{"id":"W4414856475","doi":"10.1109/tnnls.2025.3611832","title":"FedMPS: Federated Learning in a Synergy of Multi-Level Prototype-Based Contrastive Learning and Soft Label Generation","year":2025,"lang":"en","type":"article","venue":"IEEE Transactions on Neural Networks and Learning Systems","topic":"Hate Speech and Cyberbullying Detection","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Alberta","funders":"National Natural Science Foundation of China","keywords":"Consistency (knowledge bases); Feature (linguistics); Raw data; Code (set theory); Feature extraction; Convergence (economics); Key (lock); Federated learning","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":[0.0005201481,0.0002176606,0.0003254824,0.000282015,0.0006816365,0.0002828786,0.00009398487,0.0001726125,0.000001780376],"category_scores_gemma":[0.00004022807,0.0002109643,0.00004495907,0.0005803596,0.00005543726,0.0002148416,0.000004068359,0.001037608,8.175645e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00004549526,"about_ca_system_score_gemma":0.00005356548,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0004188527,"about_ca_topic_score_gemma":0.000160948,"domain_scores_codex":[0.9979756,0.0007143276,0.0003940582,0.0004585602,0.0001581099,0.0002993561],"domain_scores_gemma":[0.9992558,0.0002885014,0.000173035,0.00009149779,0.0001190007,0.00007210066],"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":[0.00008411957,0.00005895187,0.0005800024,0.00005689272,0.00002868114,0.000006805355,0.0001518897,0.8822458,0.003393834,0.00004240912,0.000002332696,0.1133483],"study_design_scores_gemma":[0.001344621,0.0005466885,0.0005409957,0.0003035516,0.0000150023,0.00001223881,0.0001683357,0.9956753,0.001014262,0.000001036918,0.0001948026,0.0001831286],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1445043,0.0004398972,0.8539029,0.00007534079,0.0004194006,0.0004623361,6.713124e-7,0.0001656491,0.00002942716],"genre_scores_gemma":[0.9981498,0.00006467382,0.000620783,0.00003602119,0.00003604025,0.0001191432,0.000003232693,0.00001602054,0.0009543328],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.8536454,"threshold_uncertainty_score":0.8602874,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02173048643077047,"score_gpt":0.2493954218797947,"score_spread":0.2276649354490243,"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."}}