{"id":"https://openalex.org/W7140161567","doi":"https://doi.org/10.48550/arxiv.2603.21056","title":"Semi-Supervised Learning with Balanced Deep Representation Distributions","display_name":"Semi-Supervised Learning with Balanced Deep Representation Distributions","publication_year":2026,"publication_date":"2026-03-22","ids":{"openalex":"https://openalex.org/W7140161567","doi":"https://doi.org/10.48550/arxiv.2603.21056"},"language":null,"primary_location":{"id":"doi:10.48550/arxiv.2603.21056","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2603.21056","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"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":"public-domain","license_id":"https://openalex.org/licenses/public-domain","version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"article"},"type":"preprint","indexed_in":["datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://doi.org/10.48550/arxiv.2603.21056","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":null,"display_name":"Li, Changchun","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Li, Changchun","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":null,"display_name":"Li, Ximing","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Li, Ximing","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":null,"display_name":"Zhang, Bingjie","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zhang, Bingjie","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":null,"display_name":"Wang, Wenting","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Wang, Wenting","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":null,"display_name":"Ouyang, Jihong","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Ouyang, Jihong","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":5,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"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/T11550","display_name":"Text and Document Classification Technologies","score":0.8666999936103821,"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/T11550","display_name":"Text and Document Classification Technologies","score":0.8666999936103821,"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":0.04430000111460686,"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/T11307","display_name":"Domain Adaptation and Few-Shot Learning","score":0.014100000262260437,"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/classifier","display_name":"Classifier (UML)","score":0.6866999864578247},{"id":"https://openalex.org/keywords/margin","display_name":"Margin (machine learning)","score":0.6008999943733215},{"id":"https://openalex.org/keywords/regularization","display_name":"Regularization (linguistics)","score":0.5788999795913696},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.5706999897956848},{"id":"https://openalex.org/keywords/gaussian","display_name":"Gaussian","score":0.5133000016212463},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.4668999910354614},{"id":"https://openalex.org/keywords/labeled-data","display_name":"Labeled data","score":0.39890000224113464},{"id":"https://openalex.org/keywords/deep-learning","display_name":"Deep learning","score":0.3959999978542328}],"concepts":[{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.7285000085830688},{"id":"https://openalex.org/C95623464","wikidata":"https://www.wikidata.org/wiki/Q1096149","display_name":"Classifier (UML)","level":2,"score":0.6866999864578247},{"id":"https://openalex.org/C774472","wikidata":"https://www.wikidata.org/wiki/Q6760393","display_name":"Margin (machine learning)","level":2,"score":0.6008999943733215},{"id":"https://openalex.org/C2776135515","wikidata":"https://www.wikidata.org/wiki/Q17143721","display_name":"Regularization (linguistics)","level":2,"score":0.5788999795913696},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.5706999897956848},{"id":"https://openalex.org/C163716315","wikidata":"https://www.wikidata.org/wiki/Q901177","display_name":"Gaussian","level":2,"score":0.5133000016212463},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.49470001459121704},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.4668999910354614},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.41850000619888306},{"id":"https://openalex.org/C2776145971","wikidata":"https://www.wikidata.org/wiki/Q30673951","display_name":"Labeled data","level":2,"score":0.39890000224113464},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.3959999978542328},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.35100001096725464},{"id":"https://openalex.org/C2984842247","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep