{"id":"https://openalex.org/W2504431993","doi":"https://doi.org/10.1145/2948068","title":"The Convergence Behavior of Naive Bayes on Large Sparse Datasets","display_name":"The Convergence Behavior of Naive Bayes on Large Sparse Datasets","publication_year":2016,"publication_date":"2016-07-20","ids":{"openalex":"https://openalex.org/W2504431993","doi":"https://doi.org/10.1145/2948068","mag":"2504431993"},"language":"en","primary_location":{"id":"doi:10.1145/2948068","is_oa":false,"landing_page_url":"https://doi.org/10.1145/2948068","pdf_url":null,"source":{"id":"https://openalex.org/S41523882","display_name":"ACM Transactions on Knowledge Discovery from Data","issn_l":"1556-4681","issn":["1556-4681","1556-472X"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319798","host_organization_name":"Association for Computing Machinery","host_organization_lineage":["https://openalex.org/P4310319798"],"host_organization_lineage_names":["Association for Computing Machinery"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ACM Transactions on Knowledge Discovery from Data","raw_type":"journal-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/A5100423209","display_name":"Xiang Li","orcid":"https://orcid.org/0000-0001-9595-8526"},"institutions":[{"id":"https://openalex.org/I125749732","display_name":"Western University","ror":"https://ror.org/02grkyz14","country_code":"CA","type":"education","lineage":["https://openalex.org/I125749732"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"Xiang Li","raw_affiliation_strings":["University of Western Ontario, Ontario, Canada"],"raw_orcid":"https://orcid.org/0000-0001-9595-8526","affiliations":[{"raw_affiliation_string":"University of Western Ontario, Ontario, Canada","institution_ids":["https://openalex.org/I125749732"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5027158588","display_name":"Charles X. Ling","orcid":"https://orcid.org/0000-0003-3797-1348"},"institutions":[{"id":"https://openalex.org/I125749732","display_name":"Western University","ror":"https://ror.org/02grkyz14","country_code":"CA","type":"education","lineage":["https://openalex.org/I125749732"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"Charles X. Ling","raw_affiliation_strings":["University of Western Ontario, Ontario, Canada"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Western Ontario, Ontario, Canada","institution_ids":["https://openalex.org/I125749732"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5076087924","display_name":"Huaimin Wang","orcid":"https://orcid.org/0000-0003-0376-640X"},"institutions":[{"id":"https://openalex.org/I170215575","display_name":"National University of Defense Technology","ror":"https://ror.org/05d2yfz11","country_code":"CN","type":"education","lineage":["https://openalex.org/I170215575"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Huaimin Wang","raw_affiliation_strings":["National University of Defense Technology, Changsha, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"National University of Defense Technology, Changsha, China","institution_ids":["https://openalex.org/I170215575"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":2.1655,"has_fulltext":false,"cited_by_count":18,"citation_normalized_percentile":{"value":0.90637575,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":98},"biblio":{"volume":"11","issue":"1","first_page":"1","last_page":"24"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11652","display_name":"Imbalanced Data Classification Techniques","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"}},"topics":[{"id":"https://openalex.org/T11652","display_name":"Imbalanced Data Classification Techniques","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"}},{"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"}},{"id":"https://openalex.org/T10057","display_name":"Face and Expression Recognition","score":0.9980999827384949,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/naive-bayes-classifier","display_name":"Naive Bayes classifier","score":0.6949045062065125},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6657743453979492},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.6300891637802124},{"id":"https://openalex.org/keywords/missing-data","display_name":"Missing data","score":0.5878476500511169},{"id":"https://openalex.org/keywords/bayes-theorem","display_name":"Bayes' theorem","score":0.575526237487793},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5304932594299316},{"id":"https://openalex.org/keywords/convergence","display_name":"Convergence (economics)","score":0.507344663143158},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.49934864044189453},{"id":"https://openalex.org/keywords/bayesian-probability","display_name":"Bayesian probability","score":0.2581685185432434},{"id":"https://openalex.org/keywords/support-vector-machine","display_name":"Support vector machine","score":0.1415765881538391}],"concepts":[{"id":"https://openalex.org/C52001869","wikidata":"https://www.wikidata.org/wiki/Q812530","display_name":"Naive Bayes classifier","level":3,"score":0.6949045062065125},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6657743453979492},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.6300891637802124},{"id":"https://openalex.org/C9357733","wikidata":"https://www.wikidata.org/wiki/Q6878417","display_name":"Missing data","level":2,"score":0.5878476500511169},{"id":"https://openalex.org/C207201462","wikidata":"https://www.wikidata.org/wiki/Q182505","display_name":"Bayes' theorem","level":3,"score":0.575526237487793},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5304932594299316},{"id":"https://openalex.org/C2777303404","wikidata":"https://www.wikidata.org/wiki/Q759757","display_name":"Convergence (economics)","level":2,"score":0.507344663143158},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.49934864044189453},{"id":"https://openalex.org/C107673813","wikidata":"https://www.wikidata.org/wiki/Q812534","display_name":"Bayesian probability","level":2,"score":0.2581685185432434},{"id":"https://openalex.org/C12267149","wikidata":"https://www.wikidata.org/wiki/Q282453","display_name":"Support