{"id":"W4390636011","doi":"10.1016/j.neunet.2024.106112","title":"Preserving domain private information via mutual information maximization","year":2024,"lang":"en","type":"article","venue":"Neural Networks","topic":"Domain Adaptation and Few-Shot Learning","field":"Computer Science","cited_by":9,"is_retracted":false,"has_abstract":false,"ca_institutions":"University of British Columbia; University of British Columbia Hospital","funders":"Mitacs","keywords":"Mutual information; Computer science; Artificial intelligence; Domain (mathematical analysis); Generalization; Divergence (linguistics); Maximization; Pattern recognition (psychology); Machine learning; Mathematics; Mathematical optimization","routes":{"ca_aff":true,"ca_fund":true,"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":["scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.0003292621,0.0001400325,0.00009807614,0.0002035557,0.0001780739,0.001247237,0.0004350246,0.00009733408,0.00004741018],"category_scores_gemma":[0.00004184829,0.0001315919,0.00005548664,0.0007271622,0.00002046985,0.00940564,0.000201707,0.0002958092,0.0002265765],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00005272544,"about_ca_system_score_gemma":0.00002199009,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000006848752,"about_ca_topic_score_gemma":0.000001663533,"domain_scores_codex":[0.9987801,0.00008026267,0.0003879835,0.0001483668,0.0003230067,0.0002802222],"domain_scores_gemma":[0.9993819,0.00008358043,0.0001116993,0.0002650424,0.00007238611,0.00008540476],"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":[0.00001230353,0.000005223648,0.0001180413,0.00004302598,0.00001147498,0.000004456187,0.002342232,0.4648508,0.00002129237,0.049861,0.002937821,0.4797923],"study_design_scores_gemma":[0.000162349,0.0000315663,0.0009348492,0.00002763767,0.000002878863,0.00001845272,0.00003260005,0.9158786,0.00001039824,0.001459182,0.08130375,0.0001377573],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.003867722,0.00009762556,0.9891298,0.00089093,0.001237301,0.0002149741,9.180757e-7,0.0006835065,0.003877236],"genre_scores_gemma":[0.9752692,0.00002726979,0.02269739,0.001548526,0.0002031403,0.00002474216,0.0001220138,0.000009795366,0.00009793615],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9714015,"threshold_uncertainty_score":0.9997895,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.00727167156067342,"score_gpt":0.2112831524705192,"score_spread":0.2040114809098457,"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."}}