{"id":"https://openalex.org/W7123350376","doi":"https://doi.org/10.1109/tkde.2026.3650911","title":"Class-Aware Multi-Granularity Co-Diffusion Models for Learning With Noisy Labels on Imbalanced Datasets","display_name":"Class-Aware Multi-Granularity Co-Diffusion Models for Learning With Noisy Labels on Imbalanced Datasets","publication_year":2026,"publication_date":"2026-01-12","ids":{"openalex":"https://openalex.org/W7123350376","doi":"https://doi.org/10.1109/tkde.2026.3650911"},"language":null,"primary_location":{"id":"doi:10.1109/tkde.2026.3650911","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tkde.2026.3650911","pdf_url":null,"source":{"id":"https://openalex.org/S30698027","display_name":"IEEE Transactions on Knowledge and Data Engineering","issn_l":"1041-4347","issn":["1041-4347","1558-2191","2326-3865"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320439","host_organization_name":"IEEE Computer Society","host_organization_lineage":["https://openalex.org/P4310320439","https://openalex.org/P4310319808"],"host_organization_lineage_names":["IEEE Computer Society","Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Knowledge and Data Engineering","raw_type":"journal-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":false,"oa_status":"closed","oa_url":null,"any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5122853920","display_name":"Senyu Hou","orcid":null},"institutions":[{"id":"https://openalex.org/I181877577","display_name":"Shanxi University","ror":"https://ror.org/03y3e3s17","country_code":"CN","type":"education","lineage":["https://openalex.org/I181877577"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Senyu Hou","raw_affiliation_strings":["School of Computer and Information Technology, Shanxi University, Taiyuan, China"],"raw_orcid":"https://orcid.org/0009-0008-4059-4292","affiliations":[{"raw_affiliation_string":"School of Computer and Information Technology, Shanxi University, Taiyuan, China","institution_ids":["https://openalex.org/I181877577"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5067305206","display_name":"Gaoxia Jiang","orcid":"https://orcid.org/0000-0002-2343-1132"},"institutions":[{"id":"https://openalex.org/I181877577","display_name":"Shanxi University","ror":"https://ror.org/03y3e3s17","country_code":"CN","type":"education","lineage":["https://openalex.org/I181877577"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Gaoxia Jiang","raw_affiliation_strings":["School of Computer and Information Technology, Shanxi University, Taiyuan, China"],"raw_orcid":"https://orcid.org/0000-0002-2343-1132","affiliations":[{"raw_affiliation_string":"School of Computer and Information Technology, Shanxi University, Taiyuan, China","institution_ids":["https://openalex.org/I181877577"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Yaqing Guo","orcid":"https://orcid.org/0000-0001-6243-8049"},"institutions":[{"id":"https://openalex.org/I181877577","display_name":"Shanxi University","ror":"https://ror.org/03y3e3s17","country_code":"CN","type":"education","lineage":["https://openalex.org/I181877577"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yaqing Guo","raw_affiliation_strings":["School of Computer and Information Technology, Shanxi University, Taiyuan, China"],"raw_orcid":"https://orcid.org/0000-0001-6243-8049","affiliations":[{"raw_affiliation_string":"School of Computer and Information Technology, Shanxi University, Taiyuan, China","institution_ids":["https://openalex.org/I181877577"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5023346861","display_name":"WenJian Wang","orcid":null},"institutions":[{"id":"https://openalex.org/I181877577","display_name":"Shanxi University","ror":"https://ror.org/03y3e3s17","country_code":"CN","type":"education","lineage":["https://openalex.org/I181877577"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Wenjian Wang","raw_affiliation_strings":["Key Laboratory of Data Intelligence and Cognitive Computing of Shanxi Province, Taiyuan, China"],"raw_orcid":"https://orcid.org/0000-0002-8276-3639","affiliations":[{"raw_affiliation_string":"Key Laboratory of Data Intelligence and Cognitive Computing of Shanxi Province, Taiyuan, China","institution_ids":["https://openalex.org/I181877577"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5122853920"],"corresponding_institution_ids":["https://openalex.org/I181877577"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.07723064,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"38","issue":"3","first_page":"1527","last_page":"1540"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12535","display_name":"Machine Learning and Data Classification","score":0.8080000281333923,"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":0.8080000281333923,"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/T11652","display_name":"Imbalanced Data Classification Techniques","score":0.0471000000834465,"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/T11550","display_name":"Text and Document Classification Technologies","score":0.02070000022649765,"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":0.881600022315979},{"id":"https://openalex.org/keywords/leverage","display_name":"Leverage (statistics)","score":0.6868000030517578},{"id":"https://openalex.org/keywords/discriminative-model","display_name":"Discriminative model","score":0.5224000215530396},{"id":"https://openalex.org/keywords/noise","display_name":"Noise (video)","score":0.43209999799728394},{"id":"https://openalex.org/keywords/deep-learning","display_name":"Deep learning","score":0.4212999939918518},{"id":"https://openalex.org/keywords/noisy-data","display_name":"Noisy data","score":0.4205000102519989},{"id":"https://openalex.org/keywords/data-modeling","display_name":"Data modeling","score":0.38260000944137573},{"id":"https://openalex.org/keywords/interpretability","display_name":"Interpretability","score":0.38190001249313354},{"id":"https://openalex.org/keywords/generative-model","display_name":"Generative model","score":0.3458000123500824}],"concepts":[{"id":"https://openalex.org/C22019652","wikidata":"https://www.wikidata.org/wiki/Q331309","display_name":"Overfitting","level":3,"score":0.881600022315979},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8062999844551086},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.7046999931335449},{"id":"https://openalex.org/C153083717","wikidata":"https://www.wikidata.org/wiki/Q6535263","display_name":"Leverage (statistics)","level":2,"score":0.6868000030517578},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.6696000099182129},{"id":"https://openalex.org/C97931131","wikidata":"https://www.wikidata.org/wiki/Q5282087","display_name":"Discriminative model","level":2,"score":0.5224000215530396},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.43209999799728394},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.4212999939918518},{"id":"https://openalex.org/C2781170535","wikidata":"https://www.wikidata.org/wiki/Q30587856","display_name":"Noisy data","level":2,"score":0.4205000102519989},{"id":"https://openalex.org/C67186912","wikidata":"https://www.wikidata.org/wiki/Q367664","display_name":"Data modeling","level":2,"score":0.38260000944137573},{"id":"https://openalex.org/C2781067378","wikidata":"https://www.wikidata.org/wiki/Q17027399","display_name":"Interpretability","level":2,"score":0.38190001249313354},{"id":"https://openalex.org/C167966045","wikidata":"https://www.wikidata.org/wiki/Q5532625","display_name":"Generative model","level":3,"score":0.3458000123500824},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.33559998869895935},{"id":"https://openalex.org/C163294075","wikidata":"https://www.wikidata.org/wiki/Q581861","display_name":"Noise reduction","level":2,"score":0.3292999863624573},{"id":"https://openalex.org/C29265498","wikidata":"https://www.wikidata.org/wiki/Q7047719","display_name":"Noise measurement","level":3,"score":0.3255000114440918},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3125},{"id":"https://openalex.org/C75684735","wikidata":"https://www.wikidata.org/wiki/Q858810","display_name":"Big data","level":2,"score":0.3061999976634979},{"id":"https://openalex.org/C2777212361","wikidata":"https://www.wikidata.org/wiki/Q5127848","display_name":"Class (philosophy)","level":2,"score":0.30000001192092896},{"id":"https://openalex.org/C150899416","wikidata":"https://www.wikidata.org/wiki/Q1820378","display_name":"Transfer of learning","level":2,"score":0.288100004196167},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.2786000072956085},{"id":"https://openalex.org/C160920958","wikidata":"https://www.wikidata.org/wiki/Q7662746","display_name":"Synthetic data","level":2,"score":0.2766000032424927},{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.27379998564720154},{"id":"https://openalex.org/C39890363","wikidata":"https://www.wikidata.org/wiki/Q36108","display_name":"Generative grammar","level":2,"score":0.26489999890327454},{"id":"https://openalex.org/C2984842247","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep neural networks","level":3,"score":0.2628999948501587},{"id":"https://openalex.org/C169258074","wikidata":"https://www.wikidata.org/wiki/Q245748","display_name":"Random forest","level":2,"score":0.26269999146461487},{"id":"https://openalex.org/C2776760102","wikidata":"https://www.wikidata.org/wiki/Q5139990","display_name":"Code (set theory)","level":3,"score":0.25130000710487366}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/tkde.2026.3650911","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tkde.2026.3650911","pdf_url":null,"source":{"id":"https://openalex.org/S30698027","display_name":"IEEE Transactions on Knowledge and Data Engineering","issn_l":"1041-4347","issn":["1041-4347","1558-2191","2326-3865"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320439","host_organization_name":"IEEE Computer Society","host_organization_lineage":["https://openalex.org/P4310320439","https://openalex.org/P4310319808"],"host_organization_lineage_names":["IEEE Computer Society","Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Knowledge and Data Engineering","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/10","display_name":"Reduced