{"id":"https://openalex.org/W4385571912","doi":"https://doi.org/10.18653/v1/2023.findings-acl.356","title":"LABO: Towards Learning Optimal Label Regularization via Bi-level Optimization","display_name":"LABO: Towards Learning Optimal Label Regularization via Bi-level Optimization","publication_year":2023,"publication_date":"2023-01-01","ids":{"openalex":"https://openalex.org/W4385571912","doi":"https://doi.org/10.18653/v1/2023.findings-acl.356"},"language":"en","primary_location":{"id":"doi:10.18653/v1/2023.findings-acl.356","is_oa":true,"landing_page_url":"http://dx.doi.org/10.18653/v1/2023.findings-acl.356","pdf_url":"https://aclanthology.org/2023.findings-acl.356.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":"Findings of the Association for Computational Linguistics: ACL 2023","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://aclanthology.org/2023.findings-acl.356.pdf","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5017071421","display_name":"Peng Lu","orcid":"https://orcid.org/0000-0001-5611-4902"},"institutions":[{"id":"https://openalex.org/I4210115038","display_name":"Huawei Technologies (Canada)","ror":"https://ror.org/026venb53","country_code":"CA","type":"company","lineage":["https://openalex.org/I2250955327","https://openalex.org/I4210115038"]},{"id":"https://openalex.org/I70931966","display_name":"Universit\u00e9 de Montr\u00e9al","ror":"https://ror.org/0161xgx34","country_code":"CA","type":"education","lineage":["https://openalex.org/I70931966"]}],"countries":["CA"],"is_corresponding":true,"raw_author_name":"Peng Lu","raw_affiliation_strings":["Huawei Noah's Ark Lab, Canada","Department of Computer Science and Operations Research, Universit\u00e9 de Montr\u00e9al"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Huawei Noah's Ark Lab, Canada","institution_ids":["https://openalex.org/I4210115038"]},{"raw_affiliation_string":"Department of Computer Science and Operations Research, Universit\u00e9 de Montr\u00e9al","institution_ids":["https://openalex.org/I70931966"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5103935867","display_name":"Ahmad Rashid","orcid":null},"institutions":[{"id":"https://openalex.org/I151746483","display_name":"University of Waterloo","ror":"https://ror.org/01aff2v68","country_code":"CA","type":"education","lineage":["https://openalex.org/I151746483"]},{"id":"https://openalex.org/I4210115038","display_name":"Huawei Technologies (Canada)","ror":"https://ror.org/026venb53","country_code":"CA","type":"company","lineage":["https://openalex.org/I2250955327","https://openalex.org/I4210115038"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"Ahmad Rashid","raw_affiliation_strings":["Department of Statistics and Actuarial Science, University of Waterloo","Huawei Noah's Ark Lab, Canada"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Statistics and Actuarial Science, University of Waterloo","institution_ids":["https://openalex.org/I151746483"]},{"raw_affiliation_string":"Huawei Noah's Ark Lab, Canada","institution_ids":["https://openalex.org/I4210115038"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5008923192","display_name":"Ivan Kobyzev","orcid":"https://orcid.org/0000-0003-1934-4842"},"institutions":[{"id":"https://openalex.org/I4210115038","display_name":"Huawei Technologies (Canada)","ror":"https://ror.org/026venb53","country_code":"CA","type":"company","lineage":["https://openalex.org/I2250955327","https://openalex.org/I4210115038"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"Ivan Kobyzev","raw_affiliation_strings":["Huawei Noah's Ark Lab, Canada"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Huawei Noah's Ark Lab, Canada","institution_ids":["https://openalex.org/I4210115038"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5028862918","display_name":"Mehdi Rezagholizadeh","orcid":"https://orcid.org/0000-0003-4014-6007"},"institutions":[{"id":"https://openalex.org/I4210115038","display_name":"Huawei Technologies (Canada)","ror":"https://ror.org/026venb53","country_code":"CA","type":"company","lineage":["https://openalex.org/I2250955327","https://openalex.org/I4210115038"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"Mehdi Rezagholizadeh","raw_affiliation_strings":["Huawei Noah's Ark Lab, Canada"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Huawei Noah's Ark Lab, Canada","institution_ids":["https://openalex.org/I4210115038"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5015070080","display_name":"Phillippe