neural networks","level":3,"score":0.33730000257492065},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.32499998807907104},{"id":"https://openalex.org/C139532973","wikidata":"https://www.wikidata.org/wiki/Q2679259","display_name":"Linear classifier","level":3,"score":0.30869999527931213},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.3037000000476837},{"id":"https://openalex.org/C196083921","wikidata":"https://www.wikidata.org/wiki/Q7915758","display_name":"Variance (accounting)","level":2,"score":0.3037000000476837},{"id":"https://openalex.org/C147764199","wikidata":"https://www.wikidata.org/wiki/Q6865248","display_name":"Minification","level":2,"score":0.2953000068664551},{"id":"https://openalex.org/C59404180","wikidata":"https://www.wikidata.org/wiki/Q17013334","display_name":"Feature learning","level":2,"score":0.2870999872684479},{"id":"https://openalex.org/C149441793","wikidata":"https://www.wikidata.org/wiki/Q200726","display_name":"Probability distribution","level":2,"score":0.26919999718666077},{"id":"https://openalex.org/C12267149","wikidata":"https://www.wikidata.org/wiki/Q282453","display_name":"Support vector machine","level":2,"score":0.26460000872612}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.48550/arxiv.2603.21056","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2603.21056","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"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":"public-domain","license_id":"https://openalex.org/licenses/public-domain","version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"article"}],"best_oa_location":{"id":"doi:10.48550/arxiv.2603.21056","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2603.21056","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"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":"public-domain","license_id":"https://openalex.org/licenses/public-domain","version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Semi-Supervised":[0,154],"Text":[1,155],"Classification":[2,156],"(SSTC)":[3],"mainly":[4],"works":[5],"under":[6],"the":[7,13,32,36,50,66,72,88,105,113,190,197,204],"spirit":[8],"of":[9,38,52,65,78,107,110,118,172,199],"self-training.":[10],"They":[11],"initialize":[12],"deep":[14,33],"classifier":[15,34],"by":[16,49,71,124,174],"training":[17],"over":[18,35,135],"labeled":[19,39,137,205],"texts;":[20],"and":[21,30,40,92,138,168,179],"then":[22],"alternatively":[23],"predict":[24],"unlabeled":[25,55],"texts":[26,111,140,206],"as":[27],"their":[28,44],"pseudo-labels":[29,53,120],"train":[31],"mixture":[37],"pseudo-labeled":[41,139],"texts.":[42,56],"Naturally,":[43],"performance":[45],"is":[46],"largely":[47],"affected":[48],"accuracy":[51,63,117],"for":[54],"Unfortunately,":[57],"they":[58,132],"often":[59],"suffer":[60],"from":[61],"low":[62],"because":[64],"margin":[67,90],"bias":[68],"problem":[69],"caused":[70],"large":[73],"difference":[74],"between":[75],"representation":[76,160],"distributions":[77],"labels":[79],"in":[80],"SSTC.":[81],"To":[82,182],"alleviate":[83],"this":[84,145],"problem,":[85],"we":[86,147,186],"apply":[87],"angular":[89],"loss,":[91],"perform":[93],"several":[94],"Gaussian":[95],"linear":[96],"transformations":[97],"to":[98],"achieve":[99],"balanced":[100],"label":[101,108,127],"angle":[102,128],"variances,":[103],"i.e.,":[104],"variance":[106],"angles":[109],"within":[112],"same":[114],"label.":[115],"More":[116],"predicted":[119],"can":[121],"be":[122],"achieved":[123],"constraining":[125],"all":[126],"variances":[129],"balanced,":[130],"where":[131],"are":[133,207],"estimated":[134],"both":[136,165],"during":[141],"self-training":[142],"loops.":[143],"With":[144],"insight,":[146],"propose":[148],"a":[149],"novel":[150],"SSTC":[151,192],"method,":[152],"namely":[153],"with":[157],"Balanced":[158],"Deep":[159],"Distributions":[161],"(S2TC-BDD).":[162],"We":[163],"implement":[164],"multi-class":[166],"classification":[167,170],"multi-label":[169],"versions":[171],"S2TC-BDD":[173],"introducing":[175],"some":[176],"pseudo-labeling":[177],"tricks":[178],"regularization":[180],"terms.":[181],"evaluate":[183],"S2":[184,200],"TC-BDD,":[185,201],"compare":[187],"it":[188],"against":[189],"state-of-the-art":[191],"methods.":[193],"Empirical":[194],"results":[195],"demonstrate":[196],"effectiveness":[198],"especially":[202],"when":[203],"scarce.":[208]},"counts_by_year":[],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2026-03-25T00:00:00"}