{"id":"https://openalex.org/W4380686953","doi":"https://doi.org/10.1145/3580305.3599318","title":"DyGen: Learning from Noisy Labels via Dynamics-Enhanced Generative Modeling","display_name":"DyGen: Learning from Noisy Labels via Dynamics-Enhanced Generative Modeling","publication_year":2023,"publication_date":"2023-08-04","ids":{"openalex":"https://openalex.org/W4380686953","doi":"https://doi.org/10.1145/3580305.3599318"},"language":"en","primary_location":{"id":"doi:10.1145/3580305.3599318","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3580305.3599318","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3580305.3599318","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 29th ACM SIGKDD Conference on Knowledge Discovery and Data Mining","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://dl.acm.org/doi/pdf/10.1145/3580305.3599318","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5063200221","display_name":"Yuchen Zhuang","orcid":"https://orcid.org/0000-0003-4641-894X"},"institutions":[{"id":"https://openalex.org/I130701444","display_name":"Georgia Institute of Technology","ror":"https://ror.org/01zkghx44","country_code":"US","type":"education","lineage":["https://openalex.org/I130701444"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Yuchen Zhuang","raw_affiliation_strings":["Georgia Institute of Technology, Atlanta, GA, USA"],"affiliations":[{"raw_affiliation_string":"Georgia Institute of Technology, Atlanta, GA, USA","institution_ids":["https://openalex.org/I130701444"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100397967","display_name":"Yue Yu","orcid":"https://orcid.org/0000-0002-3683-5208"},"institutions":[{"id":"https://openalex.org/I130701444","display_name":"Georgia Institute of Technology","ror":"https://ror.org/01zkghx44","country_code":"US","type":"education","lineage":["https://openalex.org/I130701444"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Yue Yu","raw_affiliation_strings":["Georgia Institute of Technology, Atlanta, GA, USA"],"affiliations":[{"raw_affiliation_string":"Georgia Institute of Technology, Atlanta, GA, USA","institution_ids":["https://openalex.org/I130701444"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102018639","display_name":"Lingkai Kong","orcid":"https://orcid.org/0000-0001-6480-513X"},"institutions":[{"id":"https://openalex.org/I130701444","display_name":"Georgia Institute of Technology","ror":"https://ror.org/01zkghx44","country_code":"US","type":"education","lineage":["https://openalex.org/I130701444"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Lingkai Kong","raw_affiliation_strings":["Georgia Institute of Technology, Atlanta, GA, USA"],"affiliations":[{"raw_affiliation_string":"Georgia Institute of Technology, Atlanta, GA, USA","institution_ids":["https://openalex.org/I130701444"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102715768","display_name":"Xiang Chen","orcid":"https://orcid.org/0009-0009-9864-355X"},"institutions":[{"id":"https://openalex.org/I1306409833","display_name":"Adobe Systems (United States)","ror":"https://ror.org/059tvcg64","country_code":"US","type":"company","lineage":["https://openalex.org/I1306409833"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Xiang Chen","raw_affiliation_strings":["Adobe Research, San Jose, CA, USA"],"affiliations":[{"raw_affiliation_string":"Adobe Research, San Jose, CA, USA","institution_ids":["https://openalex.org/I1306409833"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100460272","display_name":"Chao Zhang","orcid":"https://orcid.org/0000-0003-3009-598X"},"institutions":[{"id":"https://openalex.org/I130701444","display_name":"Georgia Institute of Technology","ror":"https://ror.org/01zkghx44","country_code":"US","type":"education","lineage":["https://openalex.org/I130701444"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Chao Zhang","raw_affiliation_strings":["Georgia Institute of Technology, Atlanta, GA, USA"],"affiliations":[{"raw_affiliation_string":"Georgia Institute of Technology, Atlanta, GA, USA","institution_ids":["https://openalex.org/I130701444"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5063200221"],"corresponding_institution_ids":["https://openalex.org/I130701444"],"apc_list":null,"apc_paid":null,"fwci":1.3826,"has_fulltext":true,"cited_by_count":8,"citation_normalized_percentile":{"value":0.84604579,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"3674","last_page":"3686"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12535","display_name":"Machine Learning and Data Classification","score":0.9994000196456909,"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":0.9994000196456909,"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":0.9606999754905701,"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/computer-science","display_name":"Computer