{"id":"W3206932362","doi":"10.1609/aaai.v35i5.16534","title":"Graph-Enhanced Multi-Task Learning of Multi-Level Transition Dynamics for Session-based Recommendation","year":2021,"lang":"en","type":"article","venue":"Proceedings of the AAAI Conference on Artificial Intelligence","topic":"Recommender Systems and Techniques","field":"Computer Science","cited_by":105,"is_retracted":false,"has_abstract":true,"ca_institutions":"York University; Wilfrid Laurier University","funders":"Science and Technology Planning Project of Guangdong Province; Natural Sciences and Engineering Research Council of Canada; Natural Science Foundation of Guangdong Province; National Natural Science Foundation of China","keywords":"Computer science; Session (web analytics); Graph; Interdependence; Relation (database); Task (project management); Dynamics (music); Context (archaeology); Transition (genetics); Encoder; Embedding; Machine learning; Artificial intelligence; Theoretical computer science; Data mining; World Wide Web","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":[0.0006059957,0.000197049,0.0003121239,0.0001441263,0.0002061763,0.000129254,0.000761285,0.000121091,0.00001721938],"category_scores_gemma":[0.0003297561,0.000163293,0.0001945436,0.0005686893,0.00009027006,0.0003407633,0.0001058484,0.0002395269,0.000002653924],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00006041011,"about_ca_system_score_gemma":0.0001342734,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00004432809,"about_ca_topic_score_gemma":0.00005356471,"domain_scores_codex":[0.998327,0.00004623642,0.0006707967,0.0004633205,0.0002503019,0.0002423521],"domain_scores_gemma":[0.9976406,0.0001552978,0.0005960021,0.0002132036,0.001340117,0.00005479334],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.00007784195,0.0006149267,0.0001287744,0.0003080291,0.00003387075,2.476676e-7,0.002114389,0.000470724,0.306549,0.2448716,0.00005683251,0.4447737],"study_design_scores_gemma":[0.00006052527,0.0001097011,0.00005554928,0.0002679398,0.00000721401,8.747371e-7,0.0004871673,0.446287,0.5443725,0.008217702,0.0000210644,0.0001127988],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.01222112,0.00001001278,0.9840831,0.002412431,0.0003139837,0.0004800324,0.00002292178,0.00009689498,0.000359559],"genre_scores_gemma":[0.9147046,0.0000202549,0.08498559,0.00009511047,0.00001874238,0.00007481629,0.00001032886,0.0000130407,0.0000775341],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9024835,"threshold_uncertainty_score":0.6658896,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1274622808664918,"score_gpt":0.3303898232096775,"score_spread":0.2029275423431857,"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."}}