{"id":"https://openalex.org/W7204153892","doi":"https://doi.org/10.48550/arxiv.2608.22843","title":"Favourable Missingness in Semi-Supervised Classification for Exponential Mixture Models","display_name":"Favourable Missingness in Semi-Supervised Classification for Exponential Mixture Models","publication_year":2026,"publication_date":"2026-08-24","ids":{"openalex":"https://openalex.org/W7204153892","doi":"https://doi.org/10.48550/arxiv.2608.22843"},"language":"en","primary_location":{"id":"pmh:oai:arXiv.org:2608.22843","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2608.22843","pdf_url":"https://arxiv.org/pdf/2608.22843","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by-sa","license_id":"https://openalex.org/licenses/cc-by-sa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"volume":null,"type":"preprint","indexed_in":["arxiv","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2608.22843","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5042071344","display_name":"Huanchao Zhou","orcid":"https://orcid.org/0009-0006-0285-8213","observed_orcids":["https://orcid.org/0009-0006-0285-8213"]},"institutions":[{"id":"https://openalex.org/I4610292","display_name":"Xiangtan University","ror":"https://ror.org/00xsfaz62","country_code":"CN","type":"education","lineage":["https://openalex.org/I4610292"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhou, Huanchao","raw_affiliation_strings":["School of Mathematics and Computational Science , Xiangtan University , China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Mathematics and Computational Science , Xiangtan University , China","institution_ids":["https://openalex.org/I4610292"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5044575556","display_name":"Jinran Wu","orcid":"https://orcid.org/0000-0002-2388-3614","observed_orcids":["https://orcid.org/0000-0002-2388-3614"]},"institutions":[{"id":"https://openalex.org/I160993911","display_name":"Queensland University of Technology","ror":"https://ror.org/03pnv4752","country_code":"AU","type":"education","lineage":["https://openalex.org/I160993911"]},{"id":"https://openalex.org/I165143802","display_name":"The University of Queensland","ror":"https://ror.org/00rqy9422","country_code":"AU","type":"education","lineage":["https://openalex.org/I165143802"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Wu, Jinran","raw_affiliation_strings":["School of Mathematics and Physics , The University of Queensland , Australia"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Mathematics and Physics , The University of Queensland , Australia","institution_ids":["https://openalex.org/I160993911","https://openalex.org/I165143802"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5148072214","display_name":"Fariborz Setoudehtazang","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Setoudehtazang, Fariborz","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5057375178","display_name":"Geoffrey John McLachlan","orcid":"https://orcid.org/0000-0002-5921-3145","observed_orcids":["https://orcid.org/0000-0002-5921-3145"]},"institutions":[{"id":"https://openalex.org/I160993911","display_name":"Queensland University of Technology","ror":"https://ror.org/03pnv4752","country_code":"AU","type":"education","lineage":["https://openalex.org/I160993911"]},{"id":"https://openalex.org/I165143802","display_name":"The University of Queensland","ror":"https://ror.org/00rqy9422","country_code":"AU","type":"education","lineage":["https://openalex.org/I165143802"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"McLachlan, Geoffrey J.","raw_affiliation_strings":["School of Mathematics and Physics , The University of Queensland , Australia"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Mathematics and Physics , The University of Queensland , Australia","institution_ids":["https://openalex.org/I160993911","https://openalex.org/I165143802"]}]}],"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":true,"cited_by_count":0,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11901","display_name":"Bayesian Methods and Mixture Models","score":0.9916999936103821,"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/T11901","display_name":"Bayesian Methods and Mixture Models","score":0.9916999936103821,"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":0.003100000089034438,"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/T12072","display_name":"Machine Learning and