inequalities","score":0.7552440762519836}],"awards":[{"id":"https://openalex.org/G1083341597","display_name":null,"funder_award_id":"U21A20513","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G1335682314","display_name":null,"funder_award_id":"62576201","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G5326762715","display_name":null,"funder_award_id":"62276161","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G7541316960","display_name":null,"funder_award_id":"62406179","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G7776531264","display_name":null,"funder_award_id":"62476157","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":45,"referenced_works":["https://openalex.org/W1921293667","https://openalex.org/W1941659294","https://openalex.org/W2059471177","https://openalex.org/W2118978333","https://openalex.org/W2148143831","https://openalex.org/W2165072487","https://openalex.org/W2167460663","https://openalex.org/W2490662969","https://openalex.org/W2566079294","https://openalex.org/W2763110968","https://openalex.org/W2962933664","https://openalex.org/W2963691377","https://openalex.org/W2964274690","https://openalex.org/W2964292098","https://openalex.org/W2967293034","https://openalex.org/W2981873476","https://openalex.org/W3012492726","https://openalex.org/W3015967287","https://openalex.org/W3035054804","https://openalex.org/W3035682985","https://openalex.org/W3042609801","https://openalex.org/W3050806782","https://openalex.org/W3097526925","https://openalex.org/W3120093105","https://openalex.org/W3141280041","https://openalex.org/W3168547821","https://openalex.org/W3206604724","https://openalex.org/W4254751698","https://openalex.org/W4283819154","https://openalex.org/W4287947470","https://openalex.org/W4288083516","https://openalex.org/W4292387278","https://openalex.org/W4292793914","https://openalex.org/W4312825639","https://openalex.org/W4313068152","https://openalex.org/W4367666062","https://openalex.org/W4384080802","https://openalex.org/W4386071642","https://openalex.org/W4386075893","https://openalex.org/W4393156873","https://openalex.org/W4393160254","https://openalex.org/W4399731114","https://openalex.org/W4402727170","https://openalex.org/W4402753704","https://openalex.org/W4408962448"],"related_works":[],"abstract_inverted_index":{"Data":[0],"quality":[1],"is":[2],"essential":[3],"for":[4,177],"the":[5,37,79,113,138,150,163,174,183,186],"performance":[6],"of":[7,81,166,185],"deep":[8,26],"neural":[9],"networks":[10],"in":[11,31,85,219],"various":[12],"fields.":[13],"However,":[14],"label":[15,46],"noise":[16],"and":[17,73,88,100,210,221],"class":[18,204],"imbalance":[19],"are":[20,123],"common":[21],"data":[22,75,200],"issues,":[23],"which":[24,52,95,180],"cause":[25],"learning":[27,38],"models":[28,84,93,168],"to":[29,105,141,152,172,189,198],"overfit":[30],"real-world":[32,211],"scenarios.":[33,223],"Recent":[34],"research":[35],"solves":[36],"with":[39,66],"noisy":[40,72,190,222],"labels":[41,107,122,155],"(LNL)":[42],"problem":[43,115],"by":[44,125,203],"employing":[45],"correction":[47],"or":[48],"loss":[49,102,196],"adjustment":[50,103],"methods,":[51],"often":[53],"rely":[54],"on":[55,156,207,228],"uncertainty":[56,86,99,136],"estimation.":[57],"Unfortunately,":[58],"these":[59],"methods":[60],"usually":[61],"do":[62],"not":[63],"work":[64],"well":[65,218],"imbalanced":[67,74,220],"datasets.":[68],"To":[69],"address":[70],"both":[71,208],"biases,":[76],"we":[77,111,133,161,193],"analyze":[78],"limitations":[80],"current":[82],"discriminative":[83],"estimation,":[87],"propose":[89],"Class-aware":[90],"Multi-granularity":[91],"Co-Diffusion":[92],"(CaMCoD),":[94],"leverage":[96,162],"a":[97,117,157],"generative":[98],"inconsistency":[101,165],"method":[104,216],"generate":[106,153],"more":[108,143],"robustly.":[109],"Specifically,":[110],"reframe":[112],"LNL":[114],"as":[116],"robust":[118],"diffusion-generative":[119],"process,":[120],"i.e.,":[121],"generated":[124],"gradually":[126],"refining":[127],"an":[128],"initial":[129],"random":[130],"guess.":[131],"First,":[132],"use":[134],"coarse-grained":[135],"from":[137],"diffusion":[139],"model":[140,151,187],"achieve":[142],"accurate":[144],"confidence":[145],"estimates.":[146],"This":[147],"will":[148],"guide":[149],"correct":[154],"broader":[158],"level.":[159],"Then,":[160],"fine-grained":[164],"co-diffusion":[167],"during":[169],"reverse":[170],"denoising":[171],"determine":[173],"learnable":[175],"weight":[176],"each":[178],"sample,":[179],"can":[181],"mitigate":[182],"risk":[184],"overfitting":[188],"samples.":[191],"Finally,":[192],"apply":[194],"class-aware":[195],"adjustments":[197],"reduce":[199],"bias":[201],"caused":[202],"imbalance.":[205],"Experiments":[206],"synthetic":[209],"datasets":[212],"demonstrate":[213],"that":[214],"our":[215,226],"perform":[217],"We":[224],"provide":[225],"code":[227],"GitHub:":[229],"<uri":[230],"xmlns:mml=\"http://www.w3.org/1998/Math/MathML\"":[231],"xmlns:xlink=\"http://www.w3.org/1999/xlink\">https://github.com/SenyuHou/CaMCoD</uri>.":[232]},"counts_by_year":[],"updated_date":"2026-02-13T13:36:01.753593","created_date":"2026-01-14T00:00:00"}