","wikidata":"https://www.wikidata.org/wiki/Q885373","display_name":"Bloom filter","level":2,"score":0.6800408363342285},{"id":"https://openalex.org/C192939062","wikidata":"https://www.wikidata.org/wiki/Q104840822","display_name":"Sargable","level":4,"score":0.6621123552322388},{"id":"https://openalex.org/C157692150","wikidata":"https://www.wikidata.org/wiki/Q2919848","display_name":"Query optimization","level":2,"score":0.6322038769721985},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.6297823786735535},{"id":"https://openalex.org/C99138194","wikidata":"https://www.wikidata.org/wiki/Q183427","display_name":"Hash function","level":2,"score":0.612829327583313},{"id":"https://openalex.org/C99016210","wikidata":"https://www.wikidata.org/wiki/Q5488129","display_name":"Query expansion","level":2,"score":0.4911186397075653},{"id":"https://openalex.org/C4969071","wikidata":"https://www.wikidata.org/wiki/Q7316353","display_name":"Result set","level":3,"score":0.4666946232318878},{"id":"https://openalex.org/C118689300","wikidata":"https://www.wikidata.org/wiki/Q7978614","display_name":"Web query classification","level":4,"score":0.4556979238986969},{"id":"https://openalex.org/C24028149","wikidata":"https://www.wikidata.org/wiki/Q7094056","display_name":"Online aggregation","level":5,"score":0.44354933500289917},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.4357188642024994},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.42883551120758057},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.4230678677558899},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.4140084981918335},{"id":"https://openalex.org/C164120249","wikidata":"https://www.wikidata.org/wiki/Q995982","display_name":"Web search query","level":3,"score":0.3654639720916748},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.27219516038894653},{"id":"https://openalex.org/C97854310","wikidata":"https://www.wikidata.org/wiki/Q19541","display_name":"Search engine","level":2,"score":0.20774146914482117},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.10566717386245728},{"id":"https://openalex.org/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3393527.3393534","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3393527.3393534","pdf_url":null,"source":{"id":"https://openalex.org/S4306523950","display_name":"Proceedings of the ACM Turing Celebration Conference - China","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the ACM Turing Celebration Conference - China","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":13,"referenced_works":["https://openalex.org/W1967373117","https://openalex.org/W2120933912","https://openalex.org/W2136385615","https://openalex.org/W2146005787","https://openalex.org/W2168371416","https://openalex.org/W2199464493","https://openalex.org/W2740863609","https://openalex.org/W2745606257","https://openalex.org/W2890643081","https://openalex.org/W2912601938","https://openalex.org/W2950147551","https://openalex.org/W2962771342","https://openalex.org/W3120740533"],"related_works":["https://openalex.org/W3125756434","https://openalex.org/W2096359267","https://openalex.org/W2006459955","https://openalex.org/W203907944","https://openalex.org/W1560919561","https://openalex.org/W2554271401","https://openalex.org/W1793997780","https://openalex.org/W2395498354","https://openalex.org/W2042441172","https://openalex.org/W1973282744"],"abstract_inverted_index":{"Multi-set":[0],"query":[1,16,41,69,86,97,134],"is":[2,75,127,153,177],"a":[3,59,85,90,105,148,186],"fundamental":[4],"problem":[5,56],"in":[6],"computer":[7],"systems":[8],"and":[9,43,109,130,152,162,185],"applications.":[10],"Most":[11],"traditional":[12,67],"solutions":[13,34],"for":[14],"multi-set":[15,68],"are":[17,31,117],"based":[18],"on":[19,156],"hash":[20],"tables":[21],"or":[22],"bloom":[23,107],"filters.":[24],"However,":[25],"when":[26],"the":[27,47,55,64,101,122,125,132,144,169,171],"sizes":[28],"of":[29,57,66,174],"multi-sets":[30],"large,":[32],"these":[33],"cannot":[35],"achieve":[36],"small":[37,129],"memory":[38,183],"usage,":[39],"fast":[40],"speed":[42],"high":[44],"accuracy":[45],"at":[46],"same":[48],"time.":[49],"In":[50,139],"this":[51],"work,":[52],"we":[53,99,142],"study":[54],"using":[58],"learned":[60,102,145],"oracle":[61,79,103,126,146],"to":[62,76,80,113,168],"improve":[63],"performance":[65,135],"processing":[70],"empirically.":[71],"The":[72],"key":[73],"idea":[74],"train":[77],"an":[78,95,110],"predict":[81],"which":[82],"set":[83],"contains":[84],"item":[87],"e":[88],"as":[89,147],"classification":[91],"problem.":[92],"To":[93],"ensure":[94],"exact":[96],"result,":[98],"combine":[100],"with":[104,180],"standard":[106],"filter":[108],"exact-match":[111],"index":[112],"catch":[114],"items":[115],"that":[116,166],"not":[118,154],"correctly":[119],"identified":[120],"by":[121],"oracle.":[123],"When":[124],"both":[128],"efficient,":[131],"whole":[133],"can":[136],"be":[137],"improved.":[138],"our":[140,175],"framework,":[141],"treat":[143],"complete":[149],"black":[150],"box,":[151],"dependent":[155],"its":[157],"inner":[158],"workings.":[159],"Theoretical":[160],"proofs":[161],"experimental":[163],"results":[164],"show":[165],"compared":[167],"state-of-the-art,":[170],"error":[172],"rate":[173],"approach":[176],"0%":[178],"even":[179],"much":[181],"less":[182],"usage":[184],"comparable":[187],"speed.":[188]},"counts_by_year":[],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}
