{"id":"https://openalex.org/W2142650462","doi":"https://doi.org/10.1109/icde.2010.5447888","title":"Surrogate ranking for very expensive similarity queries","display_name":"Surrogate ranking for very expensive similarity queries","publication_year":2010,"publication_date":"2010-01-01","ids":{"openalex":"https://openalex.org/W2142650462","doi":"https://doi.org/10.1109/icde.2010.5447888","mag":"2142650462"},"language":"en","primary_location":{"id":"doi:10.1109/icde.2010.5447888","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icde.2010.5447888","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2010 IEEE 26th International Conference on Data Engineering (ICDE 2010)","raw_type":"proceedings-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/A5015286019","display_name":"Fei Xu","orcid":"https://orcid.org/0000-0002-5711-7029"},"institutions":[{"id":"https://openalex.org/I33213144","display_name":"University of Florida","ror":"https://ror.org/02y3ad647","country_code":"US","type":"education","lineage":["https://openalex.org/I33213144"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Fei Xu","raw_affiliation_strings":["CISE Department, University of Florida, Gainesville, FL, USA","CISE Department, University of Florida, Gainesville, 32601, USA"],"affiliations":[{"raw_affiliation_string":"CISE Department, University of Florida, Gainesville, FL, USA","institution_ids":["https://openalex.org/I33213144"]},{"raw_affiliation_string":"CISE Department, University of Florida, Gainesville, 32601, USA","institution_ids":["https://openalex.org/I33213144"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5014385193","display_name":"Ravi Jampani","orcid":null},"institutions":[{"id":"https://openalex.org/I33213144","display_name":"University of Florida","ror":"https://ror.org/02y3ad647","country_code":"US","type":"education","lineage":["https://openalex.org/I33213144"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Ravi Jampani","raw_affiliation_strings":["CISE Department, University of Florida, Gainesville, FL, USA","CISE Department, University of Florida, Gainesville, 32601, USA"],"affiliations":[{"raw_affiliation_string":"CISE Department, University of Florida, Gainesville, FL, USA","institution_ids":["https://openalex.org/I33213144"]},{"raw_affiliation_string":"CISE Department, University of Florida, Gainesville, 32601, USA","institution_ids":["https://openalex.org/I33213144"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5103182309","display_name":"Mingxi Wu","orcid":"https://orcid.org/0009-0009-2738-7018"},"institutions":[{"id":"https://openalex.org/I1342911587","display_name":"Oracle (United States)","ror":"https://ror.org/006c77m33","country_code":"US","type":"company","lineage":["https://openalex.org/I1342911587"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Mingxi Wu","raw_affiliation_strings":["CISE Department, Oracle Corporation, Redwood Shores, CA, USA","Oracle Corp. Redwood Shores, CA, 94065, USA"],"affiliations":[{"raw_affiliation_string":"CISE Department, Oracle Corporation, Redwood Shores, CA, USA","institution_ids":["https://openalex.org/I1342911587"]},{"raw_affiliation_string":"Oracle Corp. Redwood Shores, CA, 94065, USA","institution_ids":["https://openalex.org/I1342911587"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5002518742","display_name":"Chris Jermaine","orcid":null},"institutions":[{"id":"https://openalex.org/I33213144","display_name":"University of Florida","ror":"https://ror.org/02y3ad647","country_code":"US","type":"education","lineage":["https://openalex.org/I33213144"]},{"id":"https://openalex.org/I74775410","display_name":"Rice University","ror":"https://ror.org/008zs3103","country_code":"US","type":"education","lineage":["https://openalex.org/I74775410"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Chris Jermaine","raw_affiliation_strings":["Computer Science Department, Rice University, Houston, TX, USA","CISE Department, University of Florida, Gainesville, 32601, USA"],"affiliations":[{"raw_affiliation_string":"Computer Science Department, Rice University, Houston, TX, USA","institution_ids":["https://openalex.org/I74775410"]},{"raw_affiliation_string":"CISE Department, University of Florida, Gainesville, 32601, USA","institution_ids":["https://openalex.org/I33213144"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5091769289","display_name":"Tamer Kahveci","orcid":"https://orcid.org/0000-0002-4403-8612"},"institutions":[{"id":"https://openalex.org/I33213144","display_name":"University of Florida","ror":"https://ror.org/02y3ad647","country_code":"US","type":"education","lineage":["https://openalex.org/I33213144"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Tamer