{"id":"https://openalex.org/W4379511426","doi":"https://doi.org/10.21428/594757db.6ee355e7","title":"Exploring Preferential Label Smoothing for Neural Network-based Classifiers","display_name":"Exploring Preferential Label Smoothing for Neural Network-based Classifiers","publication_year":2023,"publication_date":"2023-06-05","ids":{"openalex":"https://openalex.org/W4379511426","doi":"https://doi.org/10.21428/594757db.6ee355e7"},"language":"en","primary_location":{"id":"doi:10.21428/594757db.6ee355e7","is_oa":true,"landing_page_url":"http://dx.doi.org/10.21428/594757db.6ee355e7","pdf_url":"https://caiac.pubpub.org/pub/iooso56q/download/pdf","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Canadian Conference on Artificial Intelligence","raw_type":"journal-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://caiac.pubpub.org/pub/iooso56q/download/pdf","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5015606971","display_name":"Paritosh Goyal","orcid":null},"institutions":[{"id":"https://openalex.org/I154425047","display_name":"University of Alberta","ror":"https://ror.org/0160cpw27","country_code":"CA","type":"education","lineage":["https://openalex.org/I154425047"]}],"countries":["CA"],"is_corresponding":true,"raw_author_name":"Paritosh Goyal","raw_affiliation_strings":["University of Alberta, Canada"],"affiliations":[{"raw_affiliation_string":"University of Alberta, Canada","institution_ids":["https://openalex.org/I154425047"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5001882275","display_name":"Chenyang Huang","orcid":"https://orcid.org/0000-0003-2811-6008"},"institutions":[{"id":"https://openalex.org/I154425047","display_name":"University of Alberta","ror":"https://ror.org/0160cpw27","country_code":"CA","type":"education","lineage":["https://openalex.org/I154425047"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"Chenyang Huang","raw_affiliation_strings":["University of Alberta, Canada"],"affiliations":[{"raw_affiliation_string":"University of Alberta, Canada","institution_ids":["https://openalex.org/I154425047"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5038712780","display_name":"Amine Trabelsi","orcid":"https://orcid.org/0000-0002-1852-5265"},"institutions":[{"id":"https://openalex.org/I154425047","display_name":"University of Alberta","ror":"https://ror.org/0160cpw27","country_code":"CA","type":"education","lineage":["https://openalex.org/I154425047"]},{"id":"https://openalex.org/I135117807","display_name":"Universit\u00e9 de Sherbrooke","ror":"https://ror.org/00kybxq39","country_code":"CA","type":"education","lineage":["https://openalex.org/I135117807"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"Amine Trabelsi","raw_affiliation_strings":["Universit\u00e9 de Sherbrooke, Canada","University of Alberta"],"affiliations":[{"raw_affiliation_string":"Universit\u00e9 de Sherbrooke, Canada","institution_ids":["https://openalex.org/I135117807"]},{"raw_affiliation_string":"University of Alberta","institution_ids":["https://openalex.org/I154425047"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5053745515","display_name":"Osmar R. Za\u0131\u0308ane","orcid":"https://orcid.org/0000-0002-0060-5988"},"institutions":[{"id":"https://openalex.org/I154425047","display_name":"University of Alberta","ror":"https://ror.org/0160cpw27","country_code":"CA","type":"education","lineage":["https://openalex.org/I154425047"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"Osmar Za\u00efane","raw_affiliation_strings":["University of Alberta, Canada"],"affiliations":[{"raw_affiliation_string":"University of Alberta, Canada","institution_ids":["https://openalex.org/I154425047"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5015606971"],"corresponding_institution_ids":["https://openalex.org/I154425047"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":{"value":0.0527864,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"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/T12535","display_name":"Machine Learning and Data Classification","score":0.9735999703407288,"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":0.9735999703407288,"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/T10320","display_name":"Neural