{"id":"https://openalex.org/W4385568174","doi":"https://doi.org/10.1145/3580305.3599456","title":"Open-Set Semi-Supervised Text Classification with Latent Outlier Softening","display_name":"Open-Set Semi-Supervised Text Classification with Latent Outlier Softening","publication_year":2023,"publication_date":"2023-08-04","ids":{"openalex":"https://openalex.org/W4385568174","doi":"https://doi.org/10.1145/3580305.3599456"},"language":"en","primary_location":{"id":"doi:10.1145/3580305.3599456","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3580305.3599456","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 29th ACM SIGKDD 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/A5006061735","display_name":"Junfan Chen","orcid":"https://orcid.org/0000-0001-6807-0089"},"institutions":[{"id":"https://openalex.org/I82880672","display_name":"Beihang University","ror":"https://ror.org/00wk2mp56","country_code":"CN","type":"education","lineage":["https://openalex.org/I82880672"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Junfan Chen","raw_affiliation_strings":["Beihang University, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0001-6807-0089","affiliations":[{"raw_affiliation_string":"Beihang University, Beijing, China","institution_ids":["https://openalex.org/I82880672"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5027015677","display_name":"Richong Zhang","orcid":"https://orcid.org/0000-0002-1207-0300"},"institutions":[{"id":"https://openalex.org/I82880672","display_name":"Beihang University","ror":"https://ror.org/00wk2mp56","country_code":"CN","type":"education","lineage":["https://openalex.org/I82880672"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Richong Zhang","raw_affiliation_strings":["Beihang University, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0002-1207-0300","affiliations":[{"raw_affiliation_string":"Beihang University, Beijing, China","institution_ids":["https://openalex.org/I82880672"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5103201812","display_name":"Junchi Chen","orcid":"https://orcid.org/0000-0002-6375-9490"},"institutions":[{"id":"https://openalex.org/I82880672","display_name":"Beihang University","ror":"https://ror.org/00wk2mp56","country_code":"CN","type":"education","lineage":["https://openalex.org/I82880672"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Junchi Chen","raw_affiliation_strings":["Beihang University, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0002-6375-9490","affiliations":[{"raw_affiliation_string":"Beihang University, Beijing, China","institution_ids":["https://openalex.org/I82880672"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5086470621","display_name":"Chunming Hu","orcid":"https://orcid.org/0000-0002-9502-3955"},"institutions":[{"id":"https://openalex.org/I82880672","display_name":"Beihang University","ror":"https://ror.org/00wk2mp56","country_code":"CN","type":"education","lineage":["https://openalex.org/I82880672"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Chunming Hu","raw_affiliation_strings":["Beihang University, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0002-9502-3955","affiliations":[{"raw_affiliation_string":"Beihang University, Beijing, China","institution_ids":["https://openalex.org/I82880672"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5004793184","display_name":"Yongyi Mao","orcid":"https://orcid.org/0000-0001-5298-5778"},"institutions":[{"id":"https://openalex.org/I153718931","display_name":"University of Ottawa","ror":"https://ror.org/03c4mmv16","country_code":"CA","type":"education","lineage":["https://openalex.org/I153718931"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"Yongyi Mao","raw_affiliation_strings":["University of Ottawa, Ottawa, Canada"],"raw_orcid":"https://orcid.org/0000-0001-5298-5778","affiliations":[{"raw_affiliation_string":"University of Ottawa, Ottawa, Canada","institution_ids":["https://openalex.org/I153718931"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":4,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"226","last_page":"236"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11512","display_name":"Anomaly Detection Techniques and Applications","score":0.9939000010490417,"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/T11512","display_name":"Anomaly Detection Techniques and Applications","score":0.9939000010490417,"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/T10028","display_name":"Topic Modeling","score":0.9883000254631042,"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/T11550","display_name":"Text and Document Classification Technologies","score":0.9815999865531921,"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/anomaly-detection","display_name":"Anomaly detection","score":0.7007936239242554},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6922083497047424},{"id":"https://openalex.org/keywords/outlier","display_name":"Outlier","score":0.6539911031723022},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6375060677528381},{"id":"https://openalex.org/keywords/expectation\u2013maximization-algorithm","display_name":"Expectation\u2013maximization algorithm","score":0.5966780185699463},{"id":"https://openalex.org/keywords/principle-of-maximum-entropy","display_name":"Principle of maximum entropy","score":0.5655848383903503},{"id":"https://openalex.org/keywords/latent-variable","display_name":"Latent variable","score":0.5501376986503601},{"id":"https://openalex.org/keywords/inference","display_name":"Inference","score":0.5393071174621582},{"id":"https://openalex.org/keywords/probabilistic-logic","display_name":"Probabilistic logic","score":0.5032927393913269},{"id":"https://openalex.org/keywords/entropy-maximization","display_name":"Entropy maximization","score":0.47320717573165894},{"id":"https://openalex.org/keywords/maximization","display_name":"Maximization","score":0.45844176411628723},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.44853267073631287},{"id":"https://openalex.org/keywords/entropy","display_name":"Entropy (arrow of time)","score":0.4323880076408386},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.36448991298675537},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.3526690900325775},{"id":"https://openalex.org/keywords/maximum-likelihood","display_name":"Maximum