{"id":"W4404809472","doi":"10.1109/tmc.2024.3508260","title":"Incentive Mechanism Design for Cross-Device Federated Learning: A Reinforcement Auction Approach","year":2024,"lang":"en","type":"article","venue":"IEEE Transactions on Mobile Computing","topic":"Blockchain Technology Applications and Security","field":"Computer Science","cited_by":10,"is_retracted":false,"has_abstract":true,"ca_institutions":"Concordia University","funders":"National Natural Science Foundation of China","keywords":"Computer science; Reinforcement learning; Incentive; Mechanism design; Mechanism (biology); Double auction; Incentive compatibility; Computer security; Common value auction; Artificial intelligence; Microeconomics","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":[0.005284559,0.00115541,0.001923566,0.0007194398,0.0006183243,0.001916662,0.003112615,0.002013097,0.003578736],"category_scores_gemma":[0.008554088,0.0005967069,0.0008482958,0.0007131372,0.00147957,0.002288131,0.002068783,0.00261075,0.0004321433],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001293695,"about_ca_system_score_gemma":0.002325546,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001349209,"about_ca_topic_score_gemma":0.001034035,"domain_scores_codex":[0.9971659,0.001272363,0.0001341667,0.000514583,0.0004792292,0.0004338167],"domain_scores_gemma":[0.9951231,0.00277585,0.0006065625,0.000425945,0.0006646375,0.0004038497],"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":[0.0002525678,0.000272148,0.0008044929,0.0002085276,0.000107559,0.0003697,0.000158944,0.856128,0.002881105,0.09351881,0.001357936,0.0439402],"study_design_scores_gemma":[0.00003643096,0.00005937351,0.0000479652,0.0000112123,0.00001040091,0.00005007261,0.00001456658,0.9795024,0.0003454192,0.01942147,0.0004910876,0.000009439219],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.008955774,0.0001645597,0.9887421,0.0002094115,0.00003743983,0.0001057266,0.00002367808,0.0001340323,0.001627363],"genre_scores_gemma":[0.865824,0.0002470573,0.1303679,0.0002031941,0.00005575473,0.0002855975,0.0000454732,0.00004123107,0.002929827],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.005284559,"threshold_uncertainty_score":0.02794778,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02566485237195155,"score_gpt":0.2853113558515227,"score_spread":0.2596465034795712,"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."}}