{"id":"https://openalex.org/W2142099410","doi":"https://doi.org/10.1145/1007568.1007588","title":"Diamond in the rough","display_name":"Diamond in the rough","publication_year":2004,"publication_date":"2004-06-13","ids":{"openalex":"https://openalex.org/W2142099410","doi":"https://doi.org/10.1145/1007568.1007588","mag":"2142099410"},"language":"en","primary_location":{"id":"doi:10.1145/1007568.1007588","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1007568.1007588","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2004 ACM SIGMOD international conference on Management of data","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/A5031896681","display_name":"Graham Cormode","orcid":"https://orcid.org/0000-0002-0698-0922"},"institutions":[{"id":"https://openalex.org/I4210096112","display_name":"Rutgers Sexual and Reproductive Health and Rights","ror":"https://ror.org/00rcvgx40","country_code":"NL","type":"other","lineage":["https://openalex.org/I4210096112"]},{"id":"https://openalex.org/I102322142","display_name":"Rutgers, The State University of New Jersey","ror":"https://ror.org/05vt9qd57","country_code":"US","type":"education","lineage":["https://openalex.org/I102322142"]}],"countries":["NL","US"],"is_corresponding":true,"raw_author_name":"Graham Cormode","raw_affiliation_strings":["Rutgers University","Rutgers, University"],"affiliations":[{"raw_affiliation_string":"Rutgers University","institution_ids":["https://openalex.org/I4210096112"]},{"raw_affiliation_string":"Rutgers, University","institution_ids":["https://openalex.org/I102322142"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5110197814","display_name":"Flip Korn","orcid":null},"institutions":[{"id":"https://openalex.org/I1283103587","display_name":"AT&T (United States)","ror":"https://ror.org/02bbd5539","country_code":"US","type":"company","lineage":["https://openalex.org/I1283103587"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Flip Korn","raw_affiliation_strings":["AT&amp;T Labs-Research"],"affiliations":[{"raw_affiliation_string":"AT&amp;T Labs-Research","institution_ids":["https://openalex.org/I1283103587"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5075159410","display_name":"S. Muthukrishnan","orcid":"https://orcid.org/0009-0007-8936-5709"},"institutions":[{"id":"https://openalex.org/I102322142","display_name":"Rutgers, The State University of New Jersey","ror":"https://ror.org/05vt9qd57","country_code":"US","type":"education","lineage":["https://openalex.org/I102322142"]},{"id":"https://openalex.org/I4210096112","display_name":"Rutgers Sexual and Reproductive Health and Rights","ror":"https://ror.org/00rcvgx40","country_code":"NL","type":"other","lineage":["https://openalex.org/I4210096112"]}],"countries":["NL","US"],"is_corresponding":false,"raw_author_name":"S. Muthukrishnan","raw_affiliation_strings":["Rutgers University","Rutgers, University"],"affiliations":[{"raw_affiliation_string":"Rutgers University","institution_ids":["https://openalex.org/I4210096112"]},{"raw_affiliation_string":"Rutgers, University","institution_ids":["https://openalex.org/I102322142"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5088315797","display_name":"Divesh Srivastava","orcid":"https://orcid.org/0000-0002-7609-9217"},"institutions":[{"id":"https://openalex.org/I1283103587","display_name":"AT&T (United States)","ror":"https://ror.org/02bbd5539","country_code":"US","type":"company","lineage":["https://openalex.org/I1283103587"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Divesh Srivastava","raw_affiliation_strings":["AT&amp;T Labs-Research"],"affiliations":[{"raw_affiliation_string":"AT&amp;T Labs-Research","institution_ids":["https://openalex.org/I1283103587"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5031896681"],"corresponding_institution_ids":["https://openalex.org/I102322142","https://openalex.org/I4210096112"],"apc_list":null,"apc_paid":null,"fwci":6.0008,"has_fulltext":false,"cited_by_count":124,"citation_normalized_percentile":{"value":0.96780263,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":90,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"155","last_page":"166"},"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/T10317","display_name":"Advanced