{"id":"W4285606778","doi":"10.24963/ijcai.2022/465","title":"Escaping Feature Twist: A Variational Graph Auto-Encoder for Node Clustering","year":2022,"lang":"en","type":"article","venue":"Proceedings of the Thirty-First International Joint Conference on Artificial Intelligence","topic":"Advanced Graph Neural Networks","field":"Computer Science","cited_by":12,"is_retracted":false,"has_abstract":true,"ca_institutions":"Université du Québec à Montréal","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Cluster analysis; Autoencoder; Flattening; Theoretical computer science; Computer science; Topology (electrical circuits); Graph; Feature (linguistics); Algorithm; Twist; Artificial intelligence; Mathematics; Geometry; Deep learning; Combinatorics; Engineering","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":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0007169173,0.0003192411,0.0003063172,0.0003362626,0.0008014731,0.000321847,0.003163429,0.00008501043,0.00010784],"category_scores_gemma":[0.0003859466,0.0002784836,0.0003215413,0.0007680563,0.0001667066,0.0006675531,0.001407963,0.0006834973,0.00001040183],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000227051,"about_ca_system_score_gemma":0.0001045235,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001835744,"about_ca_topic_score_gemma":0.00001709095,"domain_scores_codex":[0.9969329,0.00002867453,0.000694854,0.0007677963,0.001135739,0.0004400589],"domain_scores_gemma":[0.9977078,0.0002456986,0.0007396684,0.000319227,0.0008947902,0.00009282678],"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":[0.0001648393,0.0001708449,0.0001113097,0.00003591537,0.00006161464,0.000001287913,0.001215538,0.03954418,0.007597846,0.9411551,0.0009171348,0.00902443],"study_design_scores_gemma":[0.00008079018,0.0001375168,0.0002372896,0.0001328989,0.00001100697,0.0000280112,0.0003276508,0.6578476,0.01144686,0.3280919,0.001378215,0.0002803392],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.004161147,0.00003610555,0.9584076,0.02867313,0.003408341,0.0009032183,0.00006852354,0.000215237,0.00412672],"genre_scores_gemma":[0.9508177,0.00002275636,0.047003,0.001150814,0.0002423594,0.0002995488,0.000007329377,0.00002772415,0.0004287343],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9466566,"threshold_uncertainty_score":0.9999667,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.05926104120348049,"score_gpt":0.2824810265796182,"score_spread":0.2232199853761377,"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."}}