vector machine","level":2,"score":0.1415765881538391},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0},{"id":"https://openalex.org/C50522688","wikidata":"https://www.wikidata.org/wiki/Q189833","display_name":"Economic growth","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/2948068","is_oa":false,"landing_page_url":"https://doi.org/10.1145/2948068","pdf_url":null,"source":{"id":"https://openalex.org/S41523882","display_name":"ACM Transactions on Knowledge Discovery from Data","issn_l":"1556-4681","issn":["1556-4681","1556-472X"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319798","host_organization_name":"Association for Computing Machinery","host_organization_lineage":["https://openalex.org/P4310319798"],"host_organization_lineage_names":["Association for Computing Machinery"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ACM Transactions on Knowledge Discovery from Data","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Peace, Justice and strong institutions","score":0.4699999988079071,"id":"https://metadata.un.org/sdg/16"}],"awards":[{"id":"https://openalex.org/G7430378521","display_name":null,"funder_award_id":"61432020 and 61472430","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"},{"id":"https://openalex.org/F4320334593","display_name":"Natural Sciences and Engineering Research Council of Canada","ror":"https://ror.org/01h531d29"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":53,"referenced_works":["https://openalex.org/W114517082","https://openalex.org/W118478992","https://openalex.org/W143080133","https://openalex.org/W168332103","https://openalex.org/W1538057645","https://openalex.org/W1619226191","https://openalex.org/W1832221731","https://openalex.org/W1849729440","https://openalex.org/W1964869462","https://openalex.org/W1992665562","https://openalex.org/W2002352636","https://openalex.org/W2016342346","https://openalex.org/W2018573356","https://openalex.org/W2027902860","https://openalex.org/W2032026767","https://openalex.org/W2044758663","https://openalex.org/W2054141820","https://openalex.org/W2085040216","https://openalex.org/W2100358124","https://openalex.org/W2101409192","https://openalex.org/W2106813372","https://openalex.org/W2120100126","https://openalex.org/W2125993116","https://openalex.org/W2131401323","https://openalex.org/W2135813353","https://openalex.org/W2137245235","https://openalex.org/W2140310134","https://openalex.org/W2140785063","https://openalex.org/W2148603752","https://openalex.org/W2155912844","https://openalex.org/W2156758690","https://openalex.org/W2157519573","https://openalex.org/W2157825442","https://openalex.org/W2158542502","https://openalex.org/W2163614729","https://openalex.org/W2165929987","https://openalex.org/W2169038197","https://openalex.org/W2170913656","https://openalex.org/W2200051882","https://openalex.org/W2241862190","https://openalex.org/W2245583245","https://openalex.org/W2303501228","https://openalex.org/W2341535507","https://openalex.org/W2560674852","https://openalex.org/W2626591897","https://openalex.org/W2791379569","https://openalex.org/W2949176378","https://openalex.org/W2951351492","https://openalex.org/W3125561743","https://openalex.org/W4206775476","https://openalex.org/W4230674625","https://openalex.org/W4292907422","https://openalex.org/W6677770173"],"related_works":["https://openalex.org/W4380150146","https://openalex.org/W3024870410","https://openalex.org/W2410652950","https://openalex.org/W4283773154","https://openalex.org/W3139174110","https://openalex.org/W1989494794","https://openalex.org/W2122031327","https://openalex.org/W1184238669","https://openalex.org/W2417174640","https://openalex.org/W3032901101"],"abstract_inverted_index":{"Large":[0],"and":[1,38,57,93,103,115,128,132,143,168,176],"sparse":[2,52,129,183],"datasets":[3,30,184],"with":[4,62],"a":[5,22,46,177],"lot":[6],"of":[7,25,65,75,88,96,146],"missing":[8,113],"values":[9],"are":[10,78],"common":[11,111],"in":[12,28,185],"the":[13,63,73,94,100,134],"big":[14],"data":[15,39,89,91,112,118,130],"era,":[16],"such":[17,29],"as":[18,54,171],"user":[19],"behaviors":[20],"over":[21],"large":[23,51,127,182],"number":[24,95],"items.":[26],"Classification":[27],"is":[31,44],"an":[32,172],"important":[33,70,154],"topic":[34],"for":[35,50,180],"machine":[36],"learning":[37,101,141],"mining.":[40],"Practically,":[41],"naive":[42,76,147],"Bayes":[43,77],"still":[45],"popular":[47],"classification":[48],"algorithm":[49],"datasets,":[53],"its":[55],"time":[56],"space":[58],"complexity":[59],"scales":[60],"linearly":[61],"size":[64],"non-missing":[66],"values.":[67],"However,":[68],"several":[69,110,153],"questions":[71],"about":[72],"behavior":[74,145],"yet":[79],"to":[80],"be":[81],"answered.":[82],"For":[83],"example,":[84],"how":[85],"different":[86],"mechanisms":[87,114],"missing,":[90],"sparsity,":[92],"attributes":[97],"systematically":[98],"affect":[99],"curves":[102],"convergence?":[104],"In":[105],"this":[106],"paper,":[107],"we":[108,164],"address":[109],"propose":[116],"novel":[117],"generation":[119],"methods":[120],"based":[121],"on":[122],"these":[123],"mechanisms.":[124],"We":[125,149],"generate":[126],"systematically,":[131],"study":[133],"entire":[135],"AUC":[136],"(Area":[137],"Under":[138],"ROC":[139],"Curve)":[140],"curve":[142],"convergence":[144],"Bayes.":[148],"not":[150],"only":[151],"have":[152],"experiment":[155],"observations,":[156],"but":[157],"also":[158],"provide":[159],"detailed":[160],"theoretic":[161,169],"studies.":[162],"Finally,":[163],"summarize":[165],"our":[166],"empirical":[167],"results":[170],"intuitive":[173],"decision":[174],"flowchart":[175],"useful":[178],"guideline":[179],"classifying":[181],"practice.":[186]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":2},{"year":2023,"cited_by_count":2},{"year":2022,"cited_by_count":1},{"year":2021,"cited_by_count":5},{"year":2020,"cited_by_count":2},{"year":2019,"cited_by_count":2},{"year":2018,"cited_by_count":1},{"year":2017,"cited_by_count":2}],"updated_date":"2026-05-21T06:26:12.895304","created_date":"2025-10-10T00:00:00"}