Database Systems and Queries","score":0.998199999332428,"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":0.9970999956130981,"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":0.7821149826049805},{"id":"https://openalex.org/keywords/aggregate","display_name":"Aggregate (composite)","score":0.6975356340408325},{"id":"https://openalex.org/keywords/data-stream-mining","display_name":"Data stream mining","score":0.6096530556678772},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.6007603406906128},{"id":"https://openalex.org/keywords/data-warehouse","display_name":"Data warehouse","score":0.5298500061035156},{"id":"https://openalex.org/keywords/hierarchy","display_name":"Hierarchy","score":0.4633956551551819},{"id":"https://openalex.org/keywords/node","display_name":"Node (physics)","score":0.44923973083496094},{"id":"https://openalex.org/keywords/data-stream","display_name":"Data stream","score":0.4459347724914551},{"id":"https://openalex.org/keywords/range","display_name":"Range (aeronautics)","score":0.42909902334213257},{"id":"https://openalex.org/keywords/theoretical-computer-science","display_name":"Theoretical computer science","score":0.37468767166137695},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.3316744267940521}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7821149826049805},{"id":"https://openalex.org/C4679612","wikidata":"https://www.wikidata.org/wiki/Q866298","display_name":"Aggregate (composite)","level":2,"score":0.6975356340408325},{"id":"https://openalex.org/C89198739","wikidata":"https://www.wikidata.org/wiki/Q3079880","display_name":"Data stream mining","level":2,"score":0.6096530556678772},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.6007603406906128},{"id":"https://openalex.org/C135572916","wikidata":"https://www.wikidata.org/wiki/Q193351","display_name":"Data warehouse","level":2,"score":0.5298500061035156},{"id":"https://openalex.org/C31170391","wikidata":"https://www.wikidata.org/wiki/Q188619","display_name":"Hierarchy","level":2,"score":0.4633956551551819},{"id":"https://openalex.org/C62611344","wikidata":"https://www.wikidata.org/wiki/Q1062658","display_name":"Node (physics)","level":2,"score":0.44923973083496094},{"id":"https://openalex.org/C2778484313","wikidata":"https://www.wikidata.org/wiki/Q1172540","display_name":"Data stream","level":2,"score":0.4459347724914551},{"id":"https://openalex.org/C204323151","wikidata":"https://www.wikidata.org/wiki/Q905424","display_name":"Range (aeronautics)","level":2,"score":0.42909902334213257},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.37468767166137695},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.3316744267940521},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.0},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0},{"id":"https://openalex.org/C192562407","wikidata":"https://www.wikidata.org/wiki/Q228736","display_name":"Materials science","level":0,"score":0.0},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.0},{"id":"https://openalex.org/C34447519","wikidata":"https://www.wikidata.org/wiki/Q179522","display_name":"Market economy","level":1,"score":0.0},{"id":"https://openalex.org/C159985019","wikidata":"https://www.wikidata.org/wiki/Q181790","display_name":"Composite material","level":1,"score":0.0},{"id":"https://openalex.org/C66938386","wikidata":"https://www.wikidata.org/wiki/Q633538","display_name":"Structural engineering","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/1007568.1007588","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1007568.1007588","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2004 ACM SIGMOD international conference on Management of