{"id":"https://openalex.org/W3185630596","doi":"https://doi.org/10.1145/3465238","title":"A Synopsis Based Approach for Itemset Frequency Estimation over Massive Multi-Transaction Stream","display_name":"A Synopsis Based Approach for Itemset Frequency Estimation over Massive Multi-Transaction Stream","publication_year":2021,"publication_date":"2021-07-21","ids":{"openalex":"https://openalex.org/W3185630596","doi":"https://doi.org/10.1145/3465238","mag":"3185630596"},"language":"en","primary_location":{"id":"doi:10.1145/3465238","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3465238","pdf_url":null,"source":{"id":"https://openalex.org/S41523882","display_name":"ACM Transactions on Knowledge Discovery from Data","issn_l":"1556-4681","issn":["1556-4681","1556-472X"],"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":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ACM Transactions on Knowledge Discovery from Data","raw_type":"journal-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"http://hdl.handle.net/10453/152013","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5102889910","display_name":"Guangtao Wang","orcid":"https://orcid.org/0000-0003-2766-0917"},"institutions":[{"id":"https://openalex.org/I27837315","display_name":"University of Michigan","ror":"https://ror.org/00jmfr291","country_code":"US","type":"education","lineage":["https://openalex.org/I27837315"]},{"id":"https://openalex.org/I72427458","display_name":"JDSU (United States)","ror":"https://ror.org/01a5v8x09","country_code":"US","type":"company","lineage":["https://openalex.org/I72427458"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Guangtao Wang","raw_affiliation_strings":["University of Michigan and JD AI Research"],"raw_orcid":"https://orcid.org/0000-0003-2766-0917","affiliations":[{"raw_affiliation_string":"University of Michigan and JD AI Research","institution_ids":["https://openalex.org/I72427458","https://openalex.org/I27837315"]}]},{"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"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Nanyang Technological University, Singapore","institution_ids":["https://openalex.org/I172675005"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100386104","display_name":"Ying Zhang","orcid":"https://orcid.org/0000-0002-2674-1638"},"institutions":[{"id":"https://openalex.org/I114017466","display_name":"University of Technology Sydney","ror":"https://ror.org/03f0f6041","country_code":"AU","type":"education","lineage":["https://openalex.org/I114017466"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Ying Zhang","raw_affiliation_strings":["University of Technology, Ultimo, NSW, Australia"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Technology, Ultimo, NSW, Australia","institution_ids":["https://openalex.org/I114017466"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102868540","display_name":"Zhen Hai","orcid":"https://orcid.org/0000-0002-4593-5286"},"institutions":[{"id":"https://openalex.org/I115228651","display_name":"Agency for Science, Technology and Research","ror":"https://ror.org/036wvzt09","country_code":"SG","type":"government","lineage":["https://openalex.org/I115228651"]},{"id":"https://openalex.org/I3005327000","display_name":"Institute for Infocomm Research","ror":"https://ror.org/053rfa017","country_code":"SG","type":"facility","lineage":["https://openalex.org/I115228651","https://openalex.org/I3005327000","https://openalex.org/I91275662"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Zhen Hai","raw_affiliation_strings":["Institute for Infocomm Research, A*STAR, Singapore"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Institute for Infocomm Research, A*STAR, Singapore","institution_ids":["https://openalex.org/I3005327000","https://openalex.org/I115228651"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5010419481","display_name":"Jieping Ye","orcid":"https://orcid.org/0000-0001-8662-5818"},"institutions":[{"id":"https://openalex.org/I27837315","display_name":"University of Michigan","ror":"https://ror.org/00jmfr291","country_code":"US","type":"education","lineage":["https://openalex.org/I27837315"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Jieping Ye","raw_affiliation_strings":["University of Michigan, MI"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Michigan, MI","institution_ids":["https://openalex.org/I27837315"]}]}],"institutions":[],"countries_distinct_count":3,"institutions_distinct_count":6,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.2822,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":{"value":0.62469726,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":97},"biblio":{"volume":"16","issue":"2","first_page":"1","last_page":"30"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10538","display_name":"Data Mining Algorithms and Applications","score":0.9998999834060669,"subfield":{"id":"https://openalex.org/subfields/1710","display_name":"Information