{"id":"https://openalex.org/W2014289389","doi":"https://doi.org/10.1145/1281192.1281263","title":"Making generative classifiers robust to selection bias","display_name":"Making generative classifiers robust to selection bias","publication_year":2007,"publication_date":"2007-08-12","ids":{"openalex":"https://openalex.org/W2014289389","doi":"https://doi.org/10.1145/1281192.1281263","mag":"2014289389"},"language":"en","primary_location":{"id":"doi:10.1145/1281192.1281263","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1281192.1281263","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 ACM SIGKDD international conference on Knowledge discovery and data mining","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/A5028522900","display_name":"Andrew T. Smith","orcid":"https://orcid.org/0000-0002-4751-6253"},"institutions":[{"id":"https://openalex.org/I36258959","display_name":"University of California San Diego","ror":"https://ror.org/0168r3w48","country_code":"US","type":"education","lineage":["https://openalex.org/I36258959"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Andrew T. Smith","raw_affiliation_strings":["University of California: San Diego","University of California, San Diego"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of California: San Diego","institution_ids":["https://openalex.org/I36258959"]},{"raw_affiliation_string":"University of California, San Diego","institution_ids":["https://openalex.org/I36258959"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5038246567","display_name":"Charles Elkan","orcid":null},"institutions":[{"id":"https://openalex.org/I36258959","display_name":"University of California San Diego","ror":"https://ror.org/0168r3w48","country_code":"US","type":"education","lineage":["https://openalex.org/I36258959"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Charles Elkan","raw_affiliation_strings":["University of California: San Diego","University of California, San Diego"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of California: San Diego","institution_ids":["https://openalex.org/I36258959"]},{"raw_affiliation_string":"University of California, San Diego","institution_ids":["https://openalex.org/I36258959"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I36258959"],"apc_list":null,"apc_paid":null,"fwci":1.527,"has_fulltext":false,"cited_by_count":29,"citation_normalized_percentile":{"value":0.82973199,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":97},"biblio":{"volume":null,"issue":null,"first_page":"657","last_page":"666"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11644","display_name":"Spam and Phishing Detection","score":0.9983000159263611,"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/T11644","display_name":"Spam and Phishing Detection","score":0.9983000159263611,"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/T12072","display_name":"Machine Learning and Algorithms","score":0.9976000189781189,"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/T11901","display_name":"Bayesian Methods and Mixture Models","score":0.9972000122070312,"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/missing-data","display_name":"Missing data","score":0.6304736137390137},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6298966407775879},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6124517917633057},{"id":"https://openalex.org/keywords/conditional-independence","display_name":"Conditional independence","score":0.5735727548599243},{"id":"https://openalex.org/keywords/classifier","display_name":"Classifier (UML)","score":0.5542751550674438},{"id":"https://openalex.org/keywords/filter","display_name":"Filter (signal processing)","score":0.5092569589614868},{"id":"https://openalex.org/keywords/labeled-data","display_name":"Labeled data","score":0.47679924964904785},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.47663769125938416},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.4747115671634674},{"id":"https://openalex.org/keywords/generative-model","display_name":"Generative model","score":0.4715302586555481},{"id":"https://openalex.org/keywords/generative-grammar","display_name":"Generative grammar","score":0.44697651267051697},{"id":"https://openalex.org/keywords/selection","display_name":"Selection (genetic algorithm)","score":0.4380807876586914},{"id":"https://openalex.org/keywords/independence","display_name":"Independence (probability theory)","score":0.414877325296402},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.3827079236507416},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.27965787053108215},{"id":"https://openalex.org/keywords/statistics","display_name":"Statistics","score":0.19237008690834045}],"concepts":[{"id":"https://openalex.org/C9357733","wikidata":"https://www.wikidata.org/wiki/Q6878417","display_name":"Missing data","level":2,"score":0.6304736137390137},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6298966407775879},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6124517917633057},{"id":"https://openalex.org/C79772020","wikidata":"https://www.wikidata.org/wiki/Q5159264","display_name":"Conditional independence","level":2,"score":0.5735727548599243},{"id":"https://openalex.org/C95623464","wikidata":"https://www.wikidata.org/wiki/Q1096149","display_name":"Classifier (UML)","level":2,"score":0.5542751550674438},{"id":"https://openalex.org/C106131492","wikidata":"https://www.wikidata.org/wiki/Q3072260","display_name":"Filter (signal processing)","level":2,"score":0.5092569589614868},{"id":"https://openalex.org/C2776145971","wikidata":"https://www.wikidata.org/wiki/Q30673951","display_name":"Labeled data","level":2,"score":0.47679924964904785},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.47663769125938416},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.4747115671634674},{"id":"https://openalex.org/C167966045","wikidata":"https://www.wikidata.org/wiki/Q5532625","display_name":"Generative