{"id":"W2921087533","doi":"10.1016/j.neunet.2021.10.008","title":"Interpolation Consistency Training for Semi-supervised Learning","year":2019,"lang":"en","type":"preprint","venue":"Neural Networks","topic":"Domain Adaptation and Few-Shot Learning","field":"Computer Science","cited_by":137,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"Finnish Center for Artificial Intelligence; Academy of Finland; Compute Canada","keywords":"Overfitting; Computer science; Interpolation (computer graphics); Regularization (linguistics); Benchmark (surveying); Machine learning; Artificial intelligence; Artificial neural network; Consistency (knowledge bases); Extrapolation; Mathematics; Statistics","routes":{"ca_aff":false,"ca_fund":true,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.004467614,0.001066254,0.001438334,0.0009988934,0.0005676232,0.001003971,0.003053057,0.001510934,0.003144478],"category_scores_gemma":[0.016142,0.0006571336,0.0008285003,0.001054929,0.002078861,0.002340228,0.003147985,0.003481753,0.001024679],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0009177965,"about_ca_system_score_gemma":0.001471066,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00143226,"about_ca_topic_score_gemma":0.001918325,"domain_scores_codex":[0.997667,0.000989691,0.0001081211,0.0004804431,0.0006453623,0.0001094947],"domain_scores_gemma":[0.9931386,0.003696861,0.0005014524,0.001563286,0.0008826988,0.0002169582],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0003496372,0.0002627978,0.002055375,0.0003585825,0.000182281,0.0001425225,0.0002087564,0.6247749,0.008811783,0.0737801,0.008247771,0.2808255],"study_design_scores_gemma":[0.000009727267,0.00003575134,0.0001032883,0.00001116216,0.000004205924,0.00002483367,0.000005491919,0.9729149,0.001580106,0.02459596,0.000707739,0.000006910518],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.003195301,0.0001187185,0.9954373,0.00008796832,0.00002569674,0.00002872672,0.00004583871,0.0005725155,0.0004880166],"genre_scores_gemma":[0.3093073,0.0003184316,0.6853324,0.0004809081,0.0002377889,0.0004159405,0.0008561019,0.0005217389,0.002529382],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.004467614,"threshold_uncertainty_score":0.02362734,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.05758556039426875,"score_gpt":0.2817844642051455,"score_spread":0.2241989038108768,"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."}}