{"id":"https://openalex.org/W2023027635","doi":"https://doi.org/10.1145/1142473.1142495","title":"Modeling skew in data streams","display_name":"Modeling skew in data streams","publication_year":2006,"publication_date":"2006-06-27","ids":{"openalex":"https://openalex.org/W2023027635","doi":"https://doi.org/10.1145/1142473.1142495","mag":"2023027635"},"language":"en","primary_location":{"id":"doi:10.1145/1142473.1142495","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1142473.1142495","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2006 ACM SIGMOD international conference on Management of data","raw_type":"proceedings-article"},"type":"conference-paper","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/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&T Labs-Research"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"AT&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"],"raw_orcid":null,"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/A5047714942","display_name":"Yihua Wu","orcid":"https://orcid.org/0000-0001-7952-4090"},"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":"Yihua Wu","raw_affiliation_strings":["Rutgers University","Rutgers, University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Rutgers University","institution_ids":["https://openalex.org/I4210096112"]},{"raw_affiliation_string":"Rutgers, University","institution_ids":["https://openalex.org/I102322142"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":26,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"181","last_page":"192"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11270","display_name":"Complex Systems and Time Series Analysis","score":0.989799976348877,"subfield":{"id":"https://openalex.org/subfields/2002","display_name":"Economics and Econometrics"},"field":{"id":"https://openalex.org/fields/20","display_name":"Economics, Econometrics and Finance"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},"topics":[{"id":"https://openalex.org/T11270","display_name":"Complex Systems and Time Series Analysis","score":0.989799976348877,"subfield":{"id":"https://openalex.org/subfields/2002","display_name":"Economics and Econometrics"},"field":{"id":"https://openalex.org/fields/20","display_name":"Economics, Econometrics and Finance"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},{"id":"https://openalex.org/T10799","display_name":"Data Visualization and Analytics","score":0.9886000156402588,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"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":0.9873999953269958,"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":0.7362945079803467},{"id":"https://openalex.org/keywords/data-stream-mining","display_name":"Data stream mining","score":0.5916640162467957},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.5679057240486145},{"id":"https://openalex.org/keywords/skew","display_name":"Skew","score":0.5031690001487732},{"id":"https://openalex.org/keywords/goodness-of-fit","display_name":"Goodness of fit","score":0.4850282073020935},{"id":"https://openalex.org/keywords/data-stream","display_name":"Data stream","score":0.4839670956134796},{"id":"https://openalex.org/keywords/data-modeling","display_name":"Data modeling","score":0.46650829911231995},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.15990877151489258}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7362945079803467},{"id":"https://openalex.org/C89198739","wikidata":"https://www.wikidata.org/wiki/Q3079880","display_name":"Data stream mining","level":2,"score":0.5916640162467957},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.5679057240486145},{"id":"https://openalex.org/C43711488","wikidata":"https://www.wikidata.org/wiki/Q7534783","display_name":"Skew","level":2,"score":0.5031690001487732},{"id":"https://openalex.org/C132480984","wikidata":"https://www.wikidata.org/wiki/Q2034239","display_name":"Goodness of fit","level":2,"score":0.4850282073020935},{"id":"https://openalex.org/C2778484313","wikidata":"https://www.wikidata.org/wiki/Q1172540","display_name":"Data stream","level":2,"score":0.4839670956134796},{"id":"https://openalex.org/C67186912","wikidata":"https://www.wikidata.org/wiki/Q367664","display_name":"Data modeling","level":2,"score":0.46650829911231995},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.15990877151489258},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.0},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/1142473.1142495","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1142473.1142495","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2006 ACM SIGMOD international conference on Management of