{"id":"https://openalex.org/W4380433195","doi":"https://doi.org/10.1145/3588935","title":"JoinSketch: A Sketch Algorithm for Accurate and Unbiased Inner-Product Estimation","display_name":"JoinSketch: A Sketch Algorithm for Accurate and Unbiased Inner-Product Estimation","publication_year":2023,"publication_date":"2023-05-26","ids":{"openalex":"https://openalex.org/W4380433195","doi":"https://doi.org/10.1145/3588935"},"language":"en","primary_location":{"is_oa":false,"landing_page_url":"https://doi.org/10.1145/3588935","pdf_url":null,"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":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false},"type":"article","type_crossref":"journal-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/A5100703848","display_name":"Feiyu Wang","orcid":"https://orcid.org/0009-0007-4322-2905"},"institutions":[{"id":"https://openalex.org/I4210136793","display_name":"Peng Cheng Laboratory","ror":"https://ror.org/03qdqbt06","country_code":"CN","type":"facility","lineage":["https://openalex.org/I4210136793"]},{"id":"https://openalex.org/I20231570","display_name":"Peking University","ror":"https://ror.org/02v51f717","country_code":"CN","type":"education","lineage":["https://openalex.org/I20231570"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Feiyu Wang","raw_affiliation_strings":["Peking University & Pengcheng Laboratory, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Peking University & Pengcheng Laboratory, Beijing, China","institution_ids":["https://openalex.org/I4210136793","https://openalex.org/I20231570"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102973444","display_name":"Qizhi Chen","orcid":"https://orcid.org/0009-0004-4020-6772"},"institutions":[{"id":"https://openalex.org/I4210136793","display_name":"Peng Cheng Laboratory","ror":"https://ror.org/03qdqbt06","country_code":"CN","type":"facility","lineage":["https://openalex.org/I4210136793"]},{"id":"https://openalex.org/I20231570","display_name":"Peking University","ror":"https://ror.org/02v51f717","country_code":"CN","type":"education","lineage":["https://openalex.org/I20231570"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Qizhi Chen","raw_affiliation_strings":["Peking University & Pengcheng Laboratory, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Peking University & Pengcheng Laboratory, Beijing, China","institution_ids":["https://openalex.org/I4210136793","https://openalex.org/I20231570"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5073374593","display_name":"Yuanpeng Li","orcid":"https://orcid.org/0000-0002-7248-1312"},"institutions":[{"id":"https://openalex.org/I4210136793","display_name":"Peng Cheng Laboratory","ror":"https://ror.org/03qdqbt06","country_code":"CN","type":"facility","lineage":["https://openalex.org/I4210136793"]},{"id":"https://openalex.org/I20231570","display_name":"Peking University","ror":"https://ror.org/02v51f717","country_code":"CN","type":"education","lineage":["https://openalex.org/I20231570"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yuanpeng Li","raw_affiliation_strings":["Peking University & Pengcheng Laboratory, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Peking University & Pengcheng Laboratory, Beijing, China","institution_ids":["https://openalex.org/I4210136793","https://openalex.org/I20231570"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5069277955","display_name":"Tong Yang","orcid":"https://orcid.org/0000-0003-2402-5854"},"institutions":[{"id":"https://openalex.org/I4210136793","display_name":"Peng Cheng Laboratory","ror":"https://ror.org/03qdqbt06","country_code":"CN","type":"facility","lineage":["https://openalex.org/I4210136793"]},{"id":"https://openalex.org/I20231570","display_name":"Peking University","ror":"https://ror.org/02v51f717","country_code":"CN","type":"education","lineage":["https://openalex.org/I20231570"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Tong Yang","raw_affiliation_strings":["Peking University & Pengcheng Laboratory, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Peking University & Pengcheng Laboratory, Beijing, China","institution_ids":["https://openalex.org/I4210136793","https://openalex.org/I20231570"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5034300662","display_name":"Yaofeng Tu","orcid":"https://orcid.org/0000-0002-2616-2273"},"institutions":[{"id":"https://openalex.org/I4210098582","display_name":"ZTE (China)","ror":"https://ror.org/00rjhhq63","country_code":"CN","type":"company","lineage":["https://openalex.org/I4210098582"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yaofeng Tu","raw_affiliation_strings":["ZTE Corporation, Nanjing, China"],"affiliations":[{"raw_affiliation_string":"ZTE Corporation, Nanjing, China","institution_ids":["https://openalex.org/I4210098582"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100758675","display_name":"Lian Yu","orcid":"https://orcid.org/0000-0002-7232-2549"},"institutions":[{"id":"https://openalex.org/I20231570","display_name":"Peking University","ror":"https://ror.org/02v51f717","country_code":"CN","type":"education","lineage":["https://openalex.org/I20231570"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Lian Yu","raw_affiliation_strings":["Peking University, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Peking University, Beijing, China","institution_ids":["https://openalex.org/I20231570"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5062357883","display_name":"Bin Cui","orcid":"https://orcid.org/0000-0003-1681-4677"},"institutions":[{"id":"https://openalex.org/I20231570","display_name":"Peking University","ror":"https://ror.org/02v51f717","country_code":"CN","type":"education","lineage":["https://openalex.org/I20231570"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Bin Cui","raw_affiliation_strings":["Peking University, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Peking University, Beijing, China","institution_ids":["https://openalex.org/I20231570"]}]}],"institution_assertions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":2.466,"has_fulltext":false,"cited_by_count":8,"citation_normalized_percentile":{"value":0.606989,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":94,"max":95},"biblio":{"volume":"1","issue":"1","first_page":"1","last_page":"26"},"is_retracted":false,"is_paratext":false,"primary_topic":{"id":"https://openalex.org/T12761","display_name":"Data Stream Mining Techniques","score":0.9998,"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/T12761","display_name":"Data Stream Mining Techniques","score":0.9998,"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/T10317","display_name":"Advanced Database Systems and Queries","score":0.9991,"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/T11106","display_name":"Data Management and Algorithms","score":0.9963,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/sketch","display_name":"Sketch","score":0.8400939},{"id":"https://openalex.org/keywords/cosine-similarity","display_name":"Cosine similarity","score":0.52721786},{"id":"https://openalex.org/keywords/similarity","display_name":"Similarity (geometry)","score":0.43959886}],"concepts":[{"id":"https://openalex.org/C2779231336","wikidata":"https://www.wikidata.org/wiki/Q7534724","display_name":"Sketch","level":2,"score":0.8400939},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.71966213},{"id":"https://openalex.org/C122342681","wikidata":"https://www.wikidata.org/wiki/Q330828","display_name":"Skewness","level":2,"score":0.56254196},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.5605374},{"id":"https://openalex.org/C90673727","wikidata":"https://www.wikidata.org/wiki/Q901718","display_name":"Product (mathematics)","level":2,"score":0.53794134},{"id":"https://openalex.org/C2780762811","wikidata":"https://www.wikidata.org/wiki/Q1784941","display_name":"Cosine similarity","level":3,"score":0.52721786},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.478783},{"id":"https://openalex.org/C196083921","wikidata":"https://www.wikidata.org/wiki/Q7915758","display_name":"Variance (accounting)","level":2,"score":0.46308595},{"id":"https://openalex.org/C103278499","wikidata":"https://www.wikidata.org/wiki/Q254465","display_name":"Similarity (geometry)","level":3,"score":0.43959886},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.24712375},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.22359335},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.2004146},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.20002061},{"id":"https://openalex.org/C121955636","wikidata":"https://www.wikidata.org/wiki/Q4116214","display_name":"Accounting","level":1,"score":0.0},{"id":"https://openalex.org/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","level":1,"score":0.0},{"id":"https://openalex.org/C144133560","wikidata":"https://www.wikidata.org/wiki/Q4830453","display_name":"Business","level":0,"score":0.0},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"is_oa":false,"landing_page_url":"https://doi.org/10.1145/3588935","pdf_url":null,"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":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false}],"best_oa_location":null,"sustainable_development_goals":[],"grants":[{"funder":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China","award_id":"No. U20A20179, No. 