{"id":"https://openalex.org/W3012396582","doi":"https://doi.org/10.3390/e22030334","title":"Semantic and Generalized Entropy Loss Functions for Semi-Supervised Deep Learning","display_name":"Semantic and Generalized Entropy Loss Functions for Semi-Supervised Deep Learning","publication_year":2020,"publication_date":"2020-03-14","ids":{"openalex":"https://openalex.org/W3012396582","doi":"https://doi.org/10.3390/e22030334","mag":"3012396582","pmid":"https://pubmed.ncbi.nlm.nih.gov/33286108"},"language":"en","primary_location":{"id":"doi:10.3390/e22030334","is_oa":true,"landing_page_url":"https://doi.org/10.3390/e22030334","pdf_url":"https://www.mdpi.com/1099-4300/22/3/334/pdf?version=1585279099","source":{"id":"https://openalex.org/S195231649","display_name":"Entropy","issn_l":"1099-4300","issn":["1099-4300"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310310987","host_organization_name":"Multidisciplinary Digital Publishing Institute","host_organization_lineage":["https://openalex.org/P4310310987"],"host_organization_lineage_names":["Multidisciplinary Digital Publishing Institute"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Entropy","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","doaj","pubmed"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://www.mdpi.com/1099-4300/22/3/334/pdf?version=1585279099","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5047203445","display_name":"Krzysztof Gajowniczek","orcid":"https://orcid.org/0000-0001-6953-8907"},"institutions":[{"id":"https://openalex.org/I170230895","display_name":"Warsaw University of Life Sciences","ror":"https://ror.org/05srvzs48","country_code":"PL","type":"education","lineage":["https://openalex.org/I170230895"]}],"countries":["PL"],"is_corresponding":true,"raw_author_name":"Krzysztof Gajowniczek","raw_affiliation_strings":["Department of Artificial Intelligence, Institute of Information Technology, Warsaw University of Life Sciences-SGGW, 02-776 Warsaw, Poland"],"raw_orcid":"https://orcid.org/0000-0001-6953-8907","affiliations":[{"raw_affiliation_string":"Department of Artificial Intelligence, Institute of Information Technology, Warsaw University of Life Sciences-SGGW, 02-776 Warsaw, Poland","institution_ids":["https://openalex.org/I170230895"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5112110952","display_name":"Yitao Liang","orcid":"https://orcid.org/0009-0009-0944-7814"},"institutions":[{"id":"https://openalex.org/I161318765","display_name":"University of California, Los Angeles","ror":"https://ror.org/046rm7j60","country_code":"US","type":"education","lineage":["https://openalex.org/I161318765"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Yitao Liang","raw_affiliation_strings":["Computer Science Department, University of California, Los Angeles, CA 90095, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Computer Science Department, University of California, Los Angeles, CA 90095, USA","institution_ids":["https://openalex.org/I161318765"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5112426575","display_name":"Tal Friedman","orcid":null},"institutions":[{"id":"https://openalex.org/I161318765","display_name":"University of California, Los Angeles","ror":"https://ror.org/046rm7j60","country_code":"US","type":"education","lineage":["https://openalex.org/I161318765"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Tal Friedman","raw_affiliation_strings":["Computer Science Department, University of California, Los Angeles, CA 90095, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Computer Science Department, University of California, Los Angeles, CA 90095, USA","institution_ids":["https://openalex.org/I161318765"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5029575854","display_name":"Tomasz Z\u0105bkowski","orcid":"https://orcid.org/0000-0003-1722-1179"},"institutions":[{"id":"https://openalex.org/I170230895","display_name":"Warsaw University of Life Sciences","ror":"https://ror.org/05srvzs48","country_code":"PL","type":"education","lineage":["https://openalex.org/I170230895"]}],"countries":["PL"],"is_corresponding":false,"raw_author_name":"Tomasz Z\u0105bkowski","raw_affiliation_strings":["Department of Artificial Intelligence, Institute of Information Technology, Warsaw University