{"id":"https://openalex.org/W2009429432","doi":"https://doi.org/10.1145/1401890.1401968","title":"Semi-supervised approach to rapid and reliable labeling of large data sets","display_name":"Semi-supervised approach to rapid and reliable labeling of large data sets","publication_year":2008,"publication_date":"2008-08-24","ids":{"openalex":"https://openalex.org/W2009429432","doi":"https://doi.org/10.1145/1401890.1401968","mag":"2009429432"},"language":"en","primary_location":{"id":"doi:10.1145/1401890.1401968","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1401890.1401968","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 14th ACM SIGKDD international conference on Knowledge discovery and data mining","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/A5050008389","display_name":"Gy\u00f6rgy Simon","orcid":"https://orcid.org/0000-0003-4715-5934"},"institutions":[{"id":"https://openalex.org/I130238516","display_name":"University of Minnesota","ror":"https://ror.org/017zqws13","country_code":"US","type":"education","lineage":["https://openalex.org/I130238516"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Gy\u00f6rgy J. Simon","raw_affiliation_strings":["University of Minnesota, Minneapolis, MN, USA",", University of Minnesota, Minneapolis, MN, USA"],"affiliations":[{"raw_affiliation_string":"University of Minnesota, Minneapolis, MN, USA","institution_ids":["https://openalex.org/I130238516"]},{"raw_affiliation_string":", University of Minnesota, Minneapolis, MN, USA","institution_ids":["https://openalex.org/I130238516"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100645812","display_name":"Vipin Kumar","orcid":"https://orcid.org/0000-0002-9040-2665"},"institutions":[{"id":"https://openalex.org/I130238516","display_name":"University of Minnesota","ror":"https://ror.org/017zqws13","country_code":"US","type":"education","lineage":["https://openalex.org/I130238516"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Vipin Kumar","raw_affiliation_strings":["University of Minnesota, Minneapolis, MN, USA",", University of Minnesota, Minneapolis, MN, USA"],"affiliations":[{"raw_affiliation_string":"University of Minnesota, Minneapolis, MN, USA","institution_ids":["https://openalex.org/I130238516"]},{"raw_affiliation_string":", University of Minnesota, Minneapolis, MN, USA","institution_ids":["https://openalex.org/I130238516"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100622097","display_name":"Zhi-Li Zhang","orcid":"https://orcid.org/0000-0001-8584-2319"},"institutions":[{"id":"https://openalex.org/I130238516","display_name":"University of Minnesota","ror":"https://ror.org/017zqws13","country_code":"US","type":"education","lineage":["https://openalex.org/I130238516"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Zhi-Li Zhang","raw_affiliation_strings":["University of Minnesota, Minneapolis, MN, USA",", University of Minnesota, Minneapolis, MN, USA"],"affiliations":[{"raw_affiliation_string":"University of Minnesota, Minneapolis, MN, USA","institution_ids":["https://openalex.org/I130238516"]},{"raw_affiliation_string":", University of Minnesota, Minneapolis, MN, USA","institution_ids":["https://openalex.org/I130238516"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5050008389"],"corresponding_institution_ids":["https://openalex.org/I130238516"],"apc_list":null,"apc_paid":null,"fwci":1.724,"has_fulltext":false,"cited_by_count":3,"citation_normalized_percentile":{"value":0.86979882,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"641","last_page":"649"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12072","display_name":"Machine Learning and Algorithms","score":0.9994000196456909,"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"}},"topics":[{"id":"https://openalex.org/T12072","display_name":"Machine Learning and Algorithms","score":0.9994000196456909,"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/T11512","display_name":"Anomaly Detection Techniques and Applications","score":0.9988999962806702,"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/T12535","display_name":"Machine Learning and Data Classification","score":0.9987999796867371,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/heuristics","display_name":"Heuristics","score":0.8550989031791687},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.796940803527832},{"id":"https://openalex.org/keywords/class","display_name":"Class (philosophy)","score":0.6456661820411682},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.6040360927581787},{"id":"https://openalex.org/keywords/exploit","display_name":"Exploit","score":0.5862663388252258},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.5849573612213135},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.532114565372467},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.512493371963501},{"id":"https://openalex.org/keywords/data-set","display_name":"Data set","score":0.42308157682418823}],"concepts":[{"id":"https://openalex.org/C127705205","wikidata":"https://www.wikidata.org/wiki/Q5748245","display_name":"Heuristics","level":2,"score":0.8550989031791687},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.796940803527832},{"id":"https://openalex.org/C2777212361","wikidata":"https://www.wikidata.org/wiki/Q5127848","display_name":"Class (philosophy)","level":2,"score":0.6456661820411682},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.6040360927581787},{"id":"https://openalex.org/C165696696","wikidata":"https://www.wikidata.org/wiki/Q11287","display_name":"Exploit","level":2,"score":0.5862663388252258},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.5849573612213135},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.532114565372467},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.512493371963501},{"id":"https://openalex.org/C58489278","wikidata":"https://www.wikidata.org/wiki/Q1172284","display_name":"Data