Langlais","orcid":null},"institutions":[{"id":"https://openalex.org/I70931966","display_name":"Universit\u00e9 de Montr\u00e9al","ror":"https://ror.org/0161xgx34","country_code":"CA","type":"education","lineage":["https://openalex.org/I70931966"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"Phillippe Langlais","raw_affiliation_strings":["Department of Computer Science and Operations Research, Universit\u00e9 de Montr\u00e9al"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science and Operations Research, Universit\u00e9 de Montr\u00e9al","institution_ids":["https://openalex.org/I70931966"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5017071421"],"corresponding_institution_ids":["https://openalex.org/I4210115038","https://openalex.org/I70931966"],"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":"5759","last_page":"5774"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12535","display_name":"Machine Learning and Data Classification","score":0.9948999881744385,"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":0.9948999881744385,"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":0.9922000169754028,"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/T12549","display_name":"Image and Object Detection Techniques","score":0.988099992275238,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"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/regularization","display_name":"Regularization (linguistics)","score":0.7872335314750671},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7015643119812012},{"id":"https://openalex.org/keywords/smoothing","display_name":"Smoothing","score":0.6356984972953796},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5954349040985107},{"id":"https://openalex.org/keywords/normalization","display_name":"Normalization (sociology)","score":0.5517489910125732},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.5079448819160461},{"id":"https://openalex.org/keywords/deep-neural-networks","display_name":"Deep neural networks","score":0.4922386705875397},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.4895225763320923},{"id":"https://openalex.org/keywords/mathematical-optimization","display_name":"Mathematical optimization","score":0.33979254961013794},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.20707190036773682}],"concepts":[{"id":"https://openalex.org/C2776135515","wikidata":"https://www.wikidata.org/wiki/Q17143721","display_name":"Regularization (linguistics)","level":2,"score":0.7872335314750671},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7015643119812012},{"id":"https://openalex.org/C3770464","wikidata":"https://www.wikidata.org/wiki/Q775963","display_name":"Smoothing","level":2,"score":0.6356984972953796},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5954349040985107},{"id":"https://openalex.org/C136886441","wikidata":"https://www.wikidata.org/wiki/Q926129","display_name":"Normalization (sociology)","level":2,"score":0.5517489910125732},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.5079448819160461},{"id":"https://openalex.org/C2984842247","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep neural networks","level":3,"score":0.4922386705875397},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.4895225763320923},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.33979254961013794},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.20707190036773682},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.0},{"id":"https://openalex.org/C144024400","wikidata":"https://www.wikidata.org/wiki/Q21201","display_name":"Sociology","level":0,"score":0.0},{"id":"https://openalex.org/C19165224","wikidata":"https://www.wikidata.org/wiki/Q23404","display_name":"Anthropology","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.18653/v1/2023.findings-acl.356","is_oa":true,"landing_page_url":"http://dx.doi.org/10.18653/v1/2023.findings-acl.356","pdf_url":"https://aclanthology.org/2023.findings-acl.356.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":"Findings of the Association for Computational Linguistics: ACL 2023","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.18653/v1/2023.findings-acl.356","is_oa":true,"landing_page_url":"http://dx.doi.org/10.18653/v1/2023.findings-acl.356","pdf_url":"https://aclanthology.org/2023.findings-acl.356.