{"id":"W4385554858","doi":"10.1016/j.eswa.2023.121086","title":"Incorporating global–local neighbors with Gaussian mixture embedding for few-shot knowledge graph completion","year":2023,"lang":"en","type":"article","venue":"Expert Systems with Applications","topic":"Advanced Graph Neural Networks","field":"Computer Science","cited_by":14,"is_retracted":false,"has_abstract":false,"ca_institutions":"York University","funders":"","keywords":"Computer science; Encoder; Embedding; Encoding (memory); Relation (database); Graph; Geospatial analysis; k-nearest neighbors algorithm; Metric (unit); Gaussian; Task (project management); ENCODE; Benchmark (surveying); Data mining; Artificial intelligence; 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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0001924981,0.0003107354,0.0003297489,0.0001589386,0.0007155322,0.0002028272,0.0007643768,0.0001099387,8.051633e-7],"category_scores_gemma":[0.000007229831,0.000235899,0.00007109489,0.003052304,0.0001466848,0.0004176611,0.0001186809,0.0001536472,0.00003732324],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001352703,"about_ca_system_score_gemma":0.00009014639,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00004668021,"about_ca_topic_score_gemma":0.0001061037,"domain_scores_codex":[0.9979477,0.00006820156,0.0003774438,0.0007891828,0.0003106991,0.0005067596],"domain_scores_gemma":[0.9982083,0.0001908025,0.0002896648,0.0008611095,0.0002386854,0.0002114447],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00006967023,0.0001659977,0.001476547,0.0002079696,0.000124582,0.00001582617,0.001535473,0.09950681,0.001084149,0.8659483,0.01494131,0.01492333],"study_design_scores_gemma":[0.001278074,0.0003600495,0.0008912794,0.000425631,0.00002238897,0.0001823731,0.001419016,0.9369671,0.0002470873,0.006952266,0.0503005,0.0009542306],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.0004115659,0.000498854,0.9941642,0.0006800903,0.0002087273,0.002077518,0.00002811987,0.0009785189,0.0009524496],"genre_scores_gemma":[0.9156563,0.00001095649,0.07762056,0.0001363869,0.0003432436,0.005927902,0.0001268306,0.00004443699,0.0001333796],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9165436,"threshold_uncertainty_score":0.9619681,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02462617786089348,"score_gpt":0.3069194756039586,"score_spread":0.2822932977430651,"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."}}