set","level":2,"score":0.42308157682418823},{"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/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","level":1,"score":0.0},{"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:10.1145/1401890.1401968","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1401890.1401968","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 14th ACM SIGKDD international conference on Knowledge discovery and data mining","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Partnerships for the goals","id":"https://metadata.un.org/sdg/17","score":0.4099999964237213}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":46,"referenced_works":["https://openalex.org/W76089463","https://openalex.org/W92894758","https://openalex.org/W1479807131","https://openalex.org/W1521150922","https://openalex.org/W1521553548","https://openalex.org/W1528361845","https://openalex.org/W1565377632","https://openalex.org/W1574877594","https://openalex.org/W1585385982","https://openalex.org/W1586759373","https://openalex.org/W1630959083","https://openalex.org/W1651093245","https://openalex.org/W1966949944","https://openalex.org/W1979675141","https://openalex.org/W1997029057","https://openalex.org/W1998565453","https://openalex.org/W2037603696","https://openalex.org/W2041453110","https://openalex.org/W2048679005","https://openalex.org/W2051645349","https://openalex.org/W2061526129","https://openalex.org/W2080021732","https://openalex.org/W2093717447","https://openalex.org/W2093825590","https://openalex.org/W2097089247","https://openalex.org/W2106578604","https://openalex.org/W2107008379","https://openalex.org/W2107968230","https://openalex.org/W2111145173","https://openalex.org/W2122837498","https://openalex.org/W2128097790","https://openalex.org/W2128614648","https://openalex.org/W2130598205","https://openalex.org/W2140535827","https://openalex.org/W2144098589","https://openalex.org/W2144372981","https://openalex.org/W2149950545","https://openalex.org/W2150884987","https://openalex.org/W2162243185","https://openalex.org/W2167917621","https://openalex.org/W2401715402","https://openalex.org/W2595840341","https://openalex.org/W2912934387","https://openalex.org/W4234632609","https://openalex.org/W6637231022","https://openalex.org/W6992441829"],"related_works":["https://openalex.org/W17155033","https://openalex.org/W3207760230","https://openalex.org/W1496222301","https://openalex.org/W4312814274","https://openalex.org/W1590307681","https://openalex.org/W2536018345","https://openalex.org/W4285370786","https://openalex.org/W2296488620","https://openalex.org/W2358353312","https://openalex.org/W2353836703"],"abstract_inverted_index":{"In":[0,30],"this":[1],"paper,":[2],"we":[3,33,39,86,206,239],"propose":[4],"a":[5,18,97,216,255,269],"method,":[6],"where":[7],"the":[8,11,25,28,72,103,108,112,114,117,121,127,132,135,143,158,173,179,181,189,193,196,212,226,234,250,264],"labeling":[9,247],"of":[10,27,45,50,71,102,111,134,175,183,192,211,219,249,258],"data":[12,136,201],"set":[13,137,202],"is":[14,92,105,153,160,170],"carried":[15],"out":[16],"in":[17],"semi-supervised":[19],"manner":[20],"with":[21,138,145],"user-specified":[22],"guarantees":[23],"about":[24],"quality":[26,191],"labeling.":[29,194],"our":[31,260],"scheme,":[32],"assume":[34,84],"that":[35,85],"for":[36],"each":[37,44,148],"class,":[38],"have":[40,59,87],"some":[41,164],"heuristics":[42,55,119],"available,":[43],"which":[46],"can":[47],"identify":[48],"instances":[49,70,133,165,176,185,213],"one":[51],"particular":[52],"class.":[53,149],"The":[54,100,150,168],"are":[56],"assumed":[57],"to":[58,67,78,94,106,129,147,162,208,241,262],"reasonable":[60],"performance":[61],"but":[62],"they":[63,76],"do":[64,75],"not":[65,154],"need":[66,77],"cover":[68],"all":[69],"class":[73],"nor":[74],"be":[79],"perfectly":[80],"reliable.":[81],"We":[82,252],"further":[83],"an":[88],"infallible":[89],"expert,":[90,180],"who":[91],"willing":[93],"manually":[95],"label":[96,209,228,236,263],"few":[98],"instances.":[99],"aim":[101],"algorithm":[104,159,169],"exploit":[107],"cluster":[109],"structure":[110],"problem,":[113],"predictions":[115],"by":[116,126,142,172,178,224,232],"imperfect":[118],"and":[120,188,231],"limited":[122],"perfect":[123],"labels":[124],"provided":[125],"expert":[128,227,235],"classify":[130,163],"(label)":[131],"guaranteed":[139],"precision":[140,152,218,245],"(specificed":[141],"user)":[144],"regards":[146],"specified":[151],"always":[155],"attainable,":[156],"so":[157],"allowed":[161],"as":[166],"dontknow.":[167],"evaluated":[171],"number":[174,182],"labeled":[177],"dontknow":[184],"(global":[186],"coverage)":[187],"achieved":[190],"On":[195],"KDD":[197],"Cup":[198],"Network":[199],"Intrusion":[200],"containing":[203],"500,000":[204],"instances,":[205,238],"managed":[207,240],"96.6%":[210],"while":[214,246],"guaranteeing":[215],"nominal":[217,244],"90%":[220],"(with":[221],"95%":[222,243],"confidence)":[223],"having":[225,233],"630":[229],"instances;":[230],"1200":[237],"guarantee":[242],"96.4%":[248],"data.":[251],"also":[253],"provide":[254],"case":[256],"study":[257],"applying":[259],"scheme":[261],"network":[265],"traffic":[266],"collected":[267],"at":[268],"large":[270],"campus":[271],"network.":[272]},"counts_by_year":[],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}