data","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":16,"referenced_works":["https://openalex.org/W1516469158","https://openalex.org/W1965972569","https://openalex.org/W2045604576","https://openalex.org/W2053075747","https://openalex.org/W2069980026","https://openalex.org/W2092103580","https://openalex.org/W2098366185","https://openalex.org/W2114029045","https://openalex.org/W2128869116","https://openalex.org/W2141441292","https://openalex.org/W2152637787","https://openalex.org/W2167973519","https://openalex.org/W4230230708","https://openalex.org/W4246532143","https://openalex.org/W4250544186","https://openalex.org/W4285719527"],"related_works":["https://openalex.org/W2106570241","https://openalex.org/W2107586730","https://openalex.org/W3046869667","https://openalex.org/W4361801939","https://openalex.org/W3207785250","https://openalex.org/W2958623481","https://openalex.org/W105155515","https://openalex.org/W2991818765","https://openalex.org/W807005383","https://openalex.org/W1572762191"],"abstract_inverted_index":{"Data":[0],"items":[1],"archived":[2],"in":[3,75,127,169,196,216],"data":[4,38,86,92,138,151,158],"warehouses":[5],"or":[6],"those":[7],"that":[8,145,165,183],"arrive":[9],"online":[10,163,186,218],"as":[11,70],"streams":[12],"typically":[13],"have":[14],"attributes":[15],"which":[16,190],"take":[17,146],"values":[18],"from":[19],"multiple":[20,99,147],"hierarchies":[21],"(e.g.,":[22],"time":[23],"and":[24,28,44,89,102,114,152,180],"geographic":[25],"location;":[26],"source":[27],"destination":[29],"IP":[30,91],"addresses).":[31],"Providing":[32],"an":[33,120],"aggregate":[34,49,121],"view":[35,50],"of":[36,57,85,106,206,209,230,236,239],"such":[37],"is":[39,131,213],"important":[40],"to":[41,80,98,133,199,220],"summarize,":[42],"visualize,":[43],"analyze.":[45],"We":[46],"develop":[47],"the":[48,82,112,128,150,154,207,237],"based":[51],"on":[52,118],"certain":[53],"hierarchically":[54],"organized":[55],"sets":[56],"large-valued":[58],"regions":[59],"(\"heavy":[60],"hitters\").":[61],"Such":[62],"Hierarchical":[63],"Heavy":[64],"Hitters":[65],"(HHHs)":[66],"were":[67],"previously":[68],"introduced":[69],"a":[71,124,226],"crucial":[72],"aggregation":[73],"technique":[74],"one":[76,170],"dimension.":[77],"In":[78],"order":[79],"analyze":[81],"wider":[83],"range":[84],"warehousing":[87,139],"applications":[88],"realistic":[90],"streams,":[93],"we":[94,141,161],"generalize":[95],"this":[96],"problem":[97],"dimensions.We":[100],"identify":[101],"study":[103],"two":[104],"variants":[105],"HHHs":[107,168,223],"for":[108,123],"multi-dimensional":[109,129],"data,":[110,182],"namely":[111],"\"overlap\"":[113],"\"split\"":[115],"cases,":[116],"depending":[117],"how":[119],"computed":[122],"child":[125],"node":[126],"hierarchy":[130],"propagated":[132],"its":[134],"parent":[135],"element(s).":[136],"For":[137,157],"applications,":[140,160],"present":[142,162],"offline":[143,201],"algorithms":[144,164,187,219],"passes":[148],"over":[149],"produce":[153],"exact":[155],"HHHs.":[156],"stream":[159],"find":[166],"approximate":[167,222],"pass,":[171],"with":[172],"provable":[173],"accuracy":[174],"guarantees.We":[175],"show":[176],"experimentally,":[177],"using":[178,224],"real":[179],"synthetic":[181],"our":[184,217],"proposed":[185],"yield":[188],"outputs":[189],"are":[191],"very":[192],"similar":[193],"(virtually":[194],"identical,":[195],"many":[197],"cases)":[198],"their":[200],"counterparts.":[202],"The":[203],"lattice":[204],"property":[205],"product":[208],"hierarchical":[210],"dimensions":[211],"(\"diamond\")":[212],"crucially":[214],"exploited":[215],"track":[221],"only":[225],"small,":[227],"fixed":[228],"number":[229,238],"statistics":[231],"per":[232],"candidate":[233],"node,":[234],"regardless":[235],"dimensions.":[240]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2024,"cited_by_count":3},{"year":2023,"cited_by_count":3},{"year":2022,"cited_by_count":1},{"year":2020,"cited_by_count":6},{"year":2019,"cited_by_count":2},{"year":2018,"cited_by_count":12},{"year":2017,"cited_by_count":5},{"year":2016,"cited_by_count":5},{"year":2015,"cited_by_count":2},{"year":2014,"cited_by_count":4},{"year":2013,"cited_by_count":3},{"year":2012,"cited_by_count":9}],"updated_date":"2026-04-10T15:06:20.359241","created_date":"2025-10-10T00:00:00"}
