{"id":"W4382237408","doi":"10.1609/aaai.v37i7.26019","title":"I’m Me, We’re Us, and I’m Us: Tri-directional Contrastive Learning on Hypergraphs","year":2023,"lang":"en","type":"article","venue":"Proceedings of the AAAI Conference on Artificial Intelligence","topic":"Advanced Graph Neural Networks","field":"Computer Science","cited_by":44,"is_retracted":false,"has_abstract":true,"ca_institutions":"Kootenay Association for Science & Technology","funders":"Institute for Information and Communications Technology Promotion; Samsung; Ministry of Science and ICT, South Korea; Korea Advanced Institute of Science and Technology","keywords":"Computer science; Contrast (vision); Generalization; Node (physics); Artificial intelligence; Representation (politics); Competitor analysis; Machine learning; Unsupervised learning; Code (set theory); Feature learning; Simple (philosophy); Natural language processing; Mathematics","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":[],"consensus_categories":[],"category_scores_codex":[0.0004322966,0.0002964064,0.0003182876,0.0002884102,0.0004330738,0.0002253101,0.00112527,0.0001160036,0.00002467143],"category_scores_gemma":[0.0005108126,0.0002296922,0.0001297718,0.001698509,0.000382907,0.0004611171,0.0003715755,0.0006361363,0.00007902265],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00003161583,"about_ca_system_score_gemma":0.00004685337,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001693084,"about_ca_topic_score_gemma":0.00001189211,"domain_scores_codex":[0.9977334,0.00003655041,0.0004553792,0.0007133953,0.000583823,0.0004775213],"domain_scores_gemma":[0.9984682,0.0004158885,0.0003421721,0.000207526,0.0004375124,0.0001287108],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.0002018395,0.0001083298,0.002780769,0.00003533643,0.00004269747,0.000003415932,0.001131638,0.002813336,0.0323472,0.8456295,0.000491681,0.1144143],"study_design_scores_gemma":[0.000134802,0.0009544792,0.005625813,0.0006954646,0.00002625998,0.0000180159,0.001147784,0.2850316,0.3430015,0.3614338,0.001242581,0.0006878064],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9457574,0.0001666052,0.01977168,0.01265831,0.001862281,0.001204461,0.00001508087,0.001104609,0.01745951],"genre_scores_gemma":[0.9976743,0.0004086434,0.001017164,0.000288995,0.00009111889,0.00003819023,8.057995e-7,0.00001848351,0.0004623291],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.4841956,"threshold_uncertainty_score":0.9366576,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.05913306889425603,"score_gpt":0.2886363057942006,"score_spread":0.2295032368999446,"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."}}