Systems"},"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/T10538","display_name":"Data Mining Algorithms and Applications","score":0.9998999834060669,"subfield":{"id":"https://openalex.org/subfields/1710","display_name":"Information Systems"},"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/T12761","display_name":"Data Stream Mining Techniques","score":0.9990000128746033,"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/T11652","display_name":"Imbalanced Data Classification Techniques","score":0.9947999715805054,"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/estimator","display_name":"Estimator","score":0.8315356969833374},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8098645210266113},{"id":"https://openalex.org/keywords/database-transaction","display_name":"Database transaction","score":0.670474648475647},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.5997019410133362},{"id":"https://openalex.org/keywords/sampling","display_name":"Sampling (signal processing)","score":0.5336931943893433},{"id":"https://openalex.org/keywords/data-stream-mining","display_name":"Data stream mining","score":0.46294960379600525},{"id":"https://openalex.org/keywords/transaction-data","display_name":"Transaction data","score":0.43527528643608093},{"id":"https://openalex.org/keywords/data-stream","display_name":"Data stream","score":0.4124908745288849},{"id":"https://openalex.org/keywords/statistics","display_name":"Statistics","score":0.15449678897857666},{"id":"https://openalex.org/keywords/database","display_name":"Database","score":0.14677822589874268},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.12105095386505127},{"id":"https://openalex.org/keywords/telecommunications","display_name":"Telecommunications","score":0.0622979998588562}],"concepts":[{"id":"https://openalex.org/C185429906","wikidata":"https://www.wikidata.org/wiki/Q1130160","display_name":"Estimator","level":2,"score":0.8315356969833374},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8098645210266113},{"id":"https://openalex.org/C75949130","wikidata":"https://www.wikidata.org/wiki/Q848010","display_name":"Database transaction","level":2,"score":0.670474648475647},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.5997019410133362},{"id":"https://openalex.org/C140779682","wikidata":"https://www.wikidata.org/wiki/Q210868","display_name":"Sampling (signal processing)","level":3,"score":0.5336931943893433},{"id":"https://openalex.org/C89198739","wikidata":"https://www.wikidata.org/wiki/Q3079880","display_name":"Data stream mining","level":2,"score":0.46294960379600525},{"id":"https://openalex.org/C127722929","wikidata":"https://www.wikidata.org/wiki/Q7833714","display_name":"Transaction data","level":3,"score":0.43527528643608093},{"id":"https://openalex.org/C2778484313","wikidata":"https://www.wikidata.org/wiki/Q1172540","display_name":"Data stream","level":2,"score":0.4124908745288849},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.15449678897857666},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.14677822589874268},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.12105095386505127},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.0622979998588562},{"id":"https://openalex.org/C94915269","wikidata":"https://www.wikidata.org/wiki/Q1834857","display_name":"Detector","level":2,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1145/3465238","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3465238","pdf_url":null,"source":{"id":"https://openalex.org/S41523882","display_name":"ACM Transactions on Knowledge Discovery from Data","issn_l":"1556-4681","issn":["1556-4681","1556-472X"],"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":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ACM Transactions on Knowledge Discovery from Data","raw_type":"journal-article"},{"id":"pmh:oai:opus.lib.uts.edu.au:10453/152013","is_oa":true,"landing_page_url":"http://hdl.handle.net/10453/152013","pdf_url":null,"source":{"id":"https://openalex.org/S4306401357","display_name":"UTS ePRESS (University of Technology Sydney)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I114017466","host_organization_name":"University of Technology Sydney","host_organization_lineage":["https://openalex.org/I114017466"],"host_organization_lineage_names":[],"type":"repository"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"Journal Article"}],"best_oa_location":{"id":"pmh:oai:opus.lib.uts.edu.au:10453/152013","is_oa":true,"landing_page_url":"http://hdl.handle.net/10453/152013","pdf_url":null,"source":{"id":"https://openalex.org/S4306401357","display_name":"UTS ePRESS (University of Technology Sydney)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I114017466","host_organization_name":"University of Technology