{"id":"https://openalex.org/W2801426799","doi":"https://doi.org/10.1109/tkde.2018.2831214","title":"Similarity Metrics for SQL Query Clustering","display_name":"Similarity Metrics for SQL Query Clustering","publication_year":2018,"publication_date":"2018-04-30","ids":{"openalex":"https://openalex.org/W2801426799","doi":"https://doi.org/10.1109/tkde.2018.2831214","mag":"2801426799"},"language":"en","primary_location":{"id":"doi:10.1109/tkde.2018.2831214","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tkde.2018.2831214","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/A5039228531","display_name":"G\u00f6khan Kul","orcid":"https://orcid.org/0000-0001-6467-1979"},"institutions":[{"id":"https://openalex.org/I63190737","display_name":"University at Buffalo, State University of New York","ror":"https://ror.org/01y64my43","country_code":"US","type":"education","lineage":["https://openalex.org/I63190737"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Gokhan Kul","raw_affiliation_strings":["Department of Computer Science and Engineering, University at Buffalo, Buffalo, NY"],"affiliations":[{"raw_affiliation_string":"Department of Computer Science and Engineering, University at Buffalo, Buffalo, NY","institution_ids":["https://openalex.org/I63190737"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5034235300","display_name":"Duc Thanh Anh Luong","orcid":"https://orcid.org/0000-0003-4768-5089"},"institutions":[{"id":"https://openalex.org/I63190737","display_name":"University at Buffalo, State University of New York","ror":"https://ror.org/01y64my43","country_code":"US","type":"education","lineage":["https://openalex.org/I63190737"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Duc Thanh Anh Luong","raw_affiliation_strings":["Department of Computer Science and Engineering, University at Buffalo, Buffalo, NY"],"affiliations":[{"raw_affiliation_string":"Department of Computer Science and Engineering, University at Buffalo, Buffalo, NY","institution_ids":["https://openalex.org/I63190737"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101496580","display_name":"Ting Xie","orcid":"https://orcid.org/0000-0003-0297-8320"},"institutions":[{"id":"https://openalex.org/I63190737","display_name":"University at Buffalo, State University of New York","ror":"https://ror.org/01y64my43","country_code":"US","type":"education","lineage":["https://openalex.org/I63190737"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Ting Xie","raw_affiliation_strings":["Department of Computer Science and Engineering, University at Buffalo, Buffalo, NY"],"affiliations":[{"raw_affiliation_string":"Department of Computer Science and Engineering, University at Buffalo, Buffalo, NY","institution_ids":["https://openalex.org/I63190737"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5003851078","display_name":"Varun Chandola","orcid":"https://orcid.org/0000-0001-8990-1398"},"institutions":[{"id":"https://openalex.org/I63190737","display_name":"University at Buffalo, State University of New York","ror":"https://ror.org/01y64my43","country_code":"US","type":"education","lineage":["https://openalex.org/I63190737"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Varun Chandola","raw_affiliation_strings":["Department of Computer Science and Engineering, University at Buffalo, Buffalo, NY"],"affiliations":[{"raw_affiliation_string":"Department of Computer Science and Engineering, University at Buffalo, Buffalo, NY","institution_ids":["https://openalex.org/I63190737"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5071259962","display_name":"Oliver Kennedy","orcid":"https://orcid.org/0000-0003-0632-1668"},"institutions":[{"id":"https://openalex.org/I63190737","display_name":"University at Buffalo, State University of New York","ror":"https://ror.org/01y64my43","country_code":"US","type":"education","lineage":["https://openalex.org/I63190737"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Oliver Kennedy","raw_affiliation_strings":["Department of Computer Science and Engineering, University at Buffalo, Buffalo, NY"],"affiliations":[{"raw_affiliation_string":"Department of Computer Science and Engineering, University at Buffalo, Buffalo, NY","institution_ids":["https://openalex.org/I63190737"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5031947971","display_name":"Shambhu Upadhyaya","orcid":"https://orcid.org/0000-0002-0596-1703"},"institutions":[{"id":"https://openalex.org/I63190737","display_name":"University at Buffalo, State University of New York","ror":"https://ror.org/01y64my43","country_code":"US","type":"education","lineage":["https://openalex.org/I63190737"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Shambhu Upadhyaya","raw_affiliation_strings":["Department of Computer Science and Engineering, University at Buffalo, Buffalo, NY"],"affiliations":[{"raw_affiliation_string":"Department of Computer Science and Engineering, University at