{"id":"W4385079011","doi":