{"id":"W4206630568","doi":"10.1109/bigdata52589.2021.9671816","title":"MixNN: Combating Noisy Labels in Deep Learning by Mixing with Nearest Neighbors","year":2021,"lang":"en","type":"article","venue":"2021 IEEE International Conference on Big Data (Big Data)","topic":"Machine Learning and Data Classification","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"McMaster University","funders":"","keywords":"Overfitting; Computer science; Artificial intelligence; Pattern recognition (psychology); Machine learning; Noise (video); Deep learning; Transfer of learning; Ground truth; Representation (politics); Artificial neural network; Image (mathematics)","routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":false},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0038751,0.00186652,0.001910947,0.001342729,0.0009911617,0.001566406,0.003220503,0.002239936,0.001297899],"category_scores_gemma":[0.009891439,0.000818743,0.0008955307,0.001429723,0.001580318,0.003938843,0.003615826,0.002773775,0.0006915867],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001353971,"about_ca_system_score_gemma":0.001092017,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.005091872,"about_ca_topic_score_gemma":0.007606315,"domain_scores_codex":[0.9976413,0.0007018275,0.0001292968,0.0006826449,0.0006598167,0.000185148],"domain_scores_gemma":[0.997024,0.001088832,0.0004069054,0.0006943519,0.0006202839,0.00016555],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0007561803,0.0004596545,0.006615926,0.0002962112,0.0003148986,0.0001788955,0.0004613682,0.4250126,0.01264467,0.01266636,0.007010465,0.5335828],"study_design_scores_gemma":[0.00001332681,0.00005939705,0.0002244974,0.00001454075,0.00001833721,0.00003148236,0.00002355459,0.9898005,0.00344045,0.005557631,0.0008011865,0.00001508436],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.04405528,0.000721738,0.9512994,0.0002792919,0.0001074265,0.00008048678,0.0001338048,0.002295762,0.001026879],"genre_scores_gemma":[0.56572,0.000444081,0.4265761,0.0006986124,0.000164932,0.0002571537,0.001156022,0.0004657323,0.004517316],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.005091872,"threshold_uncertainty_score":0.02049375,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1969339514472645,"score_gpt":0.3369666703159024,"score_spread":0.1400327188686379,"validation_status":"score_only:v0-immature-baseline","note":"Baseline scores from an immature model (maturity gate not passed). Scores rank; they never assert a category."}}