{"id":"https://openalex.org/W4281867143","doi":"https://doi.org/10.1145/3514221.3526168","title":"SAM: Database Generation from Query Workloads with Supervised Autoregressive Models","display_name":"SAM: Database Generation from Query Workloads with Supervised Autoregressive Models","publication_year":2022,"publication_date":"2022-06-10","ids":{"openalex":"https://openalex.org/W4281867143","doi":"https://doi.org/10.1145/3514221.3526168"},"language":"en","primary_location":{"id":"doi:10.1145/3514221.3526168","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3514221.3526168","pdf_url":null,"source":{"id":"https://openalex.org/S4363608845","display_name":"Proceedings of the 2022 International Conference on Management of Data","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 2022 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/A5028543950","display_name":"Jingyi Yang","orcid":"https://orcid.org/0000-0001-8219-9460"},"institutions":[{"id":"https://openalex.org/I172675005","display_name":"Nanyang Technological University","ror":"https://ror.org/02e7b5302","country_code":"SG","type":"education","lineage":["https://openalex.org/I172675005"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Jingyi Yang","raw_affiliation_strings":["Nanyang Technological University, Singapore, Singapore"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Nanyang Technological University, Singapore, Singapore","institution_ids":["https://openalex.org/I172675005"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5025301571","display_name":"Peizhi Wu","orcid":"https://orcid.org/0009-0006-4765-8733"},"institutions":[{"id":"https://openalex.org/I79576946","display_name":"University of Pennsylvania","ror":"https://ror.org/00b30xv10","country_code":"US","type":"education","lineage":["https://openalex.org/I79576946"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Peizhi Wu","raw_affiliation_strings":["University of Pennsylvania, Philadelphia, PA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Pennsylvania, Philadelphia, PA, USA","institution_ids":["https://openalex.org/I79576946"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5045198704","display_name":"Gao Cong","orcid":"https://orcid.org/0000-0002-4430-6373"},"institutions":[{"id":"https://openalex.org/I172675005","display_name":"Nanyang Technological University","ror":"https://ror.org/02e7b5302","country_code":"SG","type":"education","lineage":["https://openalex.org/I172675005"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Gao Cong","raw_affiliation_strings":["Nanyang Technological University, Singapore, Singapore"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Nanyang Technological University, Singapore, Singapore","institution_ids":["https://openalex.org/I172675005"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101487889","display_name":"Tieying Zhang","orcid":"https://orcid.org/0009-0003-2250-5528"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Tieying Zhang","raw_affiliation_strings":["ByteDance Inc., Mountain View, CA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"ByteDance Inc., Mountain View, CA, USA","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5101661867","display_name":"Xiao He","orcid":"https://orcid.org/0000-0001-7959-2157"},"institutions":[{"id":"https://openalex.org/I45928872","display_name":"Alibaba Group (China)","ror":"https://ror.org/00k642b80","country_code":"CN","type":"company","lineage":["https://openalex.org/I45928872"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xiao He","raw_affiliation_strings":["Alibaba Group, Hangzhou, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Alibaba Group, Hangzhou, China","institution_ids":["https://openalex.org/I45928872"]}]}],"institutions":[],"countries_distinct_count":3,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":13,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1542","last_page":"1555"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11106","display_name":"Data Management and Algorithms","score":0.9987999796867371,"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":0.9987999796867371,"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/T10764","display_name":"Privacy-Preserving Technologies in Data","score":0.9977999925613403,"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/T11719","display_name":"Data