{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001389145,0.001236594,0.002411846,0.001856709,0.0007997174,0.001297949,0.003363461,0.002963742,0.002808483],"category_scores_gemma":[0.006387613,0.0009712818,0.001611768,0.001814558,0.00120234,0.003794001,0.002448794,0.002762509,0.001322304],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0008172861,"about_ca_system_score_gemma":0.0013081,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0170483,"about_ca_topic_score_gemma":0.02420242,"domain_scores_codex":[0.9988876,0.0002698928,0.00005633427,0.000446369,0.0002366066,0.0001032189],"domain_scores_gemma":[0.9975299,0.001351626,0.0001625892,0.0004310198,0.0003723213,0.0001525441],"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":[0.0004342129,0.000471677,0.001466307,0.0003752628,0.0002869928,0.0001948939,0.0003429384,0.5949646,0.006361051,0.01932615,0.006774068,0.3690019],"study_design_scores_gemma":[0.000005361144,0.00001826608,0.00008681748,0.000005616668,0.0000114904,0.00001738146,0.00001293681,0.9914587,0.0004087207,0.007682477,0.0002843656,0.000007882746],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.01362471,0.0004337741,0.984124,0.0001727036,0.00005506275,0.00005699143,0.0001372781,0.0007770529,0.0006184424],"genre_scores_gemma":[0.5392947,0.0006918756,0.4493071,0.0004638211,0.0002365618,0.0002514686,0.002375846,0.000517234,0.006861288],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.0170483,"threshold_uncertainty_score":0.03389812,"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."}}