{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.003749049,0.00128845,0.001672144,0.001136734,0.0009408775,0.001870239,0.004673834,0.002541958,0.002990688],"category_scores_gemma":[0.008937034,0.000705247,0.00143425,0.001046668,0.00166161,0.004768773,0.005511537,0.003189906,0.001144344],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001197851,"about_ca_system_score_gemma":0.002097194,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.003120986,"about_ca_topic_score_gemma":0.003883076,"domain_scores_codex":[0.9976249,0.0007560564,0.0001285261,0.0007868313,0.0004968478,0.0002067743],"domain_scores_gemma":[0.9966521,0.001179033,0.0001875306,0.001280004,0.0005172441,0.000184093],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.000846503,0.0009454692,0.00332321,0.0002622186,0.0002221123,0.0003166217,0.0003802433,0.2201184,0.01726027,0.01597079,0.01037694,0.7299774],"study_design_scores_gemma":[0.00006523317,0.0001167326,0.0001823714,0.00001373739,0.0000201511,0.00007624771,0.00003340158,0.9752976,0.005561695,0.01692436,0.00168847,0.00001999314],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.01455123,0.0001992743,0.9779146,0.0002261736,0.00005245042,0.0001260926,0.0001234225,0.005943791,0.000862943],"genre_scores_gemma":[0.3698141,0.0001081463,0.6248047,0.0007117027,0.00006482086,0.0004351799,0.0009554893,0.0004437039,0.002662233],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.004673834,"threshold_uncertainty_score":0.01982707,"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."}}