{"id":"W4283793952","doi":"10.1609/aaai.v36i8.20815","title":"Generalized Equivariance and Preferential Labeling for GNN Node Classification","year":2022,"lang":"en","type":"article","venue":"Proceedings of the AAAI Conference on Artificial Intelligence","topic":"Advanced Graph Neural Networks","field":"Computer Science","cited_by":7,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Alberta","funders":"National Key Research and Development Program of China; National Natural Science Foundation of China; Innovation and Technology Commission; Compute Canada; Natural Sciences and Engineering Research Council of Canada; Canadian Institute for Advanced Research","keywords":"Node (physics); Computer science; Embedding; Property (philosophy); Identity (music); Graph; Theoretical computer science; Data mining; Artificial intelligence","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":[0.0004374123,0.0001930639,0.0002233602,0.000102437,0.0005796147,0.0001804231,0.00163105,0.00005110036,0.00002606255],"category_scores_gemma":[0.0001790071,0.0001648756,0.00009202306,0.0005790602,0.0001585063,0.0003763422,0.0007198778,0.0003085698,0.00000318103],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00004766632,"about_ca_system_score_gemma":0.00005551206,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00000944798,"about_ca_topic_score_gemma":0.000003057444,"domain_scores_codex":[0.9981536,0.00002801898,0.0004628335,0.0005974339,0.0004152859,0.0003428097],"domain_scores_gemma":[0.9987251,0.0001232941,0.0004328464,0.0002892172,0.0003606667,0.00006893339],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0001003184,0.00006005973,0.00005649223,0.00002090892,0.000009187544,8.328383e-8,0.0003246561,0.0008053779,0.1061489,0.8545578,0.0001165826,0.03779968],"study_design_scores_gemma":[0.00007749534,0.0002018079,0.00009892244,0.00004429286,0.0000135434,0.000004940225,0.0001830035,0.4640117,0.1300266,0.404669,0.0004428987,0.0002257452],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.296396,0.0002048665,0.683244,0.0133871,0.001977323,0.002186701,0.00004466126,0.0003145751,0.002244649],"genre_scores_gemma":[0.9742007,0.00004745454,0.02492752,0.0003353547,0.00007283359,0.0002161992,0.000001688568,0.00001488371,0.0001833788],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.6778046,"threshold_uncertainty_score":0.6723433,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1232492585485928,"score_gpt":0.3161050023193992,"score_spread":0.1928557437708064,"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."}}