{"id":"W4400314708","doi":"10.1109/tmc.2024.3423399","title":"A Hierarchical Incentive Mechanism for Federated Learning","year":2024,"lang":"en","type":"article","venue":"IEEE Transactions on Mobile Computing","topic":"Privacy-Preserving Technologies in Data","field":"Computer Science","cited_by":20,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Waterloo","funders":"Natural Science Foundation of Beijing Municipality","keywords":"Computer science; Incentive; Mechanism (biology); Computer network; Distributed computing","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":[0.0004071369,0.0002224901,0.0002064193,0.0003096018,0.0006869607,0.0005848331,0.004952878,0.000155213,0.00001101439],"category_scores_gemma":[0.0004440908,0.0002234917,0.0001486675,0.0007801866,0.00006579485,0.0004070037,0.000530816,0.0008852053,0.0000576489],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001605204,"about_ca_system_score_gemma":0.00009571741,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001149845,"about_ca_topic_score_gemma":0.00000387218,"domain_scores_codex":[0.9980591,0.0001023311,0.0003061768,0.0008032616,0.0002558978,0.0004732132],"domain_scores_gemma":[0.9974087,0.0008943243,0.00005160649,0.001468883,0.0001027137,0.00007379862],"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":[0.00002508209,0.0001984133,0.000002301124,0.0001532831,0.00017239,0.00005958131,0.0005678175,0.02466399,0.007500696,0.01639621,0.003896699,0.9463635],"study_design_scores_gemma":[0.0001999508,0.0002544757,0.000001371662,0.0001669929,0.00001156658,0.00002085613,0.00005243751,0.9137947,0.03941586,0.04492366,0.000936558,0.0002216007],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.009987676,0.00006867397,0.9818287,0.002139335,0.001718849,0.0005283787,0.00001773,0.003595879,0.0001147853],"genre_scores_gemma":[0.8017847,0.0000197923,0.1978239,0.0000946596,0.00005006459,0.0001135397,0.000003864267,0.00002699095,0.00008248927],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.946142,"threshold_uncertainty_score":0.9203762,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02443955280213041,"score_gpt":0.2890165729223877,"score_spread":0.2645770201202574,"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."}}