{"id":"W4386634632","doi":"10.1109/tpami.2023.3302150","title":"Information Bottleneck and Aggregated Learning","year":2023,"lang":"en","type":"article","venue":"IEEE Transactions on Pattern Analysis and Machine Intelligence","topic":"Domain Adaptation and Few-Shot Learning","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":true,"ca_institutions":"National Research Council Canada; University of Ottawa","funders":"National Key Research and Development Program of China; Fundamental Research Funds for the Central Universities; State Key Laboratory of Software Development Environment","keywords":"Information bottleneck method; Learning vector quantization; Artificial intelligence; Computer science; Competitive learning; Artificial neural network; Machine learning; Instance-based learning; Vector quantization; Feature learning; Semi-supervised learning; Quantization (signal processing); Contextual image classification; Pattern recognition (psychology); Image (mathematics); Algorithm; Mutual information","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":[0.004363865,0.0008340882,0.001982663,0.001204763,0.0007343335,0.002299943,0.002609573,0.001751909,0.002507797],"category_scores_gemma":[0.01678421,0.000523344,0.0008273665,0.001402979,0.002459826,0.005484536,0.003543886,0.002222908,0.0004733629],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001837643,"about_ca_system_score_gemma":0.001242434,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002601431,"about_ca_topic_score_gemma":0.001280259,"domain_scores_codex":[0.997516,0.0008760381,0.0001171176,0.0006164926,0.0006400131,0.0002343091],"domain_scores_gemma":[0.9929484,0.004297609,0.0006202261,0.0008903396,0.000924616,0.000318821],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.0001744434,0.0001563529,0.001854737,0.0003282931,0.0002344489,0.000198839,0.0003047891,0.4585661,0.002147453,0.442993,0.003650425,0.08939112],"study_design_scores_gemma":[0.000009523121,0.00004007931,0.0001641876,0.00001388694,0.0000136504,0.00002918912,0.00001590365,0.73967,0.0005229731,0.2586786,0.0008317958,0.00001014812],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.01911522,0.001055293,0.9757607,0.0007597351,0.00007949674,0.00002831615,0.00008245206,0.0001959939,0.002922833],"genre_scores_gemma":[0.8566476,0.001412112,0.1354991,0.00063851,0.0004298034,0.0001864684,0.000457824,0.0001457715,0.004582713],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.004363865,"threshold_uncertainty_score":0.02307862,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01830419734807983,"score_gpt":0.2581165396701066,"score_spread":0.2398123423220267,"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."}}