{"id":"https://openalex.org/W1525397625","doi":"https://doi.org/10.1109/tkde.2015.2480400","title":"Similarity Group-by Operators for Multi-Dimensional Relational Data","display_name":"Similarity Group-by Operators for Multi-Dimensional Relational Data","publication_year":2015,"publication_date":"2015-10-05","ids":{"openalex":"https://openalex.org/W1525397625","doi":"https://doi.org/10.1109/tkde.2015.2480400","mag":"1525397625"},"language":"en","primary_location":{"id":"doi:10.1109/tkde.2015.2480400","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tkde.2015.2480400","pdf_url":null,"source":{"id":"https://openalex.org/S30698027","display_name":"IEEE Transactions on Knowledge and Data Engineering","issn_l":"1041-4347","issn":["1041-4347","1558-2191","2326-3865"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320439","host_organization_name":"IEEE Computer Society","host_organization_lineage":["https://openalex.org/P4310320439","https://openalex.org/P4310319808"],"host_organization_lineage_names":["IEEE Computer Society","Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Knowledge and Data Engineering","raw_type":"journal-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/A5101512458","display_name":"Mingjie Tang","orcid":"https://orcid.org/0000-0002-8893-4574"},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Mingjie Tang","raw_affiliation_strings":["Department of Computer Science, Purdue University, Indiana, IN"],"affiliations":[{"raw_affiliation_string":"Department of Computer Science, Purdue University, Indiana, IN","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5054261003","display_name":"Ruby Y. Tahboub","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Ruby Y. Tahboub","raw_affiliation_strings":["Department of Computer Science, Purdue University, Indiana, IN"],"affiliations":[{"raw_affiliation_string":"Department of Computer Science, Purdue University, Indiana, IN","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5000123743","display_name":"Walid G. Aref","orcid":"https://orcid.org/0000-0001-8169-7775"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Walid G. Aref","raw_affiliation_strings":["Center for Education and Research in Information Assurance and Security (CERIAS), West Lafayette, IN, USA","Department of Computer Science, Purdue University, Indiana, IN"],"affiliations":[{"raw_affiliation_string":"Center for Education and Research in Information Assurance and Security (CERIAS), West Lafayette, IN, USA","institution_ids":[]},{"raw_affiliation_string":"Department of Computer Science, Purdue University, Indiana, IN","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5113562454","display_name":"Mikhail J. Atallah","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Mikhail J. Atallah","raw_affiliation_strings":["Department of Computer Science, Purdue University, Indiana, IN"],"affiliations":[{"raw_affiliation_string":"Department of Computer Science, Purdue University, Indiana, IN","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5028226990","display_name":"Qutaibah Malluhi","orcid":"https://orcid.org/0000-0003-2849-0569"},"institutions":[{"id":"https://openalex.org/I60342839","display_name":"Qatar University","ror":"https://ror.org/00yhnba62","country_code":"QA","type":"education","lineage":["https://openalex.org/I60342839"]}],"countries":["QA"],"is_corresponding":false,"raw_author_name":"Qutaibah M. Malluhi","raw_affiliation_strings":["KINDI Center for Computing Research, Qatar University, Doha-Qatar"],"affiliations":[{"raw_affiliation_string":"KINDI Center for Computing Research, Qatar University, Doha-Qatar","institution_ids":["https://openalex.org/I60342839"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5026923999","display_name":"Mourad Ouzzani","orcid":"https://orcid.org/0000-0002-4035-3025"},"institutions":[{"id":"https://openalex.org/I1301390666","display_name":"Qatar Airways (Qatar)","ror":"https://ror.org/01hx00y13","country_code":"QA","type":"company","lineage":["https://openalex.org/I1301390666"]}],"countries":["QA"],"is_corresponding":false,"raw_author_name":"Mourad Ouzzani","raw_affiliation_strings":["Qatar Computing Research Institute, Doha-Qatar"],"affiliations":[{"raw_affiliation_string":"Qatar