{"id":"https://openalex.org/W4393180319","doi":"https://doi.org/10.1145/3639321","title":"Approximate Sketches","display_name":"Approximate Sketches","publication_year":2024,"publication_date":"2024-03-12","ids":{"openalex":"https://openalex.org/W4393180319","doi":"https://doi.org/10.1145/3639321"},"language":"en","primary_location":{"id":"doi:10.1145/3639321","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3639321","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3639321","source":{"id":"https://openalex.org/S4387289859","display_name":"Proceedings of the ACM on Management of Data","issn_l":"2836-6573","issn":["2836-6573"],"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":"Proceedings of the ACM on Management of Data","raw_type":"journal-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"hybrid","oa_url":"https://dl.acm.org/doi/pdf/10.1145/3639321","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5021475646","display_name":"Brian Tsan","orcid":"https://orcid.org/0000-0001-8407-7563"},"institutions":[{"id":"https://openalex.org/I156087764","display_name":"University of California, Merced","ror":"https://ror.org/00d9ah105","country_code":"US","type":"education","lineage":["https://openalex.org/I156087764"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Brian Tsan","raw_affiliation_strings":["University of California, Merced, Merced, CA, USA"],"raw_orcid":"https://orcid.org/0000-0001-8407-7563","affiliations":[{"raw_affiliation_string":"University of California, Merced, Merced, CA, USA","institution_ids":["https://openalex.org/I156087764"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102018009","display_name":"Asoke Kumar Datta","orcid":"https://orcid.org/0009-0001-7161-8444"},"institutions":[{"id":"https://openalex.org/I156087764","display_name":"University of California, Merced","ror":"https://ror.org/00d9ah105","country_code":"US","type":"education","lineage":["https://openalex.org/I156087764"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Asoke Datta","raw_affiliation_strings":["University of California, Merced, Merced, CA, USA"],"raw_orcid":"https://orcid.org/0009-0001-7161-8444","affiliations":[{"raw_affiliation_string":"University of California, Merced, Merced, CA, USA","institution_ids":["https://openalex.org/I156087764"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5065050590","display_name":"Yesdaulet Izenov","orcid":"https://orcid.org/0000-0002-3484-2535"},"institutions":[{"id":"https://openalex.org/I156087764","display_name":"University of California, Merced","ror":"https://ror.org/00d9ah105","country_code":"US","type":"education","lineage":["https://openalex.org/I156087764"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Yesdaulet Izenov","raw_affiliation_strings":["University of California, Merced, Merced, CA, USA"],"raw_orcid":"https://orcid.org/0000-0002-3484-2535","affiliations":[{"raw_affiliation_string":"University of California, Merced, Merced, CA, USA","institution_ids":["https://openalex.org/I156087764"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5065838987","display_name":"Florin Rusu","orcid":"https://orcid.org/0000-0002-7018-9043"},"institutions":[{"id":"https://openalex.org/I156087764","display_name":"University of California, Merced","ror":"https://ror.org/00d9ah105","country_code":"US","type":"education","lineage":["https://openalex.org/I156087764"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Florin Rusu","raw_affiliation_strings":["University of California, Merced, Merced, CA, USA"],"raw_orcid":"https://orcid.org/0000-0002-7018-9043","affiliations":[{"raw_affiliation_string":"University of California, Merced, Merced, CA, USA","institution_ids":["https://openalex.org/I156087764"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5021475646"],"corresponding_institution_ids":["https://openalex.org/I156087764"],"apc_list":null,"apc_paid":null,"fwci":2.7703,"has_fulltext":true,"cited_by_count":5,"citation_normalized_percentile":{"value":0.93726555,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":90,"max":98},"biblio":{"volume":"2","issue":"1","first_page":"1","last_page":"24"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10996","display_name":"Computational Geometry and Mesh Generation","score":0.9911999702453613,"subfield":{"id":"https://openalex.org/subfields/1704","display_name":"Computer Graphics and Computer-Aided Design"},"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/T10996","display_name":"Computational Geometry and Mesh Generation","score":0.9911999702453613,"subfield":{"id":"https://openalex.org/subfields/1704","display_name":"Computer Graphics and Computer-Aided Design"},"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/T11106","display_name":"Data Management and Algorithms","score":0.984000027179718,"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/T10799","display_name":"Data Visualization and Analytics","score":0.9800000190734863,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"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":0.4390658736228943}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.4390658736228943}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3639321","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3639321","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3639321","source":{"id":"https://openalex.org/S4387289859","display_name":"Proceedings