{"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":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0005564004,0.0003579198,0.0004688232,0.0001556844,0.0002641233,0.0005615254,0.0009185547,0.0003951331,0.00003458311],"category_scores_gemma":[0.0001872176,0.0003746277,0.0003086915,0.000203174,0.00004379754,0.0003142231,0.0006867012,0.001491225,0.00001853252],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00005775395,"about_ca_system_score_gemma":0.0001160014,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000009229972,"about_ca_topic_score_gemma":0.000004348501,"domain_scores_codex":[0.9975793,0.0002414788,0.0005230774,0.0008459498,0.0002784672,0.0005317785],"domain_scores_gemma":[0.9981214,0.0005873639,0.0004139561,0.0005807694,0.0001638829,0.0001325596],"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":[0.0000254827,0.00001128284,0.0004757714,0.00006301937,0.00003478185,0.000004100871,0.002234153,0.8475692,0.00005285677,0.00322703,0.0005229672,0.1457793],"study_design_scores_gemma":[0.0004902333,0.00009735827,0.000469317,0.0001591593,0.00001854719,0.000009347257,0.000222219,0.9927911,0.000002933171,0.0007881967,0.004559543,0.0003920936],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.004645504,0.0004843421,0.9854808,0.0005905183,0.003598033,0.0007286736,0.000002334275,0.0004983263,0.003971399],"genre_scores_gemma":[0.9672928,0.0000361168,0.02994941,0.0008910761,0.0005447831,0.00008203545,0.0001266854,0.00004690671,0.00103014],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9626473,"threshold_uncertainty_score":0.9998705,"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."}}