{"id":"https://openalex.org/W2018816493","doi":"https://doi.org/10.1145/1739041.1739051","title":"Turbo-charging hidden database samplers with overflowing queries and skew reduction","display_name":"Turbo-charging hidden database samplers with overflowing queries and skew reduction","publication_year":2010,"publication_date":"2010-03-16","ids":{"openalex":"https://openalex.org/W2018816493","doi":"https://doi.org/10.1145/1739041.1739051","mag":"2018816493"},"language":"en","primary_location":{"id":"doi:10.1145/1739041.1739051","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1739041.1739051","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 13th International Conference on Extending Database Technology","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/A5057802863","display_name":"Arjun Dasgupta","orcid":null},"institutions":[{"id":"https://openalex.org/I189196454","display_name":"The University of Texas at Arlington","ror":"https://ror.org/019kgqr73","country_code":"US","type":"education","lineage":["https://openalex.org/I189196454"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Arjun Dasgupta","raw_affiliation_strings":["University of Texas at Arlington"],"affiliations":[{"raw_affiliation_string":"University of Texas at Arlington","institution_ids":["https://openalex.org/I189196454"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5103883353","display_name":"Nan Zhang","orcid":"https://orcid.org/0009-0001-1836-7332"},"institutions":[{"id":"https://openalex.org/I193531525","display_name":"George Washington University","ror":"https://ror.org/00y4zzh67","country_code":"US","type":"education","lineage":["https://openalex.org/I193531525"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Nan Zhang","raw_affiliation_strings":["George Washington University","george Washington University"],"affiliations":[{"raw_affiliation_string":"George Washington University","institution_ids":["https://openalex.org/I193531525"]},{"raw_affiliation_string":"george Washington University","institution_ids":["https://openalex.org/I193531525"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5002203026","display_name":"Gautam Das","orcid":"https://orcid.org/0000-0002-4627-9065"},"institutions":[{"id":"https://openalex.org/I189196454","display_name":"The University of Texas at Arlington","ror":"https://ror.org/019kgqr73","country_code":"US","type":"education","lineage":["https://openalex.org/I189196454"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Gautam Das","raw_affiliation_strings":["University of Texas at Arlington"],"affiliations":[{"raw_affiliation_string":"University of Texas at Arlington","institution_ids":["https://openalex.org/I189196454"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5057802863"],"corresponding_institution_ids":["https://openalex.org/I189196454"],"apc_list":null,"apc_paid":null,"fwci":4.2849,"has_fulltext":false,"cited_by_count":22,"citation_normalized_percentile":{"value":0.94758383,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"51","last_page":"62"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12016","display_name":"Web Data Mining and Analysis","score":0.9998000264167786,"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/T12016","display_name":"Web Data Mining and Analysis","score":0.9998000264167786,"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":0.9948999881744385,"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/T11644","display_name":"Spam and Phishing Detection","score":0.9945999979972839,"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":0.8628861308097839},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8078188896179199},{"id":"https://openalex.org/keywords/skew","display_name":"Skew","score":0.7493774890899658},{"id":"https://openalex.org/keywords/database","display_name":"Database","score":0.6867566704750061},{"id":"https://openalex.org/keywords/reduction","display_name":"Reduction (mathematics)","score":0.5652565360069275},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.49560821056365967},{"id":"https://openalex.org/keywords/key","display_name":"Key (lock)","score":0.48581981658935547},{"id":"https://openalex.org/keywords/sampling","display_name":"Sampling (signal processing)","score":0.4739527702331543},{"id":"https://openalex.org/keywords/operating-system","display_name":"Operating system","score":0.09984937310218811},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.08166667819023132},{"id":"https://openalex.org/keywords/filter","display_name":"Filter (signal processing)","score":0.07687464356422424}],"concepts":[{"id":"https://openalex.org/C118930307","wikidata":"https://www.wikidata.org/wiki/Q600590","display_name":"Tuple","level":2,"score":0.8628861308097839},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8078188896179199},{"id":"https://openalex.org/C43711488","wikidata":"https://www.wikidata.org/wiki/Q7534783","display_name":"Skew","level":2,"score":0.7493774890899658},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.6867566704750061},{"id":"https://openalex.org/C111335779","wikidata":"https://www.wikidata.org/wiki/Q3454686","display_name":"Reduction (mathematics)","level":2,"score":0.5652565360069275},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.49560821056365967},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.48581981658935547},{"id":"https://openalex.org/C140779682","wikidata":"https://www.wikidata.org/wiki/Q210868","display_name":"Sampling (signal processing)","level":3,"score":0.4739527702331543},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.09984937310218811},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.08166667819023132},{"id":"https://openalex.org/C106131492","wikidata":"https://www.wikidata.org/wiki/Q3072260","display_name":"Filter (signal processing)","level":2,"score":0.07687464356422424},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","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/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.0},{"id":"https://openalex.org/C118615104","wikidata":"https://www.wikidata.org/wiki/Q121416","display_name":"Discrete mathematics","level":1,"score":0.0}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1145/1739041.1739051","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1739041.1739051","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 13th International Conference on Extending Database Technology","raw_type":"proceedings-article"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.332.649","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.332.649","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www.edbt.org/Proceedings/2010-Lausanne/edbt/papers/p0051-Dasgupta.pdf","raw_type":"text"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.616.6563","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.616.6563","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://home.gwu.edu/~nzhang10/hiddenprivacy/files/DZD10.pdf","raw_type":"text"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G2482822759","display_name":null,"funder_award_id":"8.53E+47","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"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":22,"referenced_works":["https://openalex.org/W1586825695","https://openalex.org/W1601949013","https://openalex.org/W1605217017","https://openalex.org/W1978277861","https://openalex.org/W1986828474","https://openalex.org/W1998674327","https://openalex.org/W2003316857","https://openalex.org/W2083039049","https://openalex.org/W2099797738","https://openalex.org/W2102815161","https://openalex.org/W2118356300","https://openalex.org/W2128941908","https://openalex.org/W2129817180","https://openalex.org/W2131006463","https://openalex.org/W2136059419","https://openalex.org/W2147232895","https://openalex.org/W2152029707","https://openalex.org/W2155569834","https://openalex.org/W2164520297","https://openalex.org/W2170188121","https://openalex.org/W6682827647","https://openalex.org/W6685116542"],"related_works":["https://openalex.org/W4245395944","https://openalex.org/W2143551613","https://openalex.org/W4290802965","https://openalex.org/W2138823233","https://openalex.org/W1979740464","https://openalex.org/W97789383","https://openalex.org/W2143345456","https://openalex.org/W1789991335","https://openalex.org/W2562731034","https://openalex.org/W4315705795"],"abstract_inverted_index":{"Recently,":[0],"there":[1],"has":[2],"been":[3],"growing":[4],"interest":[5],"in":[6,111,124],"random":[7,66],"sampling":[8,67,135],"from":[9],"online":[10],"hidden":[11,70],"databases.":[12,71],"These":[13],"databases":[14],"reside":[15],"behind":[16],"form-like":[17],"web":[18],"interfaces":[19],"which":[20],"allow":[21],"users":[22],"to":[23,76,113],"execute":[24],"search":[25],"queries":[26,132],"by":[27,39,52,83],"specifying":[28],"the":[29,36,48,62,78,84,125],"desired":[30],"values":[31],"for":[32],"certain":[33],"attributes,":[34],"and":[35,119],"system":[37],"responds":[38],"returning":[40],"a":[41,53,99],"few":[42],"(e.g.,":[43],"top-k)":[44],"tuples":[45,118],"that":[46],"satisfy":[47],"selection":[49],"conditions,":[50],"sorted":[51],"suitable":[54],"scoring":[55],"function.":[56],"In":[57],"this":[58,93],"paper,":[59],"we":[60],"consider":[61],"problem":[63],"of":[64,80,87],"uniform":[65],"over":[68],"such":[69],"A":[72],"key":[73],"challenge":[74],"is":[75,109],"eliminate":[77],"skew":[79,123],"samples":[81],"incurred":[82],"selective":[85],"return":[86],"highly":[88,116],"ranked":[89,117],"tuples.":[90],"To":[91],"address":[92],"challenge,":[94],"all":[95],"state-of-the-art":[96],"samplers":[97],"share":[98],"common":[100],"approach:":[101],"they":[102],"do":[103],"not":[104,129],"use":[105],"overflowing":[106,131],"queries.":[107],"This":[108],"done":[110],"order":[112],"avoid":[114],"favoring":[115],"thus":[120],"incurring":[121],"high":[122],"retrieved":[126],"samples.":[127],"However,":[128],"considering":[130],"substantially":[133],"impacts":[134],"efficiency.":[136]},"counts_by_year":[{"year":2019,"cited_by_count":1},{"year":2017,"cited_by_count":3},{"year":2016,"cited_by_count":2},{"year":2015,"cited_by_count":5},{"year":2014,"cited_by_count":5},{"year":2013,"cited_by_count":1},{"year":2012,"cited_by_count":1}],"updated_date":"2026-04-05T17:49:38.594831","created_date":"2025-10-10T00:00:00"}