of Life Sciences-SGGW, 02-776 Warsaw, Poland"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Artificial Intelligence, Institute of Information Technology, Warsaw University of Life Sciences-SGGW, 02-776 Warsaw, Poland","institution_ids":["https://openalex.org/I170230895"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5009539513","display_name":"Guy Van den Broeck","orcid":"https://orcid.org/0000-0003-3434-2503"},"institutions":[{"id":"https://openalex.org/I161318765","display_name":"University of California, Los Angeles","ror":"https://ror.org/046rm7j60","country_code":"US","type":"education","lineage":["https://openalex.org/I161318765"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Guy Van den Broeck","raw_affiliation_strings":["Computer Science Department, University of California, Los Angeles, CA 90095, USA"],"raw_orcid":"https://orcid.org/0000-0003-3434-2503","affiliations":[{"raw_affiliation_string":"Computer Science Department, University of California, Los Angeles, CA 90095, USA","institution_ids":["https://openalex.org/I161318765"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5047203445"],"corresponding_institution_ids":["https://openalex.org/I170230895"],"apc_list":{"value":2000,"currency":"CHF","value_usd":2165},"apc_paid":{"value":2000,"currency":"CHF","value_usd":2165},"fwci":1.9041,"has_fulltext":true,"cited_by_count":27,"citation_normalized_percentile":{"value":0.88699173,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":95,"max":99},"biblio":{"volume":"22","issue":"3","first_page":"334","last_page":"334"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12535","display_name":"Machine Learning and Data Classification","score":0.9998000264167786,"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/T12535","display_name":"Machine Learning and Data Classification","score":0.9998000264167786,"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/T11512","display_name":"Anomaly Detection Techniques and Applications","score":0.9991999864578247,"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":0.9977999925613403,"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/mnist-database","display_name":"MNIST database","score":0.8296372294425964},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.668698787689209},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6468698382377625},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.5763798952102661},{"id":"https://openalex.org/keywords/semi-supervised-learning","display_name":"Semi-supervised learning","score":0.5736818909645081},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.5562192797660828},{"id":"https://openalex.org/keywords/entropy","display_name":"Entropy (arrow of time)","score":0.5467638969421387},{"id":"https://openalex.org/keywords/supervised-learning","display_name":"Supervised learning","score":0.5346402525901794},{"id":"https://openalex.org/keywords/cross-entropy","display_name":"Cross entropy","score":0.43843623995780945},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.37285593152046204}],"concepts":[{"id":"https://openalex.org/C190502265","wikidata":"https://www.wikidata.org/wiki/Q17069496","display_name":"MNIST database","level":3,"score":0.8296372294425964},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.668698787689209},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6468698382377625},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.5763798952102661},{"id":"https://openalex.org/C58973888","wikidata":"https://www.wikidata.org/wiki/Q1041418","display_name":"Semi-supervised learning","level":2,"score":0.5736818909645081},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.5562192797660828},{"id":"https://openalex.org/C106301342","wikidata":"https://www.wikidata.org/wiki/Q4117933","display_name":"Entropy (arrow of time)","level":2,"score":0.5467638969421387},{"id":"https://openalex.org/C136389625","wikidata":"https://www.wikidata.org/wiki/Q334384","display_name":"Supervised learning","level":3,"score":0.5346402525901794},{"id":"https://openalex.org/C167981619","wikidata":"https://www.wikidata.org/wiki/Q1685498","display_name":"Cross