Computing Research Institute, Doha-Qatar","institution_ids":["https://openalex.org/I1301390666"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5088912009","display_name":"Yasin N. Silva","orcid":"https://orcid.org/0000-0003-1852-1683"},"institutions":[{"id":"https://openalex.org/I55732556","display_name":"Arizona State University","ror":"https://ror.org/03efmqc40","country_code":"US","type":"education","lineage":["https://openalex.org/I55732556"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Yasin N. Silva","raw_affiliation_strings":["School of Mathematical and Natural Science, Arizona State University, Tempe, AZ"],"affiliations":[{"raw_affiliation_string":"School of Mathematical and Natural Science, Arizona State University, Tempe, AZ","institution_ids":["https://openalex.org/I55732556"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":7,"corresponding_author_ids":["https://openalex.org/A5101512458"],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":3.4463,"has_fulltext":false,"cited_by_count":27,"citation_normalized_percentile":{"value":0.9298041,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":98},"biblio":{"volume":"28","issue":"2","first_page":"510","last_page":"523"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11106","display_name":"Data Management and Algorithms","score":0.9995999932289124,"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":0.9995999932289124,"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/T10637","display_name":"Advanced Clustering Algorithms Research","score":0.9958999752998352,"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/T10538","display_name":"Data Mining Algorithms and Applications","score":0.9925000071525574,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/tuple","display_name":"Tuple","score":0.8926222324371338},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6391544938087463},{"id":"https://openalex.org/keywords/sql","display_name":"SQL","score":0.6105709075927734},{"id":"https://openalex.org/keywords/similarity","display_name":"Similarity (geometry)","score":0.5986305475234985},{"id":"https://openalex.org/keywords/operator","display_name":"Operator (biology)","score":0.5481000542640686},{"id":"https://openalex.org/keywords/group","display_name":"Group (periodic table)","score":0.5338479280471802},{"id":"https://openalex.org/keywords/semantics","display_name":"Semantics (computer science)","score":0.5007743835449219},{"id":"https://openalex.org/keywords/theoretical-computer-science","display_name":"Theoretical computer science","score":0.41709086298942566},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.35226380825042725},{"id":"https://openalex.org/keywords/database","display_name":"Database","score":0.25853416323661804},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.2509284019470215},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.1592872440814972},{"id":"https://openalex.org/keywords/discrete-mathematics","display_name":"Discrete mathematics","score":0.11939197778701782},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.07979738712310791}],"concepts":[{"id":"https://openalex.org/C118930307","wikidata":"https://www.wikidata.org/wiki/Q600590","display_name":"Tuple","level":2,"score":0.8926222324371338},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6391544938087463},{"id":"https://openalex.org/C510870499","wikidata":"https://www.wikidata.org/wiki/Q47607","display_name":"SQL","level":2,"score":0.6105709075927734},{"id":"https://openalex.org/C103278499","wikidata":"https://www.wikidata.org/wiki/Q254465","display_name":"Similarity (geometry)","level":3,"score":0.5986305475234985},{"id":"https://openalex.org/C17020691","wikidata":"https://www.wikidata.org/wiki/Q139677","display_name":"Operator (biology)","level":5,"score":0.5481000542640686},{"id":"https://openalex.org/C2781311116","wikidata":"https://www.wikidata.org/wiki/Q83306","display_name":"Group (periodic