Networks and Applications","score":0.9578999876976013,"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/overfitting","display_name":"Overfitting","score":0.8925403952598572},{"id":"https://openalex.org/keywords/smoothing","display_name":"Smoothing","score":0.8644876480102539},{"id":"https://openalex.org/keywords/ground-truth","display_name":"Ground truth","score":0.6692482829093933},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6356883645057678},{"id":"https://openalex.org/keywords/regularization","display_name":"Regularization (linguistics)","score":0.6279233694076538},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5490477681159973},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.5445513725280762},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.5360705256462097},{"id":"https://openalex.org/keywords/noise","display_name":"Noise (video)","score":0.4706147313117981},{"id":"https://openalex.org/keywords/binary-classification","display_name":"Binary classification","score":0.464141309261322},{"id":"https://openalex.org/keywords/generalization","display_name":"Generalization","score":0.4240337014198303},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.40151867270469666},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.26872700452804565},{"id":"https://openalex.org/keywords/support-vector-machine","display_name":"Support vector machine","score":0.12196823954582214}],"concepts":[{"id":"https://openalex.org/C22019652","wikidata":"https://www.wikidata.org/wiki/Q331309","display_name":"Overfitting","level":3,"score":0.8925403952598572},{"id":"https://openalex.org/C3770464","wikidata":"https://www.wikidata.org/wiki/Q775963","display_name":"Smoothing","level":2,"score":0.8644876480102539},{"id":"https://openalex.org/C146849305","wikidata":"https://www.wikidata.org/wiki/Q370766","display_name":"Ground truth","level":2,"score":0.6692482829093933},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6356883645057678},{"id":"https://openalex.org/C2776135515","wikidata":"https://www.wikidata.org/wiki/Q17143721","display_name":"Regularization (linguistics)","level":2,"score":0.6279233694076538},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5490477681159973},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.5445513725280762},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.5360705256462097},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.4706147313117981},{"id":"https://openalex.org/C66905080","wikidata":"https://www.wikidata.org/wiki/Q17005494","display_name":"Binary classification","level":3,"score":0.464141309261322},{"id":"https://openalex.org/C177148314","wikidata":"https://www.wikidata.org/wiki/Q170084","display_name":"Generalization","level":2,"score":0.4240337014198303},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.40151867270469666},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.26872700452804565},{"id":"https://openalex.org/C12267149","wikidata":"https://www.wikidata.org/wiki/Q282453","display_name":"Support vector machine","level":2,"score":0.12196823954582214},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.0},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.0},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.21428/594757db.6ee355e7","is_oa":true,"landing_page_url":"http://dx.doi.org/10.21428/594757db.6ee355e7","pdf_url":"https://caiac.pubpub.org/pub/iooso56q/download/pdf","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Canadian Conference on Artificial Intelligence","raw_type":"journal-article"}],"best_oa_location":{"id":"doi:10.21428/594757db.6ee355e7","is_oa":true,"landing_page_url":"http://dx.doi.org/10.21428/594757db.6ee355e7","pdf_url":"https://caiac.pubpub.org/pub/iooso56q/download/pdf","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Canadian Conference on Artificial