entropy","level":3,"score":0.43843623995780945},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.37285593152046204},{"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}],"mesh":[],"locations_count":6,"locations":[{"id":"doi:10.3390/e22030334","is_oa":true,"landing_page_url":"https://doi.org/10.3390/e22030334","pdf_url":"https://www.mdpi.com/1099-4300/22/3/334/pdf?version=1585279099","source":{"id":"https://openalex.org/S195231649","display_name":"Entropy","issn_l":"1099-4300","issn":["1099-4300"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310310987","host_organization_name":"Multidisciplinary Digital Publishing Institute","host_organization_lineage":["https://openalex.org/P4310310987"],"host_organization_lineage_names":["Multidisciplinary Digital Publishing Institute"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Entropy","raw_type":"journal-article"},{"id":"pmid:33286108","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/33286108","pdf_url":null,"source":{"id":"https://openalex.org/S4306525036","display_name":"PubMed","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1299303238","host_organization_name":"National Institutes of Health","host_organization_lineage":["https://openalex.org/I1299303238"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Entropy (Basel, Switzerland)","raw_type":null},{"id":"pmh:oai:doaj.org/article:ba6b8a05ba3a4a9eade2161f8b09cf26","is_oa":true,"landing_page_url":"https://doaj.org/article/ba6b8a05ba3a4a9eade2161f8b09cf26","pdf_url":null,"source":{"id":"https://openalex.org/S4306401280","display_name":"DOAJ (DOAJ: Directory of Open Access Journals)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"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":"Entropy, Vol 22, Iss 3, p 334 (2020)","raw_type":"article"},{"id":"pmh:oai:escholarship.org:ark:/13030/qt1781f84h","is_oa":true,"landing_page_url":"https://escholarship.org/uc/item/1781f84h","pdf_url":null,"source":{"id":"https://openalex.org/S4306400115","display_name":"eScholarship (California Digital Library)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I2801248553","host_organization_name":"California Digital Library","host_organization_lineage":["https://openalex.org/I2801248553"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Entropy, vol 22, iss 3","raw_type":"article"},{"id":"pmh:oai:mdpi.com:/1099-4300/22/3/334/","is_oa":true,"landing_page_url":"http://dx.doi.org/10.3390/e22030334","pdf_url":null,"source":{"id":"https://openalex.org/S4306400947","display_name":"MDPI (MDPI AG)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I4210097602","host_organization_name":"Multidisciplinary Digital Publishing Institute (Switzerland)","host_organization_lineage":["https://openalex.org/I4210097602"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Entropy","raw_type":"Text"},{"id":"pmh:oai:pubmedcentral.nih.gov:7516792","is_oa":true,"landing_page_url":"https://www.ncbi.nlm.nih.gov/pmc/articles/7516792","pdf_url":null,"source":{"id":"https://openalex.org/S2764455111","display_name":"PubMed Central","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1299303238","host_organization_name":"National Institutes of Health","host_organization_lineage":["https://openalex.org/I1299303238"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Entropy (Basel)","raw_type":"Text"}],"best_oa_location":{"id":"doi:10.3390/e22030334","is_oa":true,"landing_page_url":"https://doi.org/10.3390/e22030334","pdf_url":"https://www.mdpi.com/1099-4300/22/3/334/pdf?version=1585279099","source":{"id":"https://openalex.org/S195231649","display_name":"Entropy","issn_l":"1099-4300","issn":["1099-4300"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310310987","host_organization_name":"Multidisciplinary Digital Publishing Institute","host_organization_lineage":["https://openalex.org/P4310310987"],"host_organization_lineage_names":["Multidisciplinary Digital Publishing