data","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":42,"referenced_works":["https://openalex.org/W49087170","https://openalex.org/W67284852","https://openalex.org/W151938044","https://openalex.org/W1488681765","https://openalex.org/W1506099691","https://openalex.org/W1607125004","https://openalex.org/W1644934820","https://openalex.org/W1861510175","https://openalex.org/W1865797552","https://openalex.org/W1965972569","https://openalex.org/W2001474264","https://openalex.org/W2004110412","https://openalex.org/W2004154913","https://openalex.org/W2004570925","https://openalex.org/W2029284804","https://openalex.org/W2081189989","https://openalex.org/W2081903609","https://openalex.org/W2086345215","https://openalex.org/W2097995023","https://openalex.org/W2103040786","https://openalex.org/W2103733531","https://openalex.org/W2107779728","https://openalex.org/W2110784166","https://openalex.org/W2114038828","https://openalex.org/W2117853077","https://openalex.org/W2122528211","https://openalex.org/W2123274811","https://openalex.org/W2139058364","https://openalex.org/W2144042130","https://openalex.org/W2144261930","https://openalex.org/W2146603609","https://openalex.org/W2148048263","https://openalex.org/W2150569458","https://openalex.org/W2152637787","https://openalex.org/W2165967980","https://openalex.org/W2178864591","https://openalex.org/W2295205026","https://openalex.org/W4232023503","https://openalex.org/W4246464474","https://openalex.org/W4285719527","https://openalex.org/W6601990374","https://openalex.org/W7033787814"],"related_works":["https://openalex.org/W4297450198","https://openalex.org/W4389449520","https://openalex.org/W127192698","https://openalex.org/W2570600173","https://openalex.org/W2893008024","https://openalex.org/W2743735673","https://openalex.org/W4361801939","https://openalex.org/W2360131081","https://openalex.org/W2985941356","https://openalex.org/W2802243998"],"abstract_inverted_index":{"Data":[0],"stream":[1,34,128,232],"applications":[2],"have":[3],"made":[4],"use":[5],"of":[6,73,90,125,144,181,198,238,250,255,275],"statistical":[7,178],"summaries":[8],"to":[9,32,49,61,84,99,154,187,211,235],"reason":[10],"about":[11],"the":[12,38,45,86,91,115,126,160,177,183,246,273],"data":[13,35,75,111,127,173,206,231,258],"using":[14,76,118],"nonparametric":[15],"tools":[16],"such":[17],"as":[18],"histograms,":[19],"heavy":[20],"hitters,":[21],"and":[22,65,80,88,104,129,141,219,248,271],"join":[23],"sizes.":[24],"However,":[25],"relatively":[26],"little":[27],"attention":[28],"has":[29,42,208],"been":[30,209],"paid":[31],"modeling":[33],"parametrically,":[36],"despite":[37],"potential":[39,274],"this":[40,94],"approach":[41,120],"for":[43,167],"mining":[44],"data.":[46],"The":[47],"challenges":[48,117],"do":[50],"model":[51,92,190],"fitting":[52],"at":[53,192,241],"streaming":[54,193],"speeds":[55],"are":[56,138],"both":[57],"technical":[58,116],"--":[59,79,82],"how":[60,83,98],"continually":[62],"find":[63],"fast":[64,165],"reliable":[66],"parameter":[67,145],"estimates":[68,147],"on":[69,109,171,203,224],"high":[70],"speed":[71],"streams":[72,227],"skewed":[74,213],"small":[77],"space":[78],"conceptual":[81,161],"validate":[85],"goodness-of-fit":[87,169],"stability":[89,247],"online.In":[93],"paper,":[95],"we":[96,175,201,265],"show":[97],"fit":[100],"hierarchical":[101],"(binomial":[102],"multifractal)":[103],"non-hierarchical":[105],"(Pareto)":[106],"power-law":[107],"models":[108,252],"a":[110,123,149,172,195],"stream.":[112],"We":[113,158,215,244],"address":[114,159],"an":[119,260,267],"that":[121,137],"maintains":[122],"sketch":[124],"fits":[130],"least-squares":[131],"straight":[132],"lines;":[133],"it":[134],"yields":[135],"algorithms":[136],"fast,":[139],"space-efficient,":[140],"provide":[142],"approximations":[143],"value":[146],"with":[148,222],"priori":[150],"quality":[151],"guarantees":[152],"relative":[153],"those":[155],"obtained":[156],"offline.":[157],"challenge":[162],"by":[163],"designing":[164],"methods":[166,240],"online":[168,189,276],"measurements":[170],"stream;":[174],"adapt":[176],"testing":[179],"technique":[180],"examining":[182],"quantile-quantile":[184],"(q-q)":[185],"plot,":[186],"perform":[188],"validation":[191],"speeds.As":[194],"concrete":[196],"application":[197],"our":[199,217,239],"techniques,":[200],"focus":[202],"network":[204],"traffic":[205,226],"which":[207],"shown":[210],"exhibit":[212],"distributions.":[214],"complement":[216],"analytic":[218],"algorithmic":[220],"results":[221],"experiments":[223],"IP":[225,261],"in":[228,259],"AT&T's":[229],"Gigascope\u00ae":[230],"management":[233],"system,":[234],"demonstrate":[236,272],"practicality":[237],"line":[242],"speeds.":[243],"measured":[245],"robustness":[249],"these":[251],"over":[253],"weeks":[254],"operational":[256],"packet":[257],"network.":[262],"In":[263],"addition,":[264],"study":[266],"intrusion":[268],"detection":[269],"application,":[270],"parametric":[277],"modeling.":[278]},"counts_by_year":[{"year":2025,"cited_by_count":2},{"year":2023,"cited_by_count":2},{"year":2021,"cited_by_count":2},{"year":2018,"cited_by_count":1},{"year":2017,"cited_by_count":1},{"year":2015,"cited_by_count":4},{"year":2013,"cited_by_count":1},{"year":2012,"cited_by_count":4}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}