of the ACM on Management of Data","issn_l":"2836-6573","issn":["2836-6573"],"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":"Proceedings of the ACM on Management of Data","raw_type":"journal-article"}],"best_oa_location":{"id":"doi:10.1145/3639321","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3639321","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3639321","source":{"id":"https://openalex.org/S4387289859","display_name":"Proceedings of the ACM on Management of Data","issn_l":"2836-6573","issn":["2836-6573"],"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":"Proceedings of the ACM on Management of Data","raw_type":"journal-article"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/16","score":0.47999998927116394,"display_name":"Peace, Justice and strong institutions"}],"awards":[{"id":"https://openalex.org/G2634215095","display_name":null,"funder_award_id":"2008815","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"}],"funders":[{"id":"https://openalex.org/F4320306076","display_name":"National Science Foundation","ror":"https://ror.org/021nxhr62"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4393180319.pdf","grobid_xml":"https://content.openalex.org/works/W4393180319.grobid-xml"},"referenced_works_count":23,"referenced_works":["https://openalex.org/W1519039476","https://openalex.org/W2013092187","https://openalex.org/W2080234606","https://openalex.org/W2080745194","https://openalex.org/W2123845384","https://openalex.org/W2132823934","https://openalex.org/W2144982963","https://openalex.org/W2243803726","https://openalex.org/W2747329762","https://openalex.org/W2788186722","https://openalex.org/W2915063781","https://openalex.org/W2953212265","https://openalex.org/W2991530444","https://openalex.org/W3013555795","https://openalex.org/W3097225903","https://openalex.org/W3124277639","https://openalex.org/W3177390287","https://openalex.org/W3197977787","https://openalex.org/W3198024709","https://openalex.org/W4221142004","https://openalex.org/W4226086155","https://openalex.org/W4289706945","https://openalex.org/W4393180319"],"related_works":["https://openalex.org/W2748952813","https://openalex.org/W2390279801","https://openalex.org/W2358668433","https://openalex.org/W2376932109","https://openalex.org/W2001405890","https://openalex.org/W2382290278","https://openalex.org/W2478288626","https://openalex.org/W4391913857","https://openalex.org/W2350741829","https://openalex.org/W2530322880"],"abstract_inverted_index":{"Sketches":[0],"are":[1,17,33],"single-pass":[2],"small-space":[3],"data":[4],"summaries":[5],"that":[6,109],"can":[7,51,67,178],"quickly":[8],"estimate":[9,145],"the":[10,123,146,152,163,206,212],"cardinality":[11,99,113,186],"of":[12,82,125,148,151,208,216,225,227,245],"join":[13,22,132,185],"queries.":[14],"However,":[15],"sketches":[16,47,66,130,183,194,218,233,239],"not":[18],"directly":[19],"applicable":[20],"to":[21,41,112,121,144,172,197,237],"queries":[23,133,220],"with":[24,134,205,221,240],"dynamic":[25],"filter":[26,135],"conditions":[27],"---":[28,35,84,92],"where":[29],"arbitrary":[30,127,156],"selection":[31,222],"predicate(s)":[32],"applied":[34],"since":[36],"a":[37,42,80,117,139,173],"sketch":[38,96,124,147],"is":[39,93,104,170],"limited":[40],"fixed":[43],"selection.":[44,74,157],"While":[45],"multiple":[46],"for":[48,72,98,131,184],"various":[49],"selections":[50],"be":[52,68,198],"used":[53],"in":[54,86,101],"combination,":[55],"they":[56],"each":[57,142],"incur":[58],"individual":[59],"storage":[60],"and":[61,201,214,229],"maintenance":[62],"costs.":[63],"Alternatively,":[64],"exact":[65,238],"built":[69],"during":[70],"runtime":[71],"every":[73],"To":[75],"make":[76],"this":[77,160],"process":[78],"scale,":[79],"high-degree":[81],"parallelism":[83],"available":[85],"hardware":[87],"accelerators":[88],"such":[89],"as":[90],"GPUs":[91],"required.":[94],"Therefore,":[95],"usage":[97],"estimation":[100],"query":[102],"optimization":[103],"limited.":[105],"Following":[106],"recent":[107],"work":[108],"applies":[110],"transformers":[111,177],"estimation,":[114],"we":[115],"design":[116],"novel":[118],"learning-based":[119],"method":[120],"approximate":[122,179,193,217],"any":[126,149,155,180],"selection,":[128],"enabling":[129,182],"conditions.":[136,231],"We":[137,210],"train":[138],"transformer":[140],"on":[141,219],"table":[143,167],"subset":[150],"table,":[153],"i.e.,":[154],"Transformers":[158],"achieve":[159,234],"by":[161],"learning":[162],"joint":[164],"distribution":[165],"amongst":[166],"attributes,":[168],"which":[169],"equivalent":[171],"multidimensional":[174],"sketch.":[175],"Subsequently,":[176],"sketch,":[181],"estimation.":[187],"In":[188],"turn,":[189],"estimating":[190],"joins":[191],"via":[192],"allows":[195],"tables":[196],"modeled":[199],"individually":[200],"thus":[202],"scales":[203],"linearly":[204],"number":[207],"tables.":[209],"evaluate":[211],"accuracy":[213,236],"efficacy":[215],"predicates":[223],"consisting":[224],"conjunctions":[226],"point":[228],"range":[230],"Approximate":[232],"similar":[235],"at":[241],"least":[242],"one":[243],"order":[244],"magnitude":[246],"less":[247],"overhead.":[248]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":3},{"year":2024,"cited_by_count":1}],"updated_date":"2026-05-21T09:19:25.381259","created_date":"2025-10-10T00:00:00"}