{"id":"W4405073635","doi":"10.1145/3706115","title":"Heterogeneous Graph Neural Networks using Self-supervised Reciprocally Contrastive Learning","year":2024,"lang":"en","type":"article","venue":"ACM Transactions on Intelligent Systems and Technology","topic":"Advanced Graph Neural Networks","field":"Computer Science","cited_by":11,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Alberta","funders":"National Natural Science Foundation of China","keywords":"Computer science; Artificial intelligence; Topological graph theory; Network topology; Graph; Robustness (evolution); Machine learning; Theoretical computer science; Data mining; Pathwidth; Line graph","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":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0001446575,0.0003049907,0.0003276911,0.0006691805,0.0003799845,0.0002321241,0.0006466194,0.0003283343,0.000004977591],"category_scores_gemma":[0.0000166274,0.0002753335,0.0001162974,0.00147795,0.0001311224,0.00028785,0.00004399018,0.0009158291,0.000008060413],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00007308369,"about_ca_system_score_gemma":0.00002288827,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00002701853,"about_ca_topic_score_gemma":0.00001017306,"domain_scores_codex":[0.9980639,0.00009652816,0.0004197975,0.0007530831,0.0001725548,0.0004941336],"domain_scores_gemma":[0.9988664,0.0002746332,0.00007237322,0.0005805992,0.0000974412,0.0001084845],"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":[0.00001891891,0.00006523544,0.0001136606,0.00006353799,0.00023876,0.0002019024,0.0002055981,0.6800534,0.0004526737,0.01049274,0.000007715063,0.3080859],"study_design_scores_gemma":[0.0001173272,0.0003771301,0.000002949791,0.0001589454,0.00003712137,0.0007850648,0.0001019047,0.993679,0.0008975944,0.002602363,0.0009674681,0.0002731264],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.02553767,0.005773061,0.9643658,0.0004362765,0.001613349,0.0004229787,0.000002421297,0.001832985,0.00001542445],"genre_scores_gemma":[0.9890166,0.0007990798,0.009905892,0.00005473234,0.00005754568,0.00008279901,0.000001266417,0.00003486176,0.00004724183],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9634789,"threshold_uncertainty_score":0.9999699,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01694117523900615,"score_gpt":0.2519562486870152,"score_spread":0.235015073448009,"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."}}