Sydney","host_organization_lineage":["https://openalex.org/I114017466"],"host_organization_lineage_names":[],"type":"repository"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"Journal Article"},"sustainable_development_goals":[{"score":0.4300000071525574,"id":"https://metadata.un.org/sdg/8","display_name":"Decent work and economic growth"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":51,"referenced_works":["https://openalex.org/W1493892051","https://openalex.org/W1553409264","https://openalex.org/W1972525637","https://openalex.org/W1979819093","https://openalex.org/W1980242380","https://openalex.org/W1983811663","https://openalex.org/W1992363839","https://openalex.org/W2006683254","https://openalex.org/W2012301399","https://openalex.org/W2014832886","https://openalex.org/W2017062116","https://openalex.org/W2028944004","https://openalex.org/W2045487373","https://openalex.org/W2045646326","https://openalex.org/W2048117100","https://openalex.org/W2058935772","https://openalex.org/W2064379477","https://openalex.org/W2078825395","https://openalex.org/W2079136461","https://openalex.org/W2079978553","https://openalex.org/W2080234606","https://openalex.org/W2091835598","https://openalex.org/W2102476072","https://openalex.org/W2103175056","https://openalex.org/W2110893883","https://openalex.org/W2111091497","https://openalex.org/W2113139394","https://openalex.org/W2114469075","https://openalex.org/W2129501055","https://openalex.org/W2139786672","https://openalex.org/W2140914274","https://openalex.org/W2152637787","https://openalex.org/W2159393864","https://openalex.org/W2167973519","https://openalex.org/W2413139494","https://openalex.org/W2478620367","https://openalex.org/W2480979371","https://openalex.org/W2492078868","https://openalex.org/W2497664069","https://openalex.org/W2603439383","https://openalex.org/W2606279103","https://openalex.org/W2724859488","https://openalex.org/W2755216013","https://openalex.org/W2783141051","https://openalex.org/W2921404976","https://openalex.org/W2951487503","https://openalex.org/W2971194171","https://openalex.org/W2991104566","https://openalex.org/W3046185161","https://openalex.org/W3157916638","https://openalex.org/W4252403066"],"related_works":["https://openalex.org/W4389449520","https://openalex.org/W127192698","https://openalex.org/W2989589039","https://openalex.org/W2570600173","https://openalex.org/W2893008024","https://openalex.org/W2743735673","https://openalex.org/W3007554386","https://openalex.org/W4361801939","https://openalex.org/W2360131081","https://openalex.org/W2985941356"],"abstract_inverted_index":{"The":[0],"streams":[1,31,190],"where":[2],"multiple":[3,19],"transactions":[4],"are":[5,11],"associated":[6],"with":[7,132,179],"the":[8,41,65,75,82,92,98,103,120,126,175,198,209],"same":[9],"key":[10],"prevalent":[12],"in":[13],"practice,":[14],"e.g.,":[15],"a":[16,54,87,153,180],"customer":[17],"has":[18],"shopping":[20],"records":[21],"arriving":[22],"at":[23],"different":[24],"time.":[25],"Itemset":[26],"frequency":[27,66,93,204],"estimation":[28],"on":[29,188,197],"such":[30,39],"is":[32,108,171],"very":[33],"challenging":[34],"since":[35],"sampling":[36],"based":[37,61,156],"methods,":[38],"as":[40],"popularly":[42],"used":[43],"reservoir":[44],"sampling,":[45],"cannot":[46],"be":[47],"used.":[48],"In":[49],"this":[50],"article,":[51],"we":[52,73,85,151,168],"propose":[53,86],"novel":[55,88],"k":[56],"-Minimum":[57],"Value":[58],"(KMV)":[59],"synopsis":[60,155],"method":[62,107],"to":[63,90,102,115,141,208],"estimate":[64,91],"of":[67,94,128,173,177,183],"itemsets":[68,144],"over":[69,97,145],"multi-transaction":[70,146],"streams.":[71,147],"First,":[72],"extract":[74],"KMV":[76,99,154,184],"synopses":[77],"for":[78,200],"each":[79],"item":[80],"from":[81],"stream.":[83],"Then,":[84],"estimator":[89,131,162,193],"an":[95],"itemset":[96,135,203],"synopses.":[100],"Comparing":[101],"existing":[104,133,164,210],"estimator,":[105],"our":[106,129,161,192],"not":[109],"only":[110],"more":[111],"accurate":[112],"and":[113,167,205],"efficient":[114],"calculate":[116],"but":[117],"also":[118],"follows":[119],"downward-closure":[121],"property.":[122],"These":[123],"properties":[124],"enable":[125],"incorporation":[127],"new":[130],"frequent":[134,143],"mining":[136],"(FIM)":[137],"algorithm":[138,158],"(e.g.,":[139],"FP-Growth)":[140],"mine":[142],"To":[148],"demonstrate":[149],"this,":[150],"implement":[152],"FIM":[157,165,178,206],"by":[159],"integrating":[160],"into":[163],"algorithms,":[166],"prove":[169],"it":[170],"capable":[172],"guaranteeing":[174],"accuracy":[176,199],"bounded":[181],"size":[182],"synopsis.":[185],"Experimental":[186],"results":[187],"massive":[189],"show":[191],"can":[194],"significantly":[195],"improve":[196],"both":[201],"estimating":[202],"compared":[207],"estimators.":[211]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2023,"cited_by_count":1}],"updated_date":"2026-07-15T18:14:33.161393","created_date":"2025-10-10T00:00:00"}