{"id":"W4372267823","doi":"10.1109/icassp49357.2023.10095900","title":"Sparse Graph Learning with Spectrum Prior for Deep Graph Convolutional Networks","year":2023,"lang":"en","type":"article","venue":"","topic":"Advanced Graph Neural Networks","field":"Computer Science","cited_by":4,"is_retracted":false,"has_abstract":true,"ca_institutions":"York University","funders":"Natural Sciences and Engineering Research Council of Canada; National Natural Science Foundation of China","keywords":"Laplacian matrix; Graph; Computer science; Smoothing; Subspace topology; Algorithm; Matrix completion; Pairwise comparison; Graph bandwidth; Artificial intelligence; Theoretical computer science; Voltage graph; Line graph; Gaussian","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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0006332018,0.0007781687,0.0006249323,0.0006129295,0.0003416826,0.0006282239,0.001194221,0.000950428,0.001410797],"category_scores_gemma":[0.00280247,0.0004269697,0.000520431,0.000710101,0.000979465,0.001768146,0.0009888852,0.001801825,0.0005082241],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001103668,"about_ca_system_score_gemma":0.0009719873,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.006237108,"about_ca_topic_score_gemma":0.01143979,"domain_scores_codex":[0.9997167,0.00007708417,0.00001105282,0.00007410829,0.00009083695,0.00003018875],"domain_scores_gemma":[0.9992881,0.0003346434,0.00007784786,0.0001339173,0.0001157714,0.00004968483],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.00006760791,0.00006880801,0.0006214848,0.00006738576,0.00003189618,0.00006097697,0.00006579603,0.8581667,0.00845512,0.04562851,0.002679304,0.08408636],"study_design_scores_gemma":[0.000001930939,0.000006445597,0.00003417299,0.000001846219,0.000001490827,0.000005477798,0.00000251514,0.9915661,0.0005693687,0.00762396,0.0001848553,0.000001882862],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.01127805,0.00007992541,0.9874577,0.0001203556,0.00001408748,0.00001321085,0.00004504603,0.0004676233,0.0005239533],"genre_scores_gemma":[0.6074571,0.0003568984,0.3871923,0.0002662451,0.00006556691,0.0001263797,0.0006447088,0.0003524764,0.003538367],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.006237108,"threshold_uncertainty_score":0.01240164,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01455762723518834,"score_gpt":0.2339888369327207,"score_spread":0.2194312096975324,"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."}}