Buffalo, Buffalo, NY","institution_ids":["https://openalex.org/I63190737"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":6,"corresponding_author_ids":["https://openalex.org/A5039228531"],"corresponding_institution_ids":["https://openalex.org/I63190737"],"apc_list":null,"apc_paid":null,"fwci":4.6461,"has_fulltext":false,"cited_by_count":55,"citation_normalized_percentile":{"value":0.95699276,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":97,"max":99},"biblio":{"volume":"30","issue":"12","first_page":"2408","last_page":"2420"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11106","display_name":"Data Management and Algorithms","score":0.9997000098228455,"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":0.9997000098228455,"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/T10317","display_name":"Advanced Database Systems and Queries","score":0.9995999932289124,"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/T10538","display_name":"Data Mining Algorithms and Applications","score":0.9990000128746033,"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/computer-science","display_name":"Computer science","score":0.8521291017532349},{"id":"https://openalex.org/keywords/query-by-example","display_name":"Query by Example","score":0.6785718202590942},{"id":"https://openalex.org/keywords/query-optimization","display_name":"Query optimization","score":0.6658626198768616},{"id":"https://openalex.org/keywords/spatial-query","display_name":"Spatial query","score":0.5898723602294922},{"id":"https://openalex.org/keywords/query-expansion","display_name":"Query expansion","score":0.5778234004974365},{"id":"https://openalex.org/keywords/query-language","display_name":"Query language","score":0.5480402708053589},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.546812117099762},{"id":"https://openalex.org/keywords/view","display_name":"View","score":0.5327819585800171},{"id":"https://openalex.org/keywords/sargable","display_name":"Sargable","score":0.516997218132019},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.503086507320404},{"id":"https://openalex.org/keywords/web-query-classification","display_name":"Web query classification","score":0.4831359088420868},{"id":"https://openalex.org/keywords/cluster-analysis","display_name":"Cluster analysis","score":0.47478052973747253},{"id":"https://openalex.org/keywords/sql","display_name":"SQL","score":0.41971555352211},{"id":"https://openalex.org/keywords/heuristics","display_name":"Heuristics","score":0.4147895872592926},{"id":"https://openalex.org/keywords/database","display_name":"Database","score":0.39981669187545776},{"id":"https://openalex.org/keywords/web-search-query","display_name":"Web search query","score":0.3563038408756256},{"id":"https://openalex.org/keywords/database-design","display_name":"Database design","score":0.2625710368156433},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.13421818614006042},{"id":"https://openalex.org/keywords/search-engine","display_name":"Search engine","score":0.1206827163696289}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8521291017532349},{"id":"https://openalex.org/C194222762","wikidata":"https://www.wikidata.org/wiki/Q114486","display_name":"Query by Example","level":4,"score":0.6785718202590942},{"id":"https://openalex.org/C157692150","wikidata":"https://www.wikidata.org/wiki/Q2919848","display_name":"Query optimization","level":2,"score":0.6658626198768616},{"id":"https://openalex.org/C172722865","wikidata":"https://www.wikidata.org/wiki/Q2302053","display_name":"Spatial query","level":5,"score":0.5898723602294922},{"id":"https://openalex.org/C99016210","wikidata":"https://www.wikidata.org/wiki/Q5488129","display_name":"Query expansion","level":2,"score":0.5778234004974365},{"id":"https://openalex.org/C192028432","wikidata":"https://www.wikidata.org/wiki/Q845739","display_name":"Query language","level":2,"score":0.5480402708053589},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.546812117099762},{"id":"https://openalex.org/C54239708","wikidata":"https://www.wikidata.org/wiki/Q1329910","display_name":"View","level":3,"score":0.5327819585800171},{"id":"https://openalex.org/C192939062","wikidata":"https://www.wikidata.org/wiki/Q104840822","display_name":"Sargable","level":4,"score":0.516997218132019},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.503086507320404},{"id":"https://openalex.org/C118689300","wikidata":"https://www.wikidata.org/wiki/Q7978614","display_name":"Web query classification","level":4,"score":0.4831359088420868},{"id":"https://openalex.org/C73555534","wikidata":"https://www.wikidata.org/wiki/Q622825","display_name":"Cluster analysis","level":2,"score":0.47478052973747253},{"id":"https://openalex.org/C510870499","wikidata":"https://www.wikidata.org/wiki/Q47607","display_name":"SQL","level":2,"score":0.41971555352211},{"id":"https://openalex.org/C127705205","wikidata":"https://www.wikidata.org/wiki/Q5748245","display_name":"Heuristics","level":2,"score":0.4147895872592926},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.39981669187545776},{"id":"https://openalex.org/C164120249","wikidata":"https://www.wikidata.org/wiki/Q995982","display_name":"Web search query","level":3,"score":0.3563038408756256},{"id":"https://openalex.org/C148840519","wikidata":"https://www.wikidata.org/wiki/Q1049878","display_name":"Database