{"id":"W4317036100","doi":"10.1145/3576045","title":"Distilled Meta-learning for Multi-Class Incremental Learning","year":2023,"lang":"en","type":"article","venue":"ACM Transactions on Multimedia Computing Communications and Applications","topic":"Domain Adaptation and Few-Shot Learning","field":"Computer Science","cited_by":9,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Ottawa","funders":"Natural Science Foundation of Jiangsu Province; National Natural Science Foundation of China","keywords":"Forgetting; Meta learning (computer science); Computer science; Artificial intelligence; Machine learning; Incremental learning; Benchmark (surveying); Task (project management); Class (philosophy); Active learning (machine learning); Engineering; Psychology","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":["metaepi_narrow","sts"],"consensus_categories":[],"category_scores_codex":[0.0008121271,0.0002672547,0.0003299351,0.0003850482,0.002956039,0.0002686973,0.00170644,0.0001023239,0.00001722797],"category_scores_gemma":[0.0001946477,0.0002742102,0.0002247869,0.001177788,0.000189192,0.0002502714,0.0002214932,0.0006835001,0.0001311566],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00005694003,"about_ca_system_score_gemma":0.00005509759,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00003354202,"about_ca_topic_score_gemma":0.0000213422,"domain_scores_codex":[0.998008,0.0002847077,0.0004923153,0.0005764938,0.0002356328,0.0004028943],"domain_scores_gemma":[0.9951773,0.002638057,0.0002293978,0.001582207,0.0001865008,0.000186505],"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":[0.00001212617,0.0004746926,0.0002318028,0.0000442312,0.0005978787,7.002924e-7,0.00324916,0.05680897,0.001706311,0.01430543,0.00009123974,0.9224774],"study_design_scores_gemma":[0.0008248484,0.00006956703,0.000577163,0.00001536378,0.0001480165,0.000004867963,0.000646632,0.9157922,0.0001303332,0.0003219195,0.08119403,0.0002750379],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.000662647,0.0001969282,0.9937613,0.002848535,0.00007685588,0.0009505,0.00001369661,0.001224806,0.0002647279],"genre_scores_gemma":[0.5736518,0.000419877,0.4238212,0.0001557299,0.00003292544,0.001062667,0.0001357367,0.00003377107,0.0006863529],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9222024,"threshold_uncertainty_score":0.999971,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1055085410575087,"score_gpt":0.3442216972377931,"score_spread":0.2387131561802844,"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."}}