Quality and Management","score":0.9959999918937683,"subfield":{"id":"https://openalex.org/subfields/1803","display_name":"Management Science and Operations Research"},"field":{"id":"https://openalex.org/fields/18","display_name":"Decision Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8472276329994202},{"id":"https://openalex.org/keywords/database","display_name":"Database","score":0.6505756378173828},{"id":"https://openalex.org/keywords/query-optimization","display_name":"Query optimization","score":0.5932167172431946},{"id":"https://openalex.org/keywords/online-aggregation","display_name":"Online aggregation","score":0.5850930213928223},{"id":"https://openalex.org/keywords/cardinality","display_name":"Cardinality (data modeling)","score":0.5763636231422424},{"id":"https://openalex.org/keywords/view","display_name":"View","score":0.5569590330123901},{"id":"https://openalex.org/keywords/cloud-computing","display_name":"Cloud computing","score":0.49389034509658813},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.4871029853820801},{"id":"https://openalex.org/keywords/database-administrator","display_name":"Database administrator","score":0.4646247327327728},{"id":"https://openalex.org/keywords/leverage","display_name":"Leverage (statistics)","score":0.4131473898887634},{"id":"https://openalex.org/keywords/sargable","display_name":"Sargable","score":0.4104059338569641},{"id":"https://openalex.org/keywords/database-design","display_name":"Database design","score":0.32256388664245605},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.28031057119369507},{"id":"https://openalex.org/keywords/web-search-query","display_name":"Web search query","score":0.2789614200592041},{"id":"https://openalex.org/keywords/search-engine","display_name":"Search engine","score":0.1237649917602539},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.11594089865684509}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8472276329994202},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.6505756378173828},{"id":"https://openalex.org/C157692150","wikidata":"https://www.wikidata.org/wiki/Q2919848","display_name":"Query optimization","level":2,"score":0.5932167172431946},{"id":"https://openalex.org/C24028149","wikidata":"https://www.wikidata.org/wiki/Q7094056","display_name":"Online aggregation","level":5,"score":0.5850930213928223},{"id":"https://openalex.org/C87117476","wikidata":"https://www.wikidata.org/wiki/Q362383","display_name":"Cardinality (data modeling)","level":2,"score":0.5763636231422424},{"id":"https://openalex.org/C54239708","wikidata":"https://www.wikidata.org/wiki/Q1329910","display_name":"View","level":3,"score":0.5569590330123901},{"id":"https://openalex.org/C79974875","wikidata":"https://www.wikidata.org/wiki/Q483639","display_name":"Cloud computing","level":2,"score":0.49389034509658813},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.4871029853820801},{"id":"https://openalex.org/C70236469","wikidata":"https://www.wikidata.org/wiki/Q1078262","display_name":"Database administrator","level":2,"score":0.4646247327327728},{"id":"https://openalex.org/C153083717","wikidata":"https://www.wikidata.org/wiki/Q6535263","display_name":"Leverage (statistics)","level":2,"score":0.4131473898887634},{"id":"https://openalex.org/C192939062","wikidata":"https://www.wikidata.org/wiki/Q104840822","display_name":"Sargable","level":4,"score":0.4104059338569641},{"id":"https://openalex.org/C148840519","wikidata":"https://www.wikidata.org/wiki/Q1049878","display_name":"Database design","level":2,"score":0.32256388664245605},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.28031057119369507},{"id":"https://openalex.org/C164120249","wikidata":"https://www.wikidata.org/wiki/Q995982","display_name":"Web search query","level":3,"score":0.2789614200592041},{"id":"https://openalex.org/C97854310","wikidata":"https://www.wikidata.org/wiki/Q19541","display_name":"Search engine","level":2,"score":0.1237649917602539},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.11594089865684509},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3514221.3526168","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3514221.3526168","pdf_url":null,"source":{"id":"https://openalex.org/S4363608845","display_name":"Proceedings of the 2022 International Conference on Management of