{"id":"W4387940089","doi":"10.1137/21m1465056","title":"Understanding Graph Neural Networks with Generalized Geometric Scattering Transforms","year":2023,"lang":"en","type":"article","venue":"SIAM Journal on Mathematics of Data Science","topic":"Advanced Graph Neural Networks","field":"Computer Science","cited_by":6,"is_retracted":false,"has_abstract":true,"ca_institutions":"Université de Montréal; Mila - Quebec Artificial Intelligence Institute","funders":"Fonds de recherche du Québec – Nature et technologies; Institut de Valorisation des Données; National Institutes of Health; National Science Foundation","keywords":"Scattering; Graph; Deep learning; Computer science; Theoretical computer science; Wavelet; Stability (learning theory); Graph theory; Wavelet transform; Convolutional neural network; Artificial intelligence; Artificial neural network; Algorithm; Topology (electrical circuits); Mathematics; Machine learning; Combinatorics; Physics; Quantum mechanics","routes":{"ca_aff":true,"ca_fund":true,"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":[0.002145517,0.0002343648,0.0003387399,0.001419284,0.0005899519,0.0004788267,0.005203897,0.00004282331,0.000004766748],"category_scores_gemma":[0.00009803431,0.0001602914,0.00007266129,0.009709214,0.0005263399,0.004362518,0.0006440214,0.000454862,0.00000506691],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00007916766,"about_ca_system_score_gemma":0.00008569923,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":8.860886e-7,"about_ca_topic_score_gemma":0.000002113748,"domain_scores_codex":[0.9967142,0.00003493427,0.0005564761,0.0005536329,0.00138736,0.000753431],"domain_scores_gemma":[0.9974511,0.000325022,0.0004476041,0.001389269,0.0001113648,0.0002756929],"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":[0.00005419679,0.0002210255,0.00050558,0.0001479342,0.00008301455,0.0003057376,0.0008870489,0.8485771,0.004124921,0.1203351,0.0009872484,0.02377109],"study_design_scores_gemma":[0.0004893548,0.0002739527,0.0002729576,0.0001999994,0.00001252547,0.0003917083,0.0001447721,0.9725388,0.0004066248,0.02498363,0.00002127277,0.0002644446],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.05124398,0.00005931374,0.9473851,0.0005048424,0.0003571624,0.0001626213,0.000007738096,0.0001240412,0.0001552277],"genre_scores_gemma":[0.8388094,0.0003055343,0.1606672,0.0001129763,0.00006617247,0.000002363513,0.000004656047,0.0000205125,0.00001113764],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.7875655,"threshold_uncertainty_score":0.9670222,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1583805048980607,"score_gpt":0.3184821017645857,"score_spread":0.1601015968665251,"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."}}