Institute"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Entropy","raw_type":"journal-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W3012396582.pdf","grobid_xml":"https://content.openalex.org/works/W3012396582.grobid-xml"},"referenced_works_count":42,"referenced_works":["https://openalex.org/W1520121841","https://openalex.org/W1665214252","https://openalex.org/W1774786334","https://openalex.org/W1836465849","https://openalex.org/W1995052655","https://openalex.org/W1995875735","https://openalex.org/W1996191831","https://openalex.org/W2002420498","https://openalex.org/W2044074081","https://openalex.org/W2062843442","https://openalex.org/W2064487597","https://openalex.org/W2108501770","https://openalex.org/W2112796928","https://openalex.org/W2118023920","https://openalex.org/W2194775991","https://openalex.org/W2402839980","https://openalex.org/W2565516711","https://openalex.org/W2574181397","https://openalex.org/W2618530766","https://openalex.org/W2736191430","https://openalex.org/W2750384547","https://openalex.org/W2756477888","https://openalex.org/W2772282934","https://openalex.org/W2773809710","https://openalex.org/W2789696622","https://openalex.org/W2795944650","https://openalex.org/W2891681985","https://openalex.org/W2898471460","https://openalex.org/W2919115771","https://openalex.org/W2949117887","https://openalex.org/W2949416428","https://openalex.org/W2951065015","https://openalex.org/W2952229419","https://openalex.org/W2963737801","https://openalex.org/W2964159205","https://openalex.org/W2976282046","https://openalex.org/W2983144912","https://openalex.org/W2984353870","https://openalex.org/W3100132343","https://openalex.org/W3101567120","https://openalex.org/W6687483927","https://openalex.org/W6758265528"],"related_works":["https://openalex.org/W4367361129","https://openalex.org/W1586607209","https://openalex.org/W830076066","https://openalex.org/W122912556","https://openalex.org/W4312414840","https://openalex.org/W2952229419","https://openalex.org/W2621411691","https://openalex.org/W2271357838","https://openalex.org/W2556866732","https://openalex.org/W2328989934"],"abstract_inverted_index":{"The":[0,189],"increasing":[1],"size":[2],"of":[3,10,23,42,49,178],"modern":[4,28],"datasets":[5,160],"combined":[6],"with":[7,36,118],"the":[8,40,43,97,103,124,168,171,176,179,186,198],"difficulty":[9],"obtaining":[11],"real":[12],"label":[13],"information":[14,38],"(e.g.,":[15],"class)":[16],"has":[17],"made":[18],"semi-supervised":[19,206],"learning":[20,32,35,51],"a":[21,61,81,86,133],"problem":[22],"considerable":[24],"practical":[25],"importance":[26],"in":[27],"data":[29],"analysis.":[30],"Semi-supervised":[31],"is":[33,100],"supervised":[34],"additional":[37],"on":[39,105,185,205],"distribution":[41],"examples":[44],"or,":[45],"simultaneously,":[46],"an":[47,142,151],"extension":[48],"unsupervised":[50],"guided":[52],"by":[53],"some":[54],"constraints.":[55,73],"In":[56,74],"this":[57],"article":[58],"we":[59,79],"present":[60,80],"methodology":[62,149],"that":[63,93,136,193],"bridges":[64],"between":[65,170],"artificial":[66],"neural":[67,98,121],"network":[68,99],"output":[69],"vectors":[70],"and":[71,85,116,127,155,164,175,182],"logical":[72],"order":[75],"to":[76,101,112,166,200],"do":[77],"this,":[78],"semantic":[82,125],"loss":[83,89,126,130,144,173],"function":[84,90],"generalized":[87,128],"entropy":[88,129],"(R\u00e9nyi":[91],"entropy)":[92],"capture":[94],"how":[95],"close":[96],"satisfying":[102],"constraints":[104],"its":[106],"output.":[107],"Our":[108],"methods":[109],"are":[110,131,162],"intended":[111],"be":[113,138],"generally":[114],"applicable":[115],"compatible":[117],"any":[119],"feedforward":[120],"network.":[122],"Therefore,":[123],"simply":[132],"regularization":[134],"term":[135],"can":[137],"directly":[139],"plugged":[140],"into":[141],"existing":[143],"function.":[145],"We":[146],"evaluate":[147],"our":[148],"over":[150],"artificially":[152],"simulated":[153],"dataset":[154],"two":[156],"commonly":[157],"used":[158],"benchmark":[159],"which":[161],"MNIST":[163],"Fashion-MNIST":[165],"assess":[167],"relation":[169],"analyzed":[172],"functions":[174],"influence":[177],"various":[180],"input":[181],"tuning":[183],"parameters":[184],"classification":[187],"accuracy.":[188],"experimental":[190],"evaluation":[191],"shows":[192],"both":[194],"losses":[195],"effectively":[196],"guide":[197],"learner":[199],"achieve":[201],"(near-)":[202],"state-of-the-art":[203],"results":[204],"multiclass":[207],"classification.":[208]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":7},{"year":2024,"cited_by_count":5},{"year":2023,"cited_by_count":10},{"year":2021,"cited_by_count":4}],"updated_date":"2026-05-21T06:26:12.895304","created_date":"2025-10-10T00:00:00"}