Kahveci","raw_affiliation_strings":["CISE Department, University of Florida, Gainesville, FL, USA","CISE Department, University of Florida, Gainesville, 32601, USA"],"affiliations":[{"raw_affiliation_string":"CISE Department, University of Florida, Gainesville, FL, USA","institution_ids":["https://openalex.org/I33213144"]},{"raw_affiliation_string":"CISE Department, University of Florida, Gainesville, 32601, USA","institution_ids":["https://openalex.org/I33213144"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5015286019"],"corresponding_institution_ids":["https://openalex.org/I33213144"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.19954274,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"2 b","issue":null,"first_page":"848","last_page":"859"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11106","display_name":"Data Management and Algorithms","score":0.9998999834060669,"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":0.9998999834060669,"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/T11303","display_name":"Bayesian Modeling and Causal Inference","score":0.992900013923645,"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/T12205","display_name":"Time Series Analysis and Forecasting","score":0.9902999997138977,"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/computer-science","display_name":"Computer science","score":0.7507458925247192},{"id":"https://openalex.org/keywords/ranking","display_name":"Ranking (information retrieval)","score":0.7438827157020569},{"id":"https://openalex.org/keywords/similarity","display_name":"Similarity (geometry)","score":0.6767696738243103},{"id":"https://openalex.org/keywords/metric","display_name":"Metric (unit)","score":0.6235870718955994},{"id":"https://openalex.org/keywords/search-engine-indexing","display_name":"Search engine indexing","score":0.5932489633560181},{"id":"https://openalex.org/keywords/measure","display_name":"Measure (data warehouse)","score":0.589286208152771},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.5887046456336975},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.5749549269676208},{"id":"https://openalex.org/keywords/similarity-measure","display_name":"Similarity measure","score":0.5620593428611755},{"id":"https://openalex.org/keywords/bayesian-probability","display_name":"Bayesian probability","score":0.47830823063850403},{"id":"https://openalex.org/keywords/function","display_name":"Function (biology)","score":0.4470246136188507},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.44224855303764343},{"id":"https://openalex.org/keywords/construct","display_name":"Construct (python library)","score":0.43321698904037476},{"id":"https://openalex.org/keywords/database","display_name":"Database","score":0.4227350354194641},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.2539670765399933},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.10313957929611206}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7507458925247192},{"id":"https://openalex.org/C189430467","wikidata":"https://www.wikidata.org/wiki/Q7293293","display_name":"Ranking (information retrieval)","level":2,"score":0.7438827157020569},{"id":"https://openalex.org/C103278499","wikidata":"https://www.wikidata.org/wiki/Q254465","display_name":"Similarity (geometry)","level":3,"score":0.6767696738243103},{"id":"https://openalex.org/C176217482","wikidata":"https://www.wikidata.org/wiki/Q860554","display_name":"Metric (unit)","level":2,"score":0.6235870718955994},{"id":"https://openalex.org/C75165309","wikidata":"https://www.wikidata.org/wiki/Q2258979","display_name":"Search engine indexing","level":2,"score":0.5932489633560181},{"id":"https://openalex.org/C2780009758","wikidata":"https://www.wikidata.org/wiki/Q6804172","display_name":"Measure (data warehouse)","level":2,"score":0.589286208152771},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.5887046456336975},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.5749549269676208},{"id":"https://openalex.org/C2776517306","wikidata":"https://www.wikidata.org/wiki/Q29017317","display_name":"Similarity measure","level":2,"score":0.5620593428611755},{"id":"https://openalex.org/C107673813","wikidata":"https://www.wikidata.org/wiki/Q812534","display_name":"Bayesian probability","level":2,"score":0.47830823063850403},{"id":"https://openalex.org/C14036430","wikidata":"https://www.wikidata.org/wiki/Q3736076","display_name":"Function (biology)","level":2,"score":0.4470246136188507},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.44224855303764343},{"id":"https://openalex.org/C2780801425","wikidata":"https://www.wikidata.org/wiki/Q5164392","display_name":"Construct (python library)","level":2,"score":0.43321698904037476},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.4227350354194641},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.2539670765399933},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.10313957929611206},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0},{"id":"https://openalex.org/C78458016","wikidata":"https://www.wikidata.org/wiki/Q840400","display_name":"Evolutionary biology","level":1,"score":0.0},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"id":"https://openalex.org/C21547014","wikidata":"https://www.wikidata.org/wiki/Q1423657","display_name":"Operations management","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/icde.2010.5447888","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icde.2010.5447888","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2010 IEEE 26th International Conference on Data Engineering (ICDE 2010)","raw_type":"proceedings-article"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.225.9288","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.225.9288","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www.cise.ufl.edu/%7Etamer/papers/icde2009.pdf","raw_type":"text"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":31,"referenced_works":["https://openalex.org/W1569403765","https://openalex.org/W1579271636","https://openalex.org/W1592614241","https://openalex.org/W1981662606","https://openalex.org/W1995106824","https://openalex.org/W2009423060","https://openalex.org/W2046144220","https://openalex.org/W2049882758","https://openalex.org/W2050273205","https://openalex.org/W2055043387","https://openalex.org/W2068481735","https://openalex.org/W2071866949","https://openalex.org/W2097357324","https://openalex.org/W2097921974","https://openalex.org/W2109424811","https://openalex.org/W2110449999","https://openalex.org/W2116892443","https://openalex.org/W2117853077","https://openalex.org/W2121773288","https://openalex.org/W2134627110","https://openalex.org/W2136391241","https://openalex.org/W2143011057","https://openalex.org/W2152326664","https://openalex.org/W2159482845","https://openalex.org/W2488678869","https://openalex.org/W2977504015","https://openalex.org/W4232023503","https://openalex.org/W4236236547","https://openalex.org/W4256038730","https://openalex.org/W6668499198","https://openalex.org/W6674878074"],"related_works":["https://openalex.org/W3024364549","https://openalex.org/W4206019083","https://openalex.org/W2048865712","https://openalex.org/W1976265003","https://openalex.org/W2370378377","https://openalex.org/W51364034","https://openalex.org/W2141938446","https://openalex.org/W2898073868","https://openalex.org/W4284663758","https://openalex.org/W2043026651"],"abstract_inverted_index":{"We":[0,66,99],"consider":[1],"the":[2,10,14,23,39,55,80,95,106,109,113,125,131,136,143,146,151],"problem":[3],"of":[4,12,38,50,145],"similarity":[5,15,24,97,114],"search":[6],"in":[7,76],"applications":[8],"where":[9],"cost":[11],"computing":[13],"between":[16,108],"two":[17],"records":[18,41],"is":[19,26,62,83],"very":[20],"expensive,":[21],"and":[22,60,112],"measure":[25],"not":[27,64],"a":[28,35,43,68,101,117],"metric.":[29],"In":[30],"such":[31,77],"applications,":[32],"comparing":[33],"even":[34],"tiny":[36],"fraction":[37],"database":[40,57,81],"to":[42,85,123],"single":[44],"query":[45],"record":[46],"can":[47,160],"be":[48],"orders":[49],"magnitude":[51],"slower":[52],"than":[53],"reading":[54],"entire":[56],"from":[58],"disk,":[59],"indexing":[61],"often":[63],"possible.":[65],"develop":[67,100],"general-purpose,":[69],"statistical":[70],"framework":[71],"for":[72,94,164],"answering":[73],"top-k":[74],"queries":[75],"databases,":[78],"when":[79],"administrator":[82],"able":[84],"supply":[86],"an":[87],"inexpensive":[88],"surrogate":[89,110,152],"ranking":[90],"function":[91,111],"that":[92,104,157],"substitutes":[93],"actual":[96],"measure.":[98,115],"robust":[102],"method":[103],"learns":[105],"relationship":[107],"Given":[116],"query,":[118],"we":[119,139],"use":[120],"Bayesian":[121],"statistics":[122],"update":[124],"model":[126],"by":[127],"taking":[128],"into":[129],"account":[130],"observed":[132],"partial":[133],"results.":[134],"Using":[135],"updated":[137],"model,":[138],"construct":[140],"bounds":[141,163],"on":[142],"accuracy":[144],"result":[147],"set":[148],"obtained":[149],"via":[150],"ranking.":[153],"Our":[154],"experiments":[155],"show":[156],"our":[158],"models":[159],"produce":[161],"useful":[162],"several":[165],"real-life":[166],"applications.":[167]},"counts_by_year":[],"updated_date":"2026-04-05T17:49:38.594831","created_date":"2025-10-10T00:00:00"}