Intelligence","raw_type":"journal-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4379511426.pdf"},"referenced_works_count":26,"referenced_works":["https://openalex.org/W1582774210","https://openalex.org/W1811750039","https://openalex.org/W1821462560","https://openalex.org/W1836465849","https://openalex.org/W1972095489","https://openalex.org/W2010315761","https://openalex.org/W2024484010","https://openalex.org/W2130942839","https://openalex.org/W2183341477","https://openalex.org/W2194775991","https://openalex.org/W2250539671","https://openalex.org/W2626967530","https://openalex.org/W2948210185","https://openalex.org/W3035409869","https://openalex.org/W3118608800","https://openalex.org/W3173196825","https://openalex.org/W3207466819","https://openalex.org/W4225835077","https://openalex.org/W4250971714","https://openalex.org/W4385245566","https://openalex.org/W6638523607","https://openalex.org/W6679436768","https://openalex.org/W6687483927","https://openalex.org/W6691431627","https://openalex.org/W6739651123","https://openalex.org/W6739901393"],"related_works":["https://openalex.org/W2989932438","https://openalex.org/W3011996705","https://openalex.org/W3099765033","https://openalex.org/W3175189414","https://openalex.org/W4210794429","https://openalex.org/W2767651786","https://openalex.org/W2985459377","https://openalex.org/W3037079993","https://openalex.org/W2972984751","https://openalex.org/W4225463537"],"abstract_inverted_index":{"Overfitting,":[0],"a":[1,9,50,56,66,134,194],"common":[2],"problem":[3],"in":[4,15,46,69,86,227,251],"Machine":[5],"Learning,":[6],"occurs":[7],"when":[8,246],"predictive":[10],"model":[11,57,76],"learns":[12],"the":[13,16,21,32,70,75,87,102,109,121,152,155,167,180,209,216,228,242,247,252,259,270,276],"noise":[14,85],"training":[17,33,277],"data":[18,34,88,110],"instead":[19,171],"of":[20,95,101,172,178,198,211,230,244,249,261,272],"true":[22],"underlying":[23],"patterns":[24],"and":[25,115,132,263,286],"converges":[26],"to":[27,54,73,84,98,139,154,166],"perform":[28],"very":[29],"well":[30,268],"with":[31,37],"but":[35],"poorly":[36],"unseen":[38],"data.":[39],"Models":[40],"that":[41],"overfit":[42],"cannot":[43],"be":[44],"deployed":[45],"practice.":[47],"Regularization":[48],"is":[49,61,97,128,133,225,254],"technique":[51],"typically":[52],"used":[53],"help":[55],"better":[58],"generalize.":[59],"This":[60,126],"usually":[62],"achieved":[63],"by":[64],"adding":[65],"penalty":[67],"term":[68],"loss":[71],"function":[72],"discourage":[74],"from":[77,108],"fitting":[78],"noise,":[79],"making":[80],"it":[81,117],"more":[82,91,195],"robust":[83],"and,":[89],"therefore":[90],"generalizable.":[92],"One":[93],"method":[94,127,138],"regularization":[96],"take":[99],"some":[100],"concentration":[103],"(called":[104],"Smoothing":[105,190],"Ratio":[106],"(SR))":[107],"sample\u2019s":[111],"ground":[112,168],"truth":[113,157,169],"label":[114,130,200,204,221,265,273],"distribute":[116,151],"uniformly":[118],"among":[119],"all":[120],"other":[122],"labels":[123,158,186,212,250],"during":[124],"training.":[125],"called":[129],"smoothing":[131,205],"simple":[135],"yet":[136],"effective":[137],"improve":[140],"generalization.":[141],"In":[142],"this":[143,176],"work,":[144],"we":[145,150,240],"explore":[146],"what":[147],"happens":[148],"if":[149],"SR":[153,181,217],"non-ground":[156],"based":[159,182],"on":[160,183,275,283],"how":[161],"closely":[162],"they":[163],"are":[164,235],"related":[165],"label,":[170],"uniformly.":[173],"We":[174,256,279],"call":[175],"approach":[177,197],"distributing":[179],"relation":[184],"between":[185],"as":[187,208,267,269],"Preferential":[188],"Label":[189],"(PLS).":[191],"PLS":[192,224,245],"represents":[193],"unified":[196],"performing":[199],"smoothing.":[201],"Ordinary":[202],"uniform":[203,262],"becomes":[206,213,222],"pointless":[207],"number":[210,248],"large":[214],"since":[215,233],"proportion":[218],"distributed":[219],"per":[220],"negligible.":[223],"inconsequential":[226],"case":[229],"binary":[231],"classification,":[232],"there":[234],"only":[236],"two":[237],"labels.":[238],"Therefore,":[239],"investigate":[241],"effects":[243,260],"dataset":[253],"high.":[255],"also":[257],"examine":[258],"preferential":[264],"smoothing,":[266,274],"absence":[271],"dynamics.":[278],"demonstrate":[280],"our":[281],"study":[282],"image":[284],"classification":[285],"text":[287],"classification.":[288]},"counts_by_year":[],"updated_date":"2026-01-23T23:20:30.427331","created_date":"2025-10-10T00:00:00"}