likelihood","score":0.19523438811302185},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.15167051553726196},{"id":"https://openalex.org/keywords/statistics","display_name":"Statistics","score":0.08989796042442322}],"concepts":[{"id":"https://openalex.org/C739882","wikidata":"https://www.wikidata.org/wiki/Q3560506","display_name":"Anomaly detection","level":2,"score":0.7007936239242554},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6922083497047424},{"id":"https://openalex.org/C79337645","wikidata":"https://www.wikidata.org/wiki/Q779824","display_name":"Outlier","level":2,"score":0.6539911031723022},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6375060677528381},{"id":"https://openalex.org/C182081679","wikidata":"https://www.wikidata.org/wiki/Q1275153","display_name":"Expectation\u2013maximization algorithm","level":3,"score":0.5966780185699463},{"id":"https://openalex.org/C9679016","wikidata":"https://www.wikidata.org/wiki/Q1417473","display_name":"Principle of maximum entropy","level":2,"score":0.5655848383903503},{"id":"https://openalex.org/C51167844","wikidata":"https://www.wikidata.org/wiki/Q4422623","display_name":"Latent variable","level":2,"score":0.5501376986503601},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.5393071174621582},{"id":"https://openalex.org/C49937458","wikidata":"https://www.wikidata.org/wiki/Q2599292","display_name":"Probabilistic logic","level":2,"score":0.5032927393913269},{"id":"https://openalex.org/C127233936","wikidata":"https://www.wikidata.org/wiki/Q1417473","display_name":"Entropy maximization","level":3,"score":0.47320717573165894},{"id":"https://openalex.org/C2776330181","wikidata":"https://www.wikidata.org/wiki/Q18358244","display_name":"Maximization","level":2,"score":0.45844176411628723},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.44853267073631287},{"id":"https://openalex.org/C106301342","wikidata":"https://www.wikidata.org/wiki/Q4117933","display_name":"Entropy (arrow of time)","level":2,"score":0.4323880076408386},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.36448991298675537},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3526690900325775},{"id":"https://openalex.org/C49781872","wikidata":"https://www.wikidata.org/wiki/Q1045555","display_name":"Maximum likelihood","level":2,"score":0.19523438811302185},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.15167051553726196},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.08989796042442322},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3580305.3599456","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3580305.3599456","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 29th ACM SIGKDD Conference on Knowledge Discovery and Data Mining","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education","score":0.6499999761581421}],"awards":[],"funders":[{"id":"https://openalex.org/F4320326978","display_name":"State Key Laboratory of Software Development Environment","ror":null},{"id":"https://openalex.org/F4320335787","display_name":"Fundamental Research Funds for the Central Universities","ror":null}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":20,"referenced_works":["https://openalex.org/W2108281845","https://openalex.org/W2890931111","https://openalex.org/W2950886580","https://openalex.org/W2951519300","https://openalex.org/W2952696830","https://openalex.org/W2970421890","https://openalex.org/W3035451444","https://openalex.org/W3035542229","https://openalex.org/W3101606352","https://openalex.org/W3174231090","https://openalex.org/W3176015769","https://openalex.org/W3176382883","https://openalex.org/W3191916981","https://openalex.org/W3209230846","https://openalex.org/W4225107720","https://openalex.org/W4283800530","https://openalex.org/W4284680079","https://openalex.org/W4285128732","https://openalex.org/W4312634400","https://openalex.org/W4312896184"],"related_works":["https://openalex.org/W3102188974","https://openalex.org/W2147030611","https://openalex.org/W2025228226","https://openalex.org/W2020801733","https://openalex.org/W2033415512","https://openalex.org/W2143074727","https://openalex.org/W2350826920","https://openalex.org/W2251843845","https://openalex.org/W2171665021","https://openalex.org/W2060670312"],"abstract_inverted_index":{"Semi-supervised":[0,34],"text":[1],"classification":[2],"(STC)":[3],"has":[4],"been":[5],"extensively":[6],"researched":[7],"and":[8,101,119],"reduces":[9],"human":[10],"annotation.":[11],"However,":[12],"existing":[13],"research":[14],"assuming":[15],"that":[16,41,97,129],"unlabeled":[17,43],"data":[18,44],"only":[19],"contains":[20,45],"in-distribution":[21],"texts":[22,65],"is":[23,54],"unrealistic.":[24],"This":[25],"paper":[26],"extends":[27],"STC":[28],"to":[29],"a":[30,85,91],"more":[31],"practical":[32],"Open-set":[33],"Text":[35],"Classification":[36],"(OSTC)":[37],"setting,":[38],"which":[39],"assumes":[40],"the":[42,55,70,111,115],"out-of-distribution":[46],"(OOD)":[47],"texts.":[48],"The":[49],"main":[50],"challenge":[51],"in":[52,84],"OSTC":[53],"false":[56],"positive":[57],"inference":[58],"problem":[59],"caused":[60],"by":[61,114],"inadvertently":[62],"including":[63],"OOD":[64,112],"during":[66],"training.":[67],"To":[68],"address":[69],"problem,":[71],"we":[72,89],"first":[73],"develop":[74],"baseline":[75],"models":[76],"using":[77],"outlier":[78,102],"detectors":[79],"for":[80],"hard":[81],"OOD-data":[82],"filtering":[83],"pipeline":[86],"procedure.":[87],"Furthermore,":[88],"propose":[90],"Latent":[92],"Outlier":[93],"Softening":[94],"(LOS)":[95],"framework":[96],"integrates":[98],"semi-supervised":[99],"training":[100],"detection":[103],"within":[104],"probabilistic":[105],"latent":[106],"variable":[107],"modeling.":[108],"LOS":[109,130],"softens":[110],"impacts":[113],"Expectation-Maximization":[116],"(EM)":[117],"algorithm":[118],"weighted":[120],"entropy":[121],"maximization.":[122],"Experiments":[123],"on":[124],"3":[125],"created":[126],"datasets":[127],"show":[128],"significantly":[131],"outperforms":[132],"baselines.":[133]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":2}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}