{"id":"W3175853876","doi":"10.1609/aaai.v35i11.17159","title":"Online Class-Incremental Continual Learning with Adversarial Shapley Value","year":2021,"lang":"en","type":"article","venue":"Proceedings of the AAAI Conference on Artificial Intelligence","topic":"Domain Adaptation and Few-Shot Learning","field":"Computer Science","cited_by":175,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Toronto","funders":"","keywords":"Forgetting; Computer science; Machine learning; Class (philosophy); Artificial intelligence; Adversarial system; Memory footprint; Task (project management); Stability (learning theory); Engineering","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":[0.0004706404,0.0002443247,0.0002919426,0.00009852899,0.0003168762,0.0003923382,0.001225809,0.00008789093,0.0001726643],"category_scores_gemma":[0.0006107389,0.0001885151,0.0001183061,0.000750978,0.000243184,0.0005103247,0.0004346994,0.0005935949,0.00006838069],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00006177743,"about_ca_system_score_gemma":0.0002645573,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00003779404,"about_ca_topic_score_gemma":0.00003140723,"domain_scores_codex":[0.997712,0.00005522826,0.000502348,0.0005952836,0.0007438025,0.0003913042],"domain_scores_gemma":[0.9982449,0.0001285492,0.0004177025,0.0002394463,0.0008489077,0.0001205417],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.0001254132,0.0002613823,0.0006061259,0.00002139856,0.00003820899,0.000005816327,0.002135929,0.0009308601,0.06220854,0.8917853,0.00007670672,0.04180428],"study_design_scores_gemma":[0.0002985714,0.0007603991,0.001197945,0.0005024036,0.0000441896,0.00005181766,0.009219522,0.3533287,0.6083484,0.02244659,0.003146592,0.0006549201],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.7457383,0.00006848683,0.1746529,0.01187586,0.001249659,0.0007893791,0.00001540821,0.0004866079,0.06512337],"genre_scores_gemma":[0.9861624,0.00001940694,0.01218229,0.0004503662,0.0001141425,0.000008949052,0.000003556518,0.00001650158,0.001042396],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.8693388,"threshold_uncertainty_score":0.7687421,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.05678288123306853,"score_gpt":0.2831853711185195,"score_spread":0.226402489885451,"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."}}