{"id":"W3015515533","doi":"10.1109/jiot.2020.2985694","title":"Hierarchical Incentive Mechanism Design for Federated Machine Learning in Mobile Networks","year":2020,"lang":"en","type":"article","venue":"IEEE Internet of Things Journal","topic":"Privacy-Preserving Technologies in Data","field":"Computer Science","cited_by":226,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of British Columbia","funders":"Singapore University of Technology and Design; National Research Foundation Singapore; Ministry of Education, India; National Science Foundation","keywords":"Computer science; Incentive; Incentive compatibility; Mechanism design; Contract theory; Leverage (statistics); Machine learning; Artificial intelligence; Computer security; 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":["open_science"],"consensus_categories":["open_science"],"category_scores_codex":[0.00113804,0.0001872421,0.0003374905,0.0001729587,0.00009733759,0.0003035999,0.01132521,0.0001639304,0.00001661863],"category_scores_gemma":[0.006300727,0.0001710916,0.0001066115,0.0003486202,0.00006890617,0.0008861845,0.009501963,0.001524827,0.000003935674],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000105526,"about_ca_system_score_gemma":0.00007407954,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00002072235,"about_ca_topic_score_gemma":0.000001732253,"domain_scores_codex":[0.9981099,0.0002318791,0.0005628738,0.0003860749,0.0003044874,0.000404729],"domain_scores_gemma":[0.998287,0.0004167968,0.0004080098,0.0006270467,0.0001349557,0.000126238],"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":[0.00346706,0.001260905,0.003869043,0.0003931683,0.00124566,0.001766836,0.02096928,0.1496187,0.09380196,0.01393162,0.3366599,0.3730159],"study_design_scores_gemma":[0.000620013,0.0006630219,0.000009297266,0.0001281129,0.000005315095,0.00006577685,0.0000311664,0.9066877,0.03427444,0.05700462,0.0003593688,0.0001511052],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.01549877,0.0002532791,0.9765023,0.006692986,0.0005180524,0.0002758569,0.000002021347,0.0002257491,0.00003099319],"genre_scores_gemma":[0.6898282,0.0000803645,0.3095041,0.0004718845,0.0000638589,0.00001513272,0.000002053172,0.00001560387,0.00001892197],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.7570691,"threshold_uncertainty_score":0.998509,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03780165515095697,"score_gpt":0.2729948420898941,"score_spread":0.2351931869389371,"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."}}