{"id":"W4385768183","doi":"10.24963/ijcai.2023/108","title":"IMF: Integrating Matched Features Using Attentive Logit in Knowledge Distillation","year":2023,"lang":"en","type":"article","venue":"","topic":"Advanced Neural Network Applications","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":true,"ca_institutions":"Kootenay Association for Science & Technology","funders":"Institute for Information and Communications Technology Promotion; Ministry of Science and ICT, South Korea; Sungkyunkwan University","keywords":"Softmax function; Computer science; Margin (machine learning); Distillation; Inference; Feature (linguistics); Machine learning; Artificial intelligence; Logit; Matching (statistics); Representation (politics); Pattern recognition (psychology); Artificial neural network; Mathematics; Statistics","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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0001108374,0.0000944053,0.0001023155,0.0001296375,0.00009856415,0.00006472725,0.0003191404,0.00003807154,0.000004579939],"category_scores_gemma":[0.00004188039,0.00008132266,0.00002913142,0.001533821,0.00002436203,0.0003204898,0.0002521479,0.0001217649,0.00009669415],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00007255615,"about_ca_system_score_gemma":0.00001985748,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000027542,"about_ca_topic_score_gemma":0.0001686075,"domain_scores_codex":[0.999192,0.00003556413,0.0001649924,0.0003044828,0.00008680231,0.0002161641],"domain_scores_gemma":[0.9994227,0.0001766499,0.00005572157,0.0002640621,0.00004614194,0.0000347114],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00001183431,0.0001384964,0.02194923,0.00004154318,0.00002430953,0.00003621676,0.006409696,0.07044586,0.05746541,0.6074458,0.004339523,0.2316921],"study_design_scores_gemma":[0.0001415838,0.00001017751,0.05775639,0.00003283571,0.000001916979,0.000006226052,0.0002130006,0.9201455,0.001809421,0.01932096,0.0003824483,0.0001795615],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1282347,0.00004118004,0.8665741,0.0009596393,0.0001519424,0.000233595,0.000001028968,0.0004969513,0.003306828],"genre_scores_gemma":[0.9342368,0.000006057246,0.0650442,0.00004688639,0.00005594019,0.00002078591,0.000006157341,0.00000773318,0.0005754479],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.8496996,"threshold_uncertainty_score":0.3316242,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.04652173233494302,"score_gpt":0.333634815200821,"score_spread":0.287113082865878,"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."}}