{"id":"W3191294170","doi":"","title":"HNHN: Hypergraph Networks With Hyperedge Neurons","year":2020,"lang":"en","type":"article","venue":"International Conference on Machine Learning","topic":"Advanced Graph Neural Networks","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":true,"ca_institutions":"Université de Montréal","funders":"","keywords":"Hypergraph; Normalization (sociology); Cardinality (data modeling); Computer science; Representation (politics); Convolution (computer science); Theoretical computer science; Nonlinear system; Artificial intelligence; Pattern recognition (psychology); Artificial neural network; Data mining; Mathematics; Discrete mathematics","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":[0.000804966,0.000766494,0.0005564531,0.00124371,0.000420382,0.001001208,0.001689064,0.001187366,0.002578351],"category_scores_gemma":[0.003132701,0.0004326729,0.0006932704,0.001677212,0.0007770053,0.002810823,0.001404371,0.001512326,0.0009551197],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001080285,"about_ca_system_score_gemma":0.0007504402,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.004714233,"about_ca_topic_score_gemma":0.009026483,"domain_scores_codex":[0.9994876,0.0001837794,0.00002232967,0.0001583555,0.00009851711,0.00004937145],"domain_scores_gemma":[0.9992313,0.000298894,0.00008615167,0.000187828,0.0001417907,0.00005406923],"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":[0.0002579034,0.0001619781,0.003118657,0.0003386658,0.0002004824,0.0002058665,0.0002082744,0.4608194,0.01348588,0.0711098,0.0200469,0.4300463],"study_design_scores_gemma":[0.000009969901,0.00003314877,0.0004488268,0.0000187925,0.00001708346,0.00004908185,0.00002377603,0.9513888,0.002729002,0.04141374,0.003853038,0.00001483035],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.02437759,0.0005353938,0.9680858,0.0004843236,0.00008724781,0.0001017776,0.0009324036,0.002368331,0.003027112],"genre_scores_gemma":[0.4825006,0.00113192,0.4983452,0.001015418,0.0001636567,0.000482255,0.004434337,0.0004292699,0.01149721],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.004714233,"threshold_uncertainty_score":0.009373546,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03417326791921486,"score_gpt":0.2582142654043678,"score_spread":0.2240409974851529,"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."}}