61872011"}],"datasets":[],"versions":[],"referenced_works_count":48,"referenced_works":["https://openalex.org/W139562302","https://openalex.org/W1519039476","https://openalex.org/W1599329921","https://openalex.org/W1601184934","https://openalex.org/W1968625547","https://openalex.org/W1973898816","https://openalex.org/W1977951613","https://openalex.org/W2007069074","https://openalex.org/W2010890196","https://openalex.org/W2022858489","https://openalex.org/W2040063291","https://openalex.org/W2045938805","https://openalex.org/W2058858139","https://openalex.org/W2066588467","https://openalex.org/W2080234606","https://openalex.org/W2080745194","https://openalex.org/W2090403603","https://openalex.org/W2113380734","https://openalex.org/W2144982963","https://openalex.org/W2148706674","https://openalex.org/W2153406069","https://openalex.org/W2171013708","https://openalex.org/W2219888463","https://openalex.org/W2243803726","https://openalex.org/W2396309311","https://openalex.org/W2439904216","https://openalex.org/W2479510968","https://openalex.org/W2755385361","https://openalex.org/W2788186722","https://openalex.org/W2798945787","https://openalex.org/W2834288129","https://openalex.org/W2950833175","https://openalex.org/W2963898466","https://openalex.org/W2967106834","https://openalex.org/W3031692719","https://openalex.org/W3048085834","https://openalex.org/W3102387041","https://openalex.org/W3169567991","https://openalex.org/W3173382529","https://openalex.org/W3176348316","https://openalex.org/W3177067869","https://openalex.org/W3177390287","https://openalex.org/W3208389451","https://openalex.org/W3212706643","https://openalex.org/W4212994361","https://openalex.org/W4229653087","https://openalex.org/W4236226996","https://openalex.org/W4283323602"],"related_works":["https://openalex.org/W4312683641","https://openalex.org/W4206798987","https://openalex.org/W3215994059","https://openalex.org/W3027421045","https://openalex.org/W3013312691","https://openalex.org/W2980386803","https://openalex.org/W2576320324","https://openalex.org/W2389818373","https://openalex.org/W2319823519","https://openalex.org/W2220831889"],"abstract_inverted_index":{"Inner-product":[0],"estimation":[1],"is":[2,44,107,142],"the":[3,62,115,128],"base":[4],"of":[5,12,19,41,61,65,90],"many":[6],"important":[7],"tasks":[8],"in":[9,21,28,34,46,99,133],"a":[10,39,73,137],"variety":[11],"big":[13],"data":[14,22],"scenarios,":[15],"including":[16],"measuring":[17],"similarity":[18,33],"streams":[20],"stream":[23],"processing,":[24],"estimating":[25],"join":[26],"size":[27],"database,":[29],"and":[30,79,93,109,118],"analyzing":[31],"cosine":[32],"various":[35],"applications.":[36],"Sketch,":[37],"as":[38],"class":[40],"probability":[42],"algorithms,":[43],"promising":[45],"inner-product":[47,81],"estimation.":[48],"However,":[49],"existing":[50],"sketch":[51,75],"solutions":[52],"suffer":[53],"from":[54],"low":[55],"accuracy":[56,129],"due":[57],"to":[58],"their":[59],"neglect":[60],"high":[63],"skewness":[64],"real":[66],"data.":[67],"In":[68],"this":[69],"paper,":[70],"we":[71],"design":[72],"new":[74],"algorithm":[76],"for":[77],"accurate":[78],"unbiased":[80],"estimation,":[82],"namely":[83],"JoinSketch.":[84],"To":[85],"improve":[86],"accuracy,":[87],"JoinSketch":[88,106,126],"consists":[89],"multiple":[91],"components,":[92],"records":[94],"items":[95],"with":[96,114],"different":[97,100],"frequency":[98],"components.":[101],"We":[102],"theoretically":[103],"prove":[104],"that":[105,125],"unbiased,":[108],"has":[110],"lower":[111],"variance":[112],"compared":[113],"well-known":[116],"AGMS":[117],"Fast-AGMS":[119],"sketch.":[120],"The":[121],"experimental":[122],"results":[123],"show":[124],"improves":[127],"by":[130],"10":[131],"times":[132],"average":[134],"while":[135],"maintaining":[136],"comparable":[138],"speed.":[139],"All":[140],"code":[141],"open-sourced":[143],"at":[144],"Github.":[145]},"cited_by_api_url":"https://api.openalex.org/works?filter=cites:W4380433195","counts_by_year":[{"year":2024,"cited_by_count":8}],"updated_date":"2025-01-03T05:33:06.582270","created_date":"2023-06-14"}