Data","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 2022 International Conference on Management of Data","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G2818574155","display_name":null,"funder_award_id":"MOE2019-T2-2-181, RG114/19(S)","funder_id":"https://openalex.org/F4320320751","funder_display_name":"Ministry of Education - Singapore"}],"funders":[{"id":"https://openalex.org/F4320320751","display_name":"Ministry of Education - Singapore","ror":"https://ror.org/01kcva023"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":26,"referenced_works":["https://openalex.org/W1511986666","https://openalex.org/W1967927843","https://openalex.org/W1982183556","https://openalex.org/W1999602050","https://openalex.org/W2022431239","https://openalex.org/W2022858489","https://openalex.org/W2039811614","https://openalex.org/W2132823934","https://openalex.org/W2136114025","https://openalex.org/W2151583733","https://openalex.org/W2159114365","https://openalex.org/W2396309311","https://openalex.org/W2396635388","https://openalex.org/W2755385361","https://openalex.org/W2911540814","https://openalex.org/W2991530444","https://openalex.org/W3013555795","https://openalex.org/W3021702690","https://openalex.org/W3173622057","https://openalex.org/W3183953540","https://openalex.org/W4233471163","https://openalex.org/W4240788698","https://openalex.org/W4241858315","https://openalex.org/W6683468401","https://openalex.org/W6758271856","https://openalex.org/W6770828584"],"related_works":["https://openalex.org/W2554271401","https://openalex.org/W2889903446","https://openalex.org/W2992414350","https://openalex.org/W3125756434","https://openalex.org/W2150741898","https://openalex.org/W4281289408","https://openalex.org/W2371929047","https://openalex.org/W2249768123","https://openalex.org/W185198413","https://openalex.org/W2955368753"],"abstract_inverted_index":{"With":[0],"the":[1,12,40,59,133,136,139,144,160,174,179,202,211],"prevalence":[2],"of":[3,56,135,141,156,178],"cloud":[4,13,25],"databases,":[5],"database":[6,14,34,66,74,112,197],"users":[7],"are":[8],"increasingly":[9],"reliant":[10],"on":[11,184],"providers":[15,26],"to":[16,27,39,47,62,88,121,152,192,210],"manage":[17],"their":[18,89],"data.":[19,42],"It":[20],"becomes":[21],"a":[22,32,49,54,64,105,169,195],"challenge":[23],"for":[24,31,73,111],"benchmark":[28],"different":[29],"DBMS":[30],"specific":[33],"instance":[35],"without":[36],"having":[37],"access":[38],"underlying":[41],"One":[43],"viable":[44],"solution":[45],"is":[46,119,130,190,208],"leverage":[48],"query":[50,69,85,115,124,137],"workload,":[51,138],"which":[52],"contains":[53],"set":[55],"queries":[57],"and":[58,92,143,164],"corresponding":[60],"cardinalities,":[61],"generate":[63,194],"synthetic":[65],"with":[67,76],"similar":[68],"performance.":[70],"Existing":[71],"methods":[72],"generation":[75,113],"cardinality":[77,204],"constraints,":[78,205],"however,":[79],"can":[80],"only":[81,200],"handle":[82],"very":[83],"small":[84],"workloads":[86,125],"due":[87],"high":[90],"complexity":[91,129],"encounter":[93],"challenges":[94],"when":[95],"handling":[96],"join":[97,166,177],"queries.":[98],"In":[99],"this":[100],"work,":[101],"we":[102,149],"propose":[103],"SAM,":[104],"supervised":[106],"deep":[107,161],"autoregressive":[108,162],"model-based":[109],"method":[110],"from":[114,159],"workloads.":[116],"First,":[117],"SAM":[118,189],"able":[120,191],"process":[122],"large-scale":[123],"efficiently":[126,193],"as":[127],"its":[128],"linear":[131],"in":[132,168],"size":[134],"number":[140],"attributes":[142],"attribute":[145],"domain":[146],"size.":[147],"Second,":[148],"develop":[150],"algorithms":[151],"obtain":[153],"unbiased":[154],"samples":[155],"base":[157],"relations":[158],"model":[163],"assign":[165],"keys":[167],"way":[170],"that":[171,188,198],"accurately":[172],"recovers":[173],"full":[175],"outer":[176],"target":[180,212],"database.":[181,213],"Comprehensive":[182],"experiments":[183],"real-world":[185],"datasets":[186],"demonstrate":[187],"high-fidelity":[196],"not":[199],"satisfies":[201],"input":[203],"but":[206],"also":[207],"close":[209]},"counts_by_year":[{"year":2026,"cited_by_count":3},{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":6},{"year":2023,"cited_by_count":3}],"updated_date":"2026-07-17T09:13:05.818461","created_date":"2025-10-10T00:00:00"}
