{"id":"W4382457524","doi":"10.1609/aaai.v37i1.25150","title":"RankDNN: Learning to Rank for Few-Shot Learning","year":2023,"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":26,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"Science and Technology Commission of Shanghai Municipality; Fudan University","keywords":"Computer science; Ranking (information retrieval); Artificial intelligence; Learning to rank; Ranking SVM; Artificial neural network; Pipeline (software); Pattern recognition (psychology); Benchmark (surveying); Feature (linguistics); Machine learning; Rank (graph theory); Margin (machine learning); Domain (mathematical analysis); Similarity (geometry); Deep learning; Image (mathematics); Mathematics","routes":{"ca_aff":false,"ca_fund":false,"ca_venue":false,"about_ca":true,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001827004,0.002191785,0.00224633,0.001997485,0.0008644591,0.00190963,0.004957882,0.002285556,0.008358046],"category_scores_gemma":[0.007374166,0.0009170635,0.001133632,0.001535294,0.0009337586,0.004076856,0.00259589,0.003229605,0.004665534],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001752469,"about_ca_system_score_gemma":0.002286095,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0112485,"about_ca_topic_score_gemma":0.01808636,"domain_scores_codex":[0.9985077,0.0002721651,0.00009416535,0.0005094584,0.0004423936,0.0001741333],"domain_scores_gemma":[0.9983707,0.0005152121,0.0001259619,0.0004387521,0.0004045393,0.0001448796],"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":[0.000470894,0.0004218823,0.002364893,0.0005190907,0.000207375,0.0001557738,0.0001181814,0.09839203,0.006169274,0.01261083,0.04702151,0.8315482],"study_design_scores_gemma":[0.00004935998,0.0001290092,0.0003634093,0.00003665202,0.00003430379,0.00009486813,0.00003343046,0.9721074,0.004082028,0.01789401,0.005140147,0.0000353994],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.01613037,0.002040794,0.9615345,0.0004389146,0.000364394,0.0003472567,0.002001392,0.01279638,0.004345909],"genre_scores_gemma":[0.3233396,0.001388684,0.6365865,0.001500671,0.0005164287,0.0007822272,0.01374768,0.001456567,0.02068177],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.0112485,"threshold_uncertainty_score":0.02796042,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1333800895186134,"score_gpt":0.3341693147696342,"score_spread":0.2007892252510208,"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."}}