model","level":3,"score":0.4715302586555481},{"id":"https://openalex.org/C39890363","wikidata":"https://www.wikidata.org/wiki/Q36108","display_name":"Generative grammar","level":2,"score":0.44697651267051697},{"id":"https://openalex.org/C81917197","wikidata":"https://www.wikidata.org/wiki/Q628760","display_name":"Selection (genetic algorithm)","level":2,"score":0.4380807876586914},{"id":"https://openalex.org/C35651441","wikidata":"https://www.wikidata.org/wiki/Q625303","display_name":"Independence (probability theory)","level":2,"score":0.414877325296402},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3827079236507416},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.27965787053108215},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.19237008690834045},{"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/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/1281192.1281263","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1281192.1281263","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 ACM SIGKDD international conference on Knowledge discovery and data mining","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":30,"referenced_works":["https://openalex.org/W1500567887","https://openalex.org/W1548614216","https://openalex.org/W1966026565","https://openalex.org/W2009187570","https://openalex.org/W2012942264","https://openalex.org/W2014703436","https://openalex.org/W2023320048","https://openalex.org/W2029283360","https://openalex.org/W2032536435","https://openalex.org/W2034368206","https://openalex.org/W2044758663","https://openalex.org/W2049633694","https://openalex.org/W2049878836","https://openalex.org/W2059575958","https://openalex.org/W2070533641","https://openalex.org/W2087018957","https://openalex.org/W2087967566","https://openalex.org/W2097079088","https://openalex.org/W2110575115","https://openalex.org/W2129851978","https://openalex.org/W2150291618","https://openalex.org/W2167328503","https://openalex.org/W2169075655","https://openalex.org/W2271858034","https://openalex.org/W2616141209","https://openalex.org/W2811380766","https://openalex.org/W2990138404","https://openalex.org/W3197494818","https://openalex.org/W6676840641","https://openalex.org/W6721667826"],"related_works":["https://openalex.org/W4365211920","https://openalex.org/W3014948380","https://openalex.org/W4380551139","https://openalex.org/W4317695495","https://openalex.org/W4287117424","https://openalex.org/W4387506531","https://openalex.org/W4238433571","https://openalex.org/W2967848559","https://openalex.org/W4299831724","https://openalex.org/W4283803360"],"abstract_inverted_index":{"This":[0],"paper":[1],"presents":[2],"approaches":[3,131],"to":[4,76,102,122,126,132,170,201,277,302],"semi-supervised":[5],"learning":[6,210,263,297],"when":[7],"the":[8,19,33,46,49,55,73,78,87,95,103,119,137,141,152,155,180,188,220,229,232,236,258,267],"labeled":[9,96,233],"training":[10],"data":[11,14,252,290],"and":[12,32,72,118,196,208,235,246],"test":[13,34],"are":[15,24,145,168,199,300],"differently":[16],"distributed.":[17],"Specifically,":[18],"samples":[20,38,63,97,144,234],"selected":[21,146],"for":[22,69,147],"labeling":[23,106,148,280],"a":[25,124,157,217,262],"biased":[26],"subset":[27],"of":[28,37,48,54,81,86,105,114,228,231,250],"some":[29],"general":[30,43],"distribution":[31,44,47],"set":[35,113],"consists":[36],"drawn":[39],"from":[40],"either":[41],"that":[42,143,299],"or":[45],"unlabeled":[50,112,237],"samples.":[51,238],"An":[52,84],"example":[53,85],"former":[56],"appears":[57,89],"in":[58,90,93,136,159,257,288],"loan":[59],"application":[60],"approval,":[61],"where":[62],"with":[64,225,254,284],"repay/default":[65,79],"labels":[66,167,198],"exist":[67],"only":[68,150],"approved":[70],"applicants":[71],"goal":[74,120],"is":[75,121,193,212],"model":[77,223,248],"behavior":[80],"all":[82],"applicants.":[83],"latter":[88],"spam":[91],"filtering,":[92],"which":[94,160],"can":[98,183,247],"be":[99,171,184,202],"out-dated":[100],"due":[101],"cost":[104],"email":[107],"by":[108],"hand,":[109],"but":[110],"an":[111],"up-to-date":[115],"emails":[116],"exists":[117],"build":[123],"filter":[125],"sort":[127],"new":[128],"incoming":[129],"email.Most":[130],"overcoming":[133],"such":[134],"bias":[135,182,256],"literature":[138],"rely":[139],"on":[140,151,266],"assumption":[142,192],"depending":[149],"features,":[153],"not":[154,194,204,274],"labels,":[156],"case":[158],"provably":[161,213],"correct":[162],"methods":[163,298],"exist.":[164],"The":[165,239],"missing":[166,197],"said":[169,200],"\"missing":[172,203],"at":[173,205],"random\"":[174,206],"(MAR).":[175],"In":[176],"real":[177],"applications,":[178],"however,":[179],"selection":[181],"more":[185],"severe.":[186],"When":[187],"MAR":[189,304],"conditional":[190,243],"independence":[191,244],"satisfied":[195],"(MNAR),":[207],"no":[209,242],"method":[211,264],"always":[214,275],"correct.We":[215],"present":[216,261],"generative":[218],"classifier,":[219],"shifted":[221],"mixture":[222],"(SMM),":[224],"separate":[226],"representations":[227],"distributions":[230,249],"SMM":[240],"makes":[241],"assumptions":[245],"semi-labeled":[251],"sets":[253,291],"arbitrary":[255,279],"labeling.":[259],"We":[260],"based":[265],"expectation":[268],"maximization":[269],"(EM)":[270],"algorithm":[271],"that,":[272],"while":[273],"able":[276],"overcome":[278,303],"bias,":[281],"learns":[282],"SMMs":[283],"higher":[285],"test-set":[286],"accuracy":[287],"real-world":[289],"(with":[292],"MNAR":[293],"bias)":[294],"than":[295],"existing":[296],"proven":[301],"bias.":[305]},"counts_by_year":[{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":1},{"year":2022,"cited_by_count":2},{"year":2020,"cited_by_count":2},{"year":2019,"cited_by_count":2},{"year":2018,"cited_by_count":1},{"year":2017,"cited_by_count":1},{"year":2016,"cited_by_count":1},{"year":2015,"cited_by_count":2},{"year":2014,"cited_by_count":2},{"year":2013,"cited_by_count":3},{"year":2012,"cited_by_count":1}],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}