design","level":2,"score":0.2625710368156433},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.13421818614006042},{"id":"https://openalex.org/C97854310","wikidata":"https://www.wikidata.org/wiki/Q19541","display_name":"Search engine","level":2,"score":0.1206827163696289},{"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:10.1109/tkde.2018.2831214","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tkde.2018.2831214","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"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320306076","display_name":"National Science Foundation","ror":"https://ror.org/021nxhr62"},{"id":"https://openalex.org/F4320309636","display_name":"University of Minnesota","ror":"https://ror.org/03grvy078"},{"id":"https://openalex.org/F4320332641","display_name":"University at Buffalo","ror":"https://ror.org/01y64my43"},{"id":"https://openalex.org/F4320338287","display_name":"Oak Ridge National Laboratory","ror":"https://ror.org/01qz5mb56"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":39,"referenced_works":["https://openalex.org/W5925479","https://openalex.org/W255556494","https://openalex.org/W1481547447","https://openalex.org/W1488870204","https://openalex.org/W1623444038","https://openalex.org/W1979514837","https://openalex.org/W2003251288","https://openalex.org/W2071304174","https://openalex.org/W2080224812","https://openalex.org/W2108883953","https://openalex.org/W2114432784","https://openalex.org/W2115482638","https://openalex.org/W2118178958","https://openalex.org/W2119745643","https://openalex.org/W2131145040","https://openalex.org/W2134179408","https://openalex.org/W2142498761","https://openalex.org/W2145663758","https://openalex.org/W2163345053","https://openalex.org/W2269738476","https://openalex.org/W2294695527","https://openalex.org/W2295144739","https://openalex.org/W2400869242","https://openalex.org/W2403952154","https://openalex.org/W2405294958","https://openalex.org/W2486008984","https://openalex.org/W2492576631","https://openalex.org/W2508283490","https://openalex.org/W2546758670","https://openalex.org/W2911978475","https://openalex.org/W3145004415","https://openalex.org/W4285719527","https://openalex.org/W6600242695","https://openalex.org/W6629052763","https://openalex.org/W6681029592","https://openalex.org/W6713325888","https://openalex.org/W6713705578","https://openalex.org/W6713722459","https://openalex.org/W6723072248"],"related_works":["https://openalex.org/W1003283331","https://openalex.org/W2374912898","https://openalex.org/W2150741898","https://openalex.org/W2554271401","https://openalex.org/W2406556739","https://openalex.org/W2128834514","https://openalex.org/W2970853428","https://openalex.org/W4379390531","https://openalex.org/W2186703450","https://openalex.org/W2903968032"],"abstract_inverted_index":{"Database":[0],"access":[1],"logs":[2,28],"are":[3,29],"the":[4,47,61,71,86,96,106,121,140,143,170],"starting":[5],"point":[6],"for":[7,39,81],"many":[8,24,66],"forms":[9],"of":[10,49,73,98,114,135,142,172],"database":[11,14,90],"administration,":[12],"from":[13,46],"performance":[15,171],"tuning,":[16],"to":[17,20,42,79,124,157],"security":[18],"auditing,":[19],"benchmark":[21],"design,":[22],"and":[23,32,34,89],"more.":[25],"Unfortunately,":[26],"query":[27,63,107,116,125,129,136,155,159],"also":[30],"large":[31],"unwieldy,":[33],"it":[35],"can":[36],"be":[37],"difficult":[38],"an":[40],"analyst":[41],"extract":[43],"broad":[44],"patterns":[45],"set":[48],"queries":[50],"found":[51],"therein.":[52],"Clustering":[53],"is":[54,77,92],"a":[55,111,148,166],"natural":[56],"first":[57],"step":[58],"towards":[59],"understanding":[60],"massive":[62],"logs.":[64],"However,":[65],"clustering":[67,126],"methods":[68],"rely":[69],"on":[70,105,127],"notion":[72],"pairwise":[74],"similarity,":[75],"which":[76],"challenging":[78],"compute":[80],"SQL":[82],"queries,":[83,102],"especially":[84],"when":[85],"underlying":[87],"data":[88],"schema":[91],"unavailable.":[93],"We":[94,109],"investigate":[95],"problem":[97],"computing":[99],"similarity":[100,117,175],"between":[101],"relying":[103],"only":[104],"structure.":[108,160],"conduct":[110],"rigorous":[112],"evaluation":[113],"three":[115,144,174],"heuristics":[118],"proposed":[119,162],"in":[120,165,169],"literature":[122],"applied":[123],"multiple":[128],"log":[130],"datasets,":[131],"representing":[132],"different":[133],"types":[134],"workloads.":[137],"To":[138],"improve":[139],"accuracy":[141],"heuristics,":[145],"we":[146],"propose":[147],"generic":[149],"feature":[150],"engineering":[151],"strategy,":[152],"using":[153],"classical":[154],"rewrites":[156],"standardize":[158],"The":[161],"strategy":[163],"results":[164],"significant":[167],"improvement":[168],"all":[173],"heuristics.":[176]},"counts_by_year":[{"year":2025,"cited_by_count":10},{"year":2024,"cited_by_count":4},{"year":2023,"cited_by_count":6},{"year":2022,"cited_by_count":7},{"year":2021,"cited_by_count":5},{"year":2020,"cited_by_count":12},{"year":2019,"cited_by_count":7},{"year":2018,"cited_by_count":4}],"updated_date":"2026-03-20T23:20:44.827607","created_date":"2025-10-10T00:00:00"}