science","score":0.8079469203948975},{"id":"https://openalex.org/keywords/overfitting","display_name":"Overfitting","score":0.7352456450462341},{"id":"https://openalex.org/keywords/embedding","display_name":"Embedding","score":0.6351222991943359},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6113468408584595},{"id":"https://openalex.org/keywords/noise","display_name":"Noise (video)","score":0.5639028549194336},{"id":"https://openalex.org/keywords/prior-probability","display_name":"Prior probability","score":0.5533285140991211},{"id":"https://openalex.org/keywords/regularization","display_name":"Regularization (linguistics)","score":0.5532820820808411},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.5235669016838074},{"id":"https://openalex.org/keywords/generative-model","display_name":"Generative model","score":0.48269200325012207},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.4285045266151428},{"id":"https://openalex.org/keywords/language-model","display_name":"Language model","score":0.42329108715057373},{"id":"https://openalex.org/keywords/generative-grammar","display_name":"Generative grammar","score":0.36920469999313354},{"id":"https://openalex.org/keywords/bayesian-probability","display_name":"Bayesian probability","score":0.17427906394004822},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.10440808534622192}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8079469203948975},{"id":"https://openalex.org/C22019652","wikidata":"https://www.wikidata.org/wiki/Q331309","display_name":"Overfitting","level":3,"score":0.7352456450462341},{"id":"https://openalex.org/C41608201","wikidata":"https://www.wikidata.org/wiki/Q980509","display_name":"Embedding","level":2,"score":0.6351222991943359},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6113468408584595},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.5639028549194336},{"id":"https://openalex.org/C177769412","wikidata":"https://www.wikidata.org/wiki/Q278090","display_name":"Prior probability","level":3,"score":0.5533285140991211},{"id":"https://openalex.org/C2776135515","wikidata":"https://www.wikidata.org/wiki/Q17143721","display_name":"Regularization (linguistics)","level":2,"score":0.5532820820808411},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.5235669016838074},{"id":"https://openalex.org/C167966045","wikidata":"https://www.wikidata.org/wiki/Q5532625","display_name":"Generative model","level":3,"score":0.48269200325012207},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.4285045266151428},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.42329108715057373},{"id":"https://openalex.org/C39890363","wikidata":"https://www.wikidata.org/wiki/Q36108","display_name":"Generative grammar","level":2,"score":0.36920469999313354},{"id":"https://openalex.org/C107673813","wikidata":"https://www.wikidata.org/wiki/Q812534","display_name":"Bayesian probability","level":2,"score":0.17427906394004822},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.10440808534622192},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3580305.3599318","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3580305.3599318","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3580305.3599318","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 29th ACM SIGKDD Conference on Knowledge Discovery and Data Mining","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.1145/3580305.3599318","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3580305.3599318","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3580305.3599318","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 29th ACM SIGKDD Conference on Knowledge Discovery and Data Mining","raw_type":"proceedings-article"},"sustainable_development_goals":[{"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4","score":0.4000000059604645}],"awards":[{"id":"https://openalex.org/G11240557","display_name":null,"funder_award_id":"MURI N00014-17-1-2656","funder_id":"https://openalex.org/F4320337345","funder_display_name":"Office of Naval Research"},{"id":"https://openalex.org/G1726583756","display_name":"III: Small: Go Beyond Short-term Dependency and Homogeneity: A General-Purpose Transformer Recipe for Multi-Domain Heterogeneous Sequential Data Analysis","funder_award_id":"2008334","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G4504108201","display_name":null,"funder_award_id":"N00014-17-1","funder_id":"https://openalex.org/F4320337345","funder_display_name":"Office of Naval Research"},{"id":"https://openalex.org/G4751570384","display_name":null,"funder_award_id":"4-17-1-","funder_id":"https://openalex.org/F4320337345","funder_display_name":"Office of Naval Research"},{"id":"https://openalex.org/G4987246806","display_name":"CAREER: Accelerating Spatial Network Design: An Uncertainty-Driven Predict-and-Optimize Learning Framework","funder_award_id":"2144338","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G5397617431","display_name":null,"funder_award_id":"N00014-17-1-2656","funder_id":"https://openalex.org/F4320333591","funder_display_name":"Multidisciplinary University Research