{"id":"W4393160207","doi":"10.1609/aaai.v38i15.29562","title":"Federated Partial Label Learning with Local-Adaptive Augmentation and Regularization","year":2024,"lang":"en","type":"article","venue":"Proceedings of the AAAI Conference on Artificial Intelligence","topic":"Text and Document Classification Technologies","field":"Computer Science","cited_by":8,"is_retracted":false,"has_abstract":true,"ca_institutions":"Canadian Institute for Advanced Research; Carleton University","funders":"","keywords":"Regularization (linguistics); Computer science; Artificial intelligence","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":[0.003032784,0.001207784,0.001866524,0.0007394733,0.001140086,0.00184287,0.003720991,0.001927838,0.002356602],"category_scores_gemma":[0.007944854,0.0006011672,0.001076,0.001387118,0.002003103,0.004953873,0.004671757,0.003098059,0.001325974],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001272516,"about_ca_system_score_gemma":0.002175818,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00272955,"about_ca_topic_score_gemma":0.005511069,"domain_scores_codex":[0.9968929,0.001076604,0.0001195243,0.001015931,0.0006748599,0.0002200624],"domain_scores_gemma":[0.99518,0.001433999,0.0003527782,0.002119518,0.0007148382,0.0001987324],"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":[0.0006575271,0.0004734568,0.003173647,0.0002043427,0.0001185193,0.0002728387,0.0005854568,0.445411,0.01576529,0.0304363,0.01136856,0.4915331],"study_design_scores_gemma":[0.00002154783,0.00004237893,0.0001128048,0.000007326351,0.000008614295,0.00004813551,0.00003552673,0.9804028,0.003229422,0.01485746,0.00122027,0.00001371738],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.01287931,0.0001188301,0.9837489,0.0002122833,0.00002979705,0.00004951716,0.00008590259,0.002116072,0.0007593456],"genre_scores_gemma":[0.5213465,0.0001278651,0.4713597,0.000560092,0.0001004985,0.0003237421,0.0008280626,0.0004411071,0.004912453],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.003720991,"threshold_uncertainty_score":0.01603913,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.06017459565364345,"score_gpt":0.2866706267842369,"score_spread":0.2264960311305934,"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."}}