Algorithms","score":0.0008999999845400453,"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/semi-supervised-classification","display_name":"semi-supervised classification","score":0.9860000014305115},{"id":"https://openalex.org/keywords/fisher-information","display_name":"Fisher information","score":0.5529999732971191},{"id":"https://openalex.org/keywords/information-decomposition","display_name":"information decomposition","score":0.6340000033378601},{"id":"https://openalex.org/keywords/asymptotic-relative-efficiency","display_name":"asymptotic relative efficiency","score":0.7200000286102295}],"concepts":[{"id":"https://openalex.org/C9357733","wikidata":"https://www.wikidata.org/wiki/Q6878417","display_name":"Missing data","level":2,"score":0.7692000269889832},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.7221999764442444},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.5544000267982483},{"id":"https://openalex.org/C55974624","wikidata":"https://www.wikidata.org/wiki/Q1188504","display_name":"Exponential family","level":2,"score":0.5019999742507935},{"id":"https://openalex.org/C29406490","wikidata":"https://www.wikidata.org/wiki/Q1420659","display_name":"Fisher information","level":2,"score":0.477400004863739},{"id":"https://openalex.org/C2908647359","wikidata":"https://www.wikidata.org/wiki/Q2625603","display_name":"Population","level":2,"score":0.4700999855995178},{"id":"https://openalex.org/C151376022","wikidata":"https://www.wikidata.org/wiki/Q168698","display_name":"Exponential function","level":2,"score":0.4571000039577484},{"id":"https://openalex.org/C207201462","wikidata":"https://www.wikidata.org/wiki/Q182505","display_name":"Bayes' theorem","level":3,"score":0.4345000088214874},{"id":"https://openalex.org/C19499675","wikidata":"https://www.wikidata.org/wiki/Q232207","display_name":"Monte Carlo method","level":2,"score":0.42149999737739563},{"id":"https://openalex.org/C28826006","wikidata":"https://www.wikidata.org/wiki/Q33521","display_name":"Applied mathematics","level":1,"score":0.39010000228881836},{"id":"https://openalex.org/C61224824","wikidata":"https://www.wikidata.org/wiki/Q2260434","display_name":"Mixture model","level":2,"score":0.38499999046325684},{"id":"https://openalex.org/C79772020","wikidata":"https://www.wikidata.org/wiki/Q5159264","display_name":"Conditional independence","level":2,"score":0.3490999937057495},{"id":"https://openalex.org/C104317236","wikidata":"https://www.wikidata.org/wiki/Q4330126","display_name":"Classification rule","level":2,"score":0.3409000039100647},{"id":"https://openalex.org/C2777212361","wikidata":"https://www.wikidata.org/wiki/Q5127848","display_name":"Class (philosophy)","level":2,"score":0.33709999918937683},{"id":"https://openalex.org/C2776709221","wikidata":"https://www.wikidata.org/wiki/Q6031040","display_name":"Information Criteria","level":3,"score":0.33079999685287476},{"id":"https://openalex.org/C95623464","wikidata":"https://www.wikidata.org/wiki/Q1096149","display_name":"Classifier (UML)","level":2,"score":0.3172000050544739},{"id":"https://openalex.org/C182081679","wikidata":"https://www.wikidata.org/wiki/Q1275153","display_name":"Expectation\u2013maximization algorithm","level":3,"score":0.3138999938964844},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.3043000102043152},{"id":"https://openalex.org/C55350006","wikidata":"https://www.wikidata.org/wiki/Q237193","display_name":"Exponential distribution","level":2,"score":0.2971000075340271},{"id":"https://openalex.org/C83282275","wikidata":"https://www.wikidata.org/wiki/Q7435350","display_name":"Scoring algorithm","level":2,"score":0.2775999903678894},{"id":"https://openalex.org/C40696583","wikidata":"https://www.wikidata.org/wiki/Q989120","display_name":"Type I and type II errors","level":2,"score":0.2775000035762787},{"id":"https://openalex.org/C114289077","wikidata":"https://www.wikidata.org/wiki/Q3284399","display_name":"Statistical model","level":2,"score":0.27390000224113464},{"id":"https://openalex.org/C57830394","wikidata":"https://www.wikidata.org/wiki/Q278079","display_name":"Posterior