{"id":"W2962851649","doi":"","title":"Distributed Maximization of \"Submodular plus Diversity\" Functions for Multi-label Feature Selection on Huge Datasets","year":2019,"lang":"en","type":"article","venue":"International Conference on Artificial Intelligence and Statistics","topic":"Text and Document Classification Technologies","field":"Computer Science","cited_by":3,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of British Columbia","funders":"","keywords":"Submodular set function; Feature selection; Computer science; Redundancy (engineering); Automatic summarization; Feature (linguistics); Greedy algorithm; Maximization; Optimization problem; Mathematical optimization; Data mining; Function (biology); Artificial intelligence; Machine learning; Algorithm; Mathematics","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":[0.0001313879,0.0001237428,0.0001316086,0.0001731873,0.0001648462,0.0001398302,0.0004569065,0.00008474519,0.00006288245],"category_scores_gemma":[0.0002475445,0.0001200874,0.0000240107,0.0001828932,0.0000757879,0.0002562959,0.000159653,0.000119719,0.00004970618],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0000677104,"about_ca_system_score_gemma":0.00005506653,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00002433571,"about_ca_topic_score_gemma":0.00003895972,"domain_scores_codex":[0.9989989,0.00002726116,0.000233461,0.0003364311,0.000271851,0.0001320885],"domain_scores_gemma":[0.999029,0.0001666433,0.0001767409,0.0002135584,0.0003757067,0.00003833722],"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":[0.0001001478,0.0001347465,0.0002293778,0.00001056965,0.00002258747,6.274144e-7,0.0001033013,0.0006887048,0.0009577684,0.9185342,0.001162918,0.07805504],"study_design_scores_gemma":[0.0001516387,0.0003794656,0.000767373,0.00002982837,0.000009602159,0.000001533848,0.0002725579,0.9255025,0.005455711,0.06663711,0.0006433763,0.000149335],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.002328874,0.00000537548,0.9934265,0.001216021,0.0004877386,0.000290043,0.001999073,0.00007749857,0.0001688964],"genre_scores_gemma":[0.9091585,0.00005293087,0.08908912,0.00009781445,0.00002303478,0.00002159787,0.00106421,0.000005809698,0.000487002],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9248137,"threshold_uncertainty_score":0.4897022,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1479739312535318,"score_gpt":0.3478739285134115,"score_spread":0.1998999972598797,"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."}}