Initiative"},{"id":"https://openalex.org/G6369104783","display_name":null,"funder_award_id":"N00014-17-1-2656","funder_id":"https://openalex.org/F4320337345","funder_display_name":"Office of Naval Research"},{"id":"https://openalex.org/G6484623147","display_name":"III: Medium: Collaborative Research: Principled Uncertainty Quantification in Deep Learning Models for Time Series Analysis","funder_award_id":"2106961","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G6671297155","display_name":null,"funder_award_id":"CAREER","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G8876996369","display_name":null,"funder_award_id":"N00014","funder_id":"https://openalex.org/F4320337345","funder_display_name":"Office of Naval Research"}],"funders":[{"id":"https://openalex.org/F4320306076","display_name":"National Science Foundation","ror":"https://ror.org/021nxhr62"},{"id":"https://openalex.org/F4320333591","display_name":"Multidisciplinary University Research Initiative","ror":null},{"id":"https://openalex.org/F4320337345","display_name":"Office of Naval Research","ror":"https://ror.org/00rk2pe57"}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4380686953.pdf","grobid_xml":"https://content.openalex.org/works/W4380686953.grobid-xml"},"referenced_works_count":32,"referenced_works":["https://openalex.org/W2065151783","https://openalex.org/W2187089797","https://openalex.org/W2612690371","https://openalex.org/W2751936342","https://openalex.org/W2759474451","https://openalex.org/W2892181857","https://openalex.org/W2911489562","https://openalex.org/W2962764460","https://openalex.org/W2963846996","https://openalex.org/W2964274690","https://openalex.org/W2964292098","https://openalex.org/W2979826702","https://openalex.org/W2981873476","https://openalex.org/W3004146535","https://openalex.org/W3012687255","https://openalex.org/W3034185248","https://openalex.org/W3034891697","https://openalex.org/W3037099311","https://openalex.org/W3038098779","https://openalex.org/W3039366696","https://openalex.org/W3042609801","https://openalex.org/W3046375318","https://openalex.org/W3099142828","https://openalex.org/W3103649165","https://openalex.org/W3103981637","https://openalex.org/W3104255659","https://openalex.org/W3154813414","https://openalex.org/W4212774754","https://openalex.org/W4287854750","https://openalex.org/W4301183982","https://openalex.org/W4385571571","https://openalex.org/W4385573358"],"related_works":["https://openalex.org/W4365211920","https://openalex.org/W3014948380","https://openalex.org/W3042518613","https://openalex.org/W3015304056","https://openalex.org/W4380551139","https://openalex.org/W2280377497","https://openalex.org/W4387506531","https://openalex.org/W3174044702","https://openalex.org/W4238433571","https://openalex.org/W2967848559"],"abstract_inverted_index":{"Learning":[0],"from":[1,45,121],"noisy":[2,27,46,104,122,139],"labels":[3,47,120,123,140],"is":[4,131,182],"a":[5,128],"challenge":[6],"that":[7],"arises":[8],"in":[9,72,91,178],"many":[10],"real-world":[11,160],"applications":[12],"where":[13],"training":[14,125],"data":[15],"can":[16,30,63,70],"contain":[17],"incorrect":[18,75],"or":[19,74],"corrupted":[20],"labels.":[21],"When":[22],"fine-tuning":[23,97],"language":[24,100],"models":[25,29,101],"with":[26],"labels,":[28],"easily":[31],"overfit":[32],"the":[33,60,82,92,96,109,115,135,165,173],"label":[34,67,105],"noise,":[35],"leading":[36],"to":[37,102,113,133,164],"decreased":[38],"performance.":[39],"Most":[40],"existing":[41],"methods":[42,56],"for":[43,52,184],"learning":[44],"use":[48],"static":[49],"input":[50],"features":[51],"denoising,":[53],"but":[54],"these":[55],"are":[57],"limited":[58],"by":[59],"information":[61],"they":[62],"provide":[64],"on":[65,151,158,186],"true":[66,119],"distributions":[68,117],"and":[69,124,141,156,170],"result":[71],"biased":[73],"predictions.":[76,106],"In":[77],"this":[78],"work,":[79],"we":[80],"propose":[81],"Dynamics-Enhanced":[83],"Generative":[84],"Model":[85],"(DyGen),":[86],"which":[87],"uses":[88,108],"dynamic":[89],"patterns":[90],"embedding":[93],"space":[94],"during":[95],"process":[98],"of":[99,118,137,149,175],"improve":[103],"DyGen":[107,143],"variational":[110],"auto-encoding":[111],"framework":[112],"infer":[114],"posterior":[116],"dynamics.":[126],"Additionally,":[127],"co-regularization":[129],"mechanism":[130],"used":[132],"minimize":[134],"impact":[136],"potentially":[138],"priors.":[142],"demonstrates":[144],"an":[145],"average":[146],"accuracy":[147],"improvement":[148],"3.10%":[150],"two":[152],"synthetic":[153],"noise":[154,161],"datasets":[155,162],"1.48%":[157],"three":[159],"compared":[163],"previous":[166],"state-of-the-art.":[167],"Extensive":[168],"experiments":[169],"analyses":[171],"show":[172],"effectiveness":[174],"each":[176],"component":[177],"DyGen.":[179],"Our":[180],"code":[181],"available":[183],"reproducibility":[185],"GitHub.":[187]},"counts_by_year":[{"year":2025,"cited_by_count":3},{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":4}],"updated_date":"2026-04-10T15:06:20.359241","created_date":"2023-06-15T00:00:00"}