probability","level":3,"score":0.26489999890327454},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.2605000138282776},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.25870001316070557}],"mesh":[],"locations_count":2,"locations":[{"id":"pmh:oai:arXiv.org:2608.22843","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2608.22843","pdf_url":"https://arxiv.org/pdf/2608.22843","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by-sa","license_id":"https://openalex.org/licenses/cc-by-sa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"doi:10.48550/arxiv.2608.22843","doi":"https://doi.org/10.48550/arxiv.2608.22843","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2608.22843","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2608.22843","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2608.22843","pdf_url":"https://arxiv.org/pdf/2608.22843","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by-sa","license_id":"https://openalex.org/licenses/cc-by-sa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[],"study_designs":[],"awards":[{"id":"https://openalex.org/G2676022535","display_name":null,"funder_award_id":"2025M783140","funder_id":"https://openalex.org/F4320321543","funder_display_name":"China Postdoctoral Science Foundation"},{"id":"https://openalex.org/G6179874790","display_name":"A Novel Approach to Semi-Supervised Statistical Machine Learning","funder_award_id":"DP230101671","funder_id":"https://openalex.org/F4320334704","funder_display_name":"Australian Research Council"}],"funders":[{"id":"https://openalex.org/F4320321543","display_name":"China Postdoctoral Science Foundation","ror":"https://ror.org/0426zh255"},{"id":"https://openalex.org/F4320334704","display_name":"Australian Research Council","ror":"https://ror.org/05mmh0f86"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W7204153892.pdf","grobid_xml":"https://content.openalex.org/works/W7204153892.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W7206195559","https://openalex.org/W7204274953","https://openalex.org/W2980711498","https://openalex.org/W3083444919","https://openalex.org/W7214067365","https://openalex.org/W4417086700","https://openalex.org/W4391718654","https://openalex.org/W2936210142","https://openalex.org/W4417028081","https://openalex.org/W3017025251"],"abstract_inverted_index":{"Semi-supervised":[0],"classifiers":[1],"are":[2,11,17],"commonly":[3],"trained":[4],"from":[5,198],"samples":[6,188],"in":[7,45,110,168],"which":[8,46,169,207],"all":[9],"features":[10],"observed":[12,26,60],"but":[13],"some":[14],"class":[15,29],"labels":[16],"missing.":[18],"When":[19],"label":[20,50],"missingness":[21,51,126],"is":[22,96],"independent":[23],"of":[24,49,79,140],"the":[25,47,59,68,74,93,102,111,130,141,145,148,157,161,170,191,195,199,204,208],"data,":[27],"unavailable":[28],"memberships":[30],"reduce":[31],"Fisher":[32,142],"information":[33,66,77,143,158],"relative":[34,176,209],"to":[35,153],"a":[36,42,88,138],"completely":[37],"classified":[38,133],"sample.":[39],"We":[40,113,135],"study":[41],"different":[43],"regime":[44],"probability":[48],"depends":[52],"on":[53,73,101],"posterior":[54],"classification":[55],"uncertainty,":[56],"so":[57],"that":[58],"missing-label":[61],"indicators":[62],"can":[63],"themselves":[64],"carry":[65],"about":[67],"Bayes":[69],"decision":[70],"boundary.":[71],"Building":[72],"conditionally":[75,149],"weighted":[76,150],"decomposition":[78,139],"Ahfock":[80],"and":[81,99,117,124,128,156],"McLachlan,":[82],"we":[83],"develop":[84],"this":[85],"phenomenon":[86],"for":[87],"two-component":[89],"exponential":[90,94],"mixture.":[91],"Although":[92],"model":[95],"non-Gaussian,":[97],"asymmetric,":[98],"supported":[100],"positive":[103],"half-line,":[104],"its":[105,118],"log-posterior":[106],"odds":[107],"remain":[108],"linear":[109],"feature.":[112],"derive":[114,137],"Bayes'":[115],"rule":[116],"exact":[119],"error":[120],"rate,":[121],"formulate":[122],"entropy-logistic":[123],"squared-discriminant":[125],"mechanisms,":[127],"obtain":[129],"full":[131,171],"partially":[132],"likelihood.":[134],"then":[136],"into":[144],"complete-data":[146],"information,":[147],"loss":[151],"due":[152],"missing":[154,162],"labels,":[155],"contributed":[159],"by":[160],"labels.":[163],"Numerical":[164],"quadrature":[165],"identifies":[166],"regions":[167],"likelihood":[172],"classifier":[173],"has":[174],"asymptotic":[175,200],"efficiency":[177,210],"above":[178],"or":[179],"below":[180],"one.":[181,212],"Monte":[182],"Carlo":[183],"experiments":[184],"with":[185,194],"finite":[186],"training":[187],"broadly":[189],"support":[190],"population":[192],"calculations,":[193],"largest":[196],"departures":[197],"predictions":[201],"occurring":[202],"near":[203],"transition":[205],"at":[206],"crosses":[211]},"counts_by_year":[],"updated_date":"2026-10-28T10:33:24.094632","created_date":"2026-08-26T00:00:00"}