{"id":"W4390673744","doi":"10.1016/j.patcog.2024.110264","title":"Edge-labeling based modified gated graph network for few-shot learning","year":2024,"lang":"en","type":"article","venue":"Pattern Recognition","topic":"Domain Adaptation and Few-Shot Learning","field":"Computer Science","cited_by":24,"is_retracted":false,"has_abstract":false,"ca_institutions":"Toronto Metropolitan University","funders":"National Natural Science Foundation of China","keywords":"Computer science; Graph; Benchmark (surveying); Node (physics); Enhanced Data Rates for GSM Evolution; Convolutional neural network; Feature learning; Artificial intelligence; Pattern recognition (psychology); Theoretical computer science","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":[0.0005694697,0.00101046,0.001755791,0.001253724,0.0006311791,0.0007127832,0.003405222,0.002109864,0.002972426],"category_scores_gemma":[0.002230109,0.0005155007,0.0008348424,0.001454593,0.0008397643,0.001904233,0.001595339,0.001755027,0.000847269],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0009435203,"about_ca_system_score_gemma":0.001152893,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.01124743,"about_ca_topic_score_gemma":0.01457837,"domain_scores_codex":[0.9994843,0.0001026831,0.00001973973,0.0002295329,0.00009245656,0.00007118972],"domain_scores_gemma":[0.999134,0.0003810925,0.00005969902,0.0001598183,0.0001861795,0.00007925295],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0003816039,0.000336503,0.001593532,0.0002383802,0.0001536359,0.0002141541,0.000131633,0.5209483,0.01876745,0.01599683,0.00740273,0.4338354],"study_design_scores_gemma":[0.00000436503,0.0000179871,0.0001175047,0.000003629084,0.000007786993,0.00001807694,0.00000517214,0.9942964,0.0009349367,0.004322852,0.0002656531,0.000005660379],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.01791853,0.0003580172,0.9794633,0.0001592185,0.00005799791,0.0000570189,0.0002103439,0.0009251434,0.000850361],"genre_scores_gemma":[0.6196811,0.0006681079,0.3668575,0.0005612605,0.0001269351,0.0003270405,0.002697441,0.000343056,0.008737594],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.01124743,"threshold_uncertainty_score":0.0223639,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.06803367941487512,"score_gpt":0.2818680301077588,"score_spread":0.2138343506928837,"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."}}