table)","level":2,"score":0.5338479280471802},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.5007743835449219},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.41709086298942566},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.35226380825042725},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.25853416323661804},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.2509284019470215},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.1592872440814972},{"id":"https://openalex.org/C118615104","wikidata":"https://www.wikidata.org/wiki/Q121416","display_name":"Discrete mathematics","level":1,"score":0.11939197778701782},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.07979738712310791},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.0},{"id":"https://openalex.org/C158448853","wikidata":"https://www.wikidata.org/wiki/Q425218","display_name":"Repressor","level":4,"score":0.0},{"id":"https://openalex.org/C178790620","wikidata":"https://www.wikidata.org/wiki/Q11351","display_name":"Organic chemistry","level":1,"score":0.0},{"id":"https://openalex.org/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"score":0.0},{"id":"https://openalex.org/C55493867","wikidata":"https://www.wikidata.org/wiki/Q7094","display_name":"Biochemistry","level":1,"score":0.0},{"id":"https://openalex.org/C86339819","wikidata":"https://www.wikidata.org/wiki/Q407384","display_name":"Transcription factor","level":3,"score":0.0},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/tkde.2015.2480400","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tkde.2015.2480400","pdf_url":null,"source":{"id":"https://openalex.org/S30698027","display_name":"IEEE Transactions on Knowledge and Data Engineering","issn_l":"1041-4347","issn":["1041-4347","1558-2191","2326-3865"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320439","host_organization_name":"IEEE Computer Society","host_organization_lineage":["https://openalex.org/P4310320439","https://openalex.org/P4310319808"],"host_organization_lineage_names":["IEEE Computer Society","Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Knowledge and Data Engineering","raw_type":"journal-article"},{"id":"pmh:oai:qspace.qu.edu.qa:10576/18429","is_oa":false,"landing_page_url":"http://hdl.handle.net/10576/18429","pdf_url":null,"source":{"id":"https://openalex.org/S4306400014","display_name":"Qatar University QSpace (Qatar University)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I60342839","host_organization_name":"Qatar University","host_organization_lineage":["https://openalex.org/I60342839"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Conference"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G7047449081","display_name":null,"funder_award_id":"CCF-0939370","funder_id":"https://openalex.org/F4320320952","funder_display_name":"International Science and Technology Center"},{"id":"https://openalex.org/G7525947664","display_name":null,"funder_award_id":"IIS-1117766","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G8575824204","display_name":null,"funder_award_id":"CPS-1329979","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"},{"id":"https://openalex.org/F4320320952","display_name":"International Science and Technology Center","ror":"https://ror.org/03fn1w943"},{"id":"https://openalex.org/F4320332753","display_name":"Qatar National Research Fund","ror":"https://ror.org/01svaqq28"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":33,"referenced_works":["https://openalex.org/W71682066","https://openalex.org/W259338706","https://openalex.org/W299839057","https://openalex.org/W1501500081","https://openalex.org/W1525397625","https://openalex.org/W1673310716","https://openalex.org/W1973293833","https://openalex.org/W1979720745","https://openalex.org/W1986842437","https://openalex.org/W2004420255","https://openalex.org/W2026815233","https://openalex.org/W2044146725","https://openalex.org/W2085843229","https://openalex.org/W2094951520","https://openalex.org/W2095897464","https://openalex.org/W2098028660","https://openalex.org/W2110953678","https://openalex.org/W2115057574","https://openalex.org/W2118269922","https://openalex.org/W2119441285","https://openalex.org/W2131687179","https://openalex.org/W2132151704","https://openalex.org/W2140190241","https://openalex.org/W2157092487","https://openalex.org/W2161160262","https://openalex.org/W2166612479","https://openalex.org/W2296677182","https://openalex.org/W2950646721","https://openalex.org/W4231029117","https://openalex.org/W4251391716","https://openalex.org/W6637131181","https://openalex.org/W6679747670","https://openalex.org/W6682969285"],"related_works":["https://openalex.org/W2143345456","https://openalex.org/W2143551613","https://openalex.org/W4245395944","https://openalex.org/W1979740464","https://openalex.org/W2138823233","https://openalex.org/W2023236823","https://openalex.org/W1789991335","https://openalex.org/W2562731034","https://openalex.org/W2101053337","https://openalex.org/W3030674916"],"abstract_inverted_index":{"The":[0,52,134,157,241,263],"SQL":[1,66],"group-by":[2,22],"operator":[3,56,136,159],"plays":[4],"an":[5],"important":[6],"role":[7],"in":[8,14,31,104,113,147,182,215,288],"summarizing":[9],"and":[10,94,110,219,230,236,251,269],"aggregating":[11],"large":[12],"datasets":[13],"a":[15,39,148,165,169,186,205,222,270],"data":[16,45,70],"analytics":[17],"stack.":[18],"While":[19,78],"the":[20,61,64,114,138,145,161,172,183,190,209,213,232,252,260,276,296],"standard":[21,65,261],"operator,":[23],"which":[24],"is":[25,29,137,160,174],"based":[26,266],"on":[27,43,91,267],"equality,":[28],"useful":[30],"several":[32],"applications,":[33],"allowing":[34],"similarity":[35],"aware":[36],"grouping":[37,69,81],"provides":[38],"more":[40],"realistic":[41],"view":[42],"real-world":[44],"that":[46,275],"could":[47],"lead":[48],"to":[49,168,201,248,257,282,294],"better":[50],"insights.":[51],"Similarity":[53],"SQL-based":[54],"Group-By":[55],"(SGB,":[57],"for":[58,131,225],"short)":[59],"extends":[60],"semantics":[62,200],"of":[63,193,259,285],"Group-by":[67],"by":[68,244],"with":[71,203],"similar":[72],"but":[73],"not":[74,118],"necessarily":[75],"equal":[76],"values.":[77],"existing":[79],"similarity-based":[80],"operators":[82,130,235,246],"efficiently":[83],"realize":[84],"these":[85,245],"approximate":[86],"semantics,":[87],"they":[88],"primarily":[89],"focus":[90],"one-dimensional":[92],"attributes":[93,97],"treat":[95],"multi-dimensional":[96,115,132],"independently.":[98],"However,":[99],"correlated":[100],"attributes,":[101],"such":[102,204],"as":[103],"spatial":[105],"data,":[106,273],"are":[107,117,150,255],"processed":[108],"independently,":[109],"hence,":[111],"groups":[112],"space":[116],"detected":[119],"properly.":[120],"To":[121],"address":[122],"this":[123,226],"problem,":[124],"we":[125,196],"introduce":[126,197],"two":[127],"new":[128,223,233],"SGB":[129,234],"data.":[133],"first":[135],"clique":[139],"(or":[140],"distance-to-all)":[141],"SGB,":[142,163],"where":[143,164],"all":[144],"tuples":[146],"group":[149,170,224],"within":[151,175],"some":[152,176],"distance":[153,177],"from":[154,178],"each":[155],"other.":[156],"second":[158],"distance-to-any":[162],"tuple":[166,173,181,187,214],"belongs":[167],"if":[171],"any":[179,216],"other":[180],"group.":[184],"Since":[185],"may":[188],"satisfy":[189],"membership":[191],"criterion":[192],"multiple":[194],"groups,":[195],"three":[198,283],"different":[199],"deal":[202],"case:":[206],"(i)":[207],"eliminate":[208],"tuple,":[210],"(ii)":[211],"put":[212],"one":[217],"group,":[218],"(iii)":[220],"create":[221],"tuple.":[227],"We":[228],"implement":[229],"test":[231],"their":[237],"algorithms":[238,278],"inside":[239],"PostgreSQL.":[240],"overhead":[242],"introduced":[243],"proves":[247],"be":[249],"minimal":[250],"execution":[253],"times":[254],"comparable":[256],"those":[258],"Group-by.":[262],"experimental":[264],"study,":[265],"TPC-H":[268],"social":[271],"check-in":[272],"demonstrates":[274],"proposed":[277],"can":[279],"achieve":[280],"up":[281],"orders":[284],"magnitude":[286],"enhancement":[287],"performance":[289],"over":[290],"baseline":[291],"methods":[292],"developed":[293],"solve":[295],"same":[297],"problem.":[298]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":3},{"year":2023,"cited_by_count":1},{"year":2021,"cited_by_count":3},{"year":2020,"cited_by_count":4},{"year":2019,"cited_by_count":3},{"year":2018,"cited_by_count":4},{"year":2017,"cited_by_count":3},{"year":2016,"cited_by_count":2},{"year":2015,"cited_by_count":2},{"year":2014,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}
