{"id":"W4385287479","doi":"10.1109/icde55515.2023.00370","title":"Adversarial Deep Embedded Clustering: On a better trade-off between Feature Randomness and Feature Drift (Extended abstract)","year":2023,"lang":"en","type":"article","venue":"","topic":"Anomaly Detection Techniques and Applications","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"ca_institutions":"Université du Québec à Montréal","funders":"","keywords":"Discriminator; Feature (linguistics); Randomness; Cluster analysis; Computer science; Autoencoder; Artificial intelligence; Adversarial system; Pattern recognition (psychology); Data mining; Machine learning; Deep learning; 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":[0.0002013116,0.0002163473,0.0002461368,0.000170987,0.000270936,0.0002106287,0.0004910028,0.0002430827,0.00002244167],"category_scores_gemma":[0.00001359746,0.0001795355,0.0001079285,0.0005744171,0.00004839612,0.0002641872,0.0001939558,0.0003717895,0.00005340409],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002374069,"about_ca_system_score_gemma":0.00001989454,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000007416957,"about_ca_topic_score_gemma":0.00001365437,"domain_scores_codex":[0.998678,0.00003219589,0.0001790976,0.0005451288,0.0002505199,0.0003150151],"domain_scores_gemma":[0.9990914,0.0001431933,0.00008221607,0.0005170256,0.00002595647,0.0001402032],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"not_applicable","study_design_scores_codex":[0.000181557,0.0001312672,0.0004974387,0.00006912519,0.000151792,0.00006282868,0.001668099,0.0001282591,0.003770625,0.01473441,0.1139689,0.8646356],"study_design_scores_gemma":[0.0131522,0.0009908394,0.3376619,0.0001645486,0.0001666627,0.0001602808,0.0005262388,0.1675691,0.03816239,0.01918703,0.4193538,0.002905138],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.0558201,0.00006547652,0.8859292,0.04264387,0.0004773257,0.001333964,0.00002543146,0.003696574,0.0100081],"genre_scores_gemma":[0.9711233,0.00003815788,0.02442049,0.001202946,0.0004191711,0.0001286264,0.00002727891,0.00002638549,0.002613662],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9153032,"threshold_uncertainty_score":0.7321244,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01266821633079525,"score_gpt":0.2595749829643869,"score_spread":0.2469067666335917,"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."}}