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":"Findings of the Association for Computational Linguistics: ACL 2023","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4385571912.pdf"},"referenced_works_count":48,"referenced_works":["https://openalex.org/W1821462560","https://openalex.org/W1836465849","https://openalex.org/W2023858465","https://openalex.org/W2095705004","https://openalex.org/W2108598243","https://openalex.org/W2124659975","https://openalex.org/W2144513243","https://openalex.org/W2165698076","https://openalex.org/W2183341477","https://openalex.org/W2194775991","https://openalex.org/W2251322177","https://openalex.org/W2257408573","https://openalex.org/W2577366047","https://openalex.org/W2613904329","https://openalex.org/W2888519496","https://openalex.org/W2938704169","https://openalex.org/W2939710050","https://openalex.org/W2946599989","https://openalex.org/W2962784628","https://openalex.org/W2963086938","https://openalex.org/W2963163009","https://openalex.org/W2963351448","https://openalex.org/W2963855133","https://openalex.org/W2973049979","https://openalex.org/W2978017171","https://openalex.org/W2992308087","https://openalex.org/W3005389111","https://openalex.org/W3034695001","https://openalex.org/W3034756453","https://openalex.org/W3035409869","https://openalex.org/W3035512170","https://openalex.org/W3035618147","https://openalex.org/W3094502228","https://openalex.org/W3102138045","https://openalex.org/W3105966348","https://openalex.org/W3108124733","https://openalex.org/W3118608800","https://openalex.org/W3123639697","https://openalex.org/W3173933441","https://openalex.org/W3204130541","https://openalex.org/W3204610735","https://openalex.org/W3209984917","https://openalex.org/W3211640112","https://openalex.org/W4221153087","https://openalex.org/W4285223309","https://openalex.org/W4297798436","https://openalex.org/W4385245566","https://openalex.org/W4386566845"],"related_works":["https://openalex.org/W2383807498","https://openalex.org/W1978572805","https://openalex.org/W1997992934","https://openalex.org/W1987225439","https://openalex.org/W4213275102","https://openalex.org/W4287755480","https://openalex.org/W3113607506","https://openalex.org/W2898211994","https://openalex.org/W2294590153","https://openalex.org/W4220659530"],"abstract_inverted_index":{"Regularization":[0],"techniques":[1],"are":[2],"crucial":[3],"to":[4,27,46,128],"improving":[5],"the":[6,56,117,121,126,130,133],"generalization":[7],"performance":[8],"and":[9,30,39,113,144,162],"training":[10,57,75,174],"efficiency":[11],"of":[12,55,98,116,135],"deep":[13,17],"neural":[14,169],"networks.":[15],"Many":[16],"learning":[18,99],"algorithms":[19],"rely":[20],"on":[21,90,155],"weight":[22],"decay,":[23],"dropout,":[24],"batch/layer":[25],"normalization":[26],"converge":[28],"faster":[29],"generalize.":[31],"Label":[32],"Smoothing":[33],"(LS)":[34],"is":[35,64],"another":[36],"simple,":[37],"versatile":[38],"efficient":[40,96],"regularization":[41,101,154],"which":[42,79],"can":[43,84],"be":[44],"applied":[45],"various":[47,156,168],"supervised":[48],"classification":[49,165],"tasks.":[50],"Conventional":[51],"LS,":[52],"however,":[53],"regardless":[54],"instance":[58],"assumes":[59],"that":[60],"each":[61],"non-target":[62],"class":[63],"equally":[65],"likely.In":[66],"this":[67,91],"work,":[68],"we":[69,93,140],"present":[70],"a":[71,104,111,136],"general":[72],"framework":[73],"for":[74],"with":[76],"label":[77,123,153],"regularization,":[78],"includes":[80],"conventional":[81,152],"LS":[82],"but":[83],"also":[85],"model":[86],"instance-specific":[87],"variants.":[88],"Based":[89],"formulation,":[92],"propose":[94],"an":[95],"way":[97],"LAbel":[100],"by":[102],"devising":[103],"Bi-level":[105],"Optimization":[106],"(LABO)":[107],"problem.":[108],"We":[109],"derive":[110],"deterministic":[112],"interpretable":[114],"solution":[115],"inner":[118],"loop":[119],"as":[120],"optimal":[122],"smoothing":[124],"without":[125],"need":[127],"store":[129],"parameters":[131],"or":[132],"output":[134],"trained":[137],"model.":[138],"Finally,":[139],"conduct":[141],"extensive":[142],"experiments":[143],"demonstrate":[145],"our":[146],"LABO":[147],"consistently":[148],"yields":[149],"improvement":[150],"over":[151],"fields,":[157],"including":[158],"seven":[159],"machine":[160],"translation":[161],"three":[163],"image":[164],"tasks":[166],"across":[167],"network":[170],"architectures":[171],"while":[172],"maintaining":[173],"efficiency.":[175]},"counts_by_year":[],"updated_date":"2026-07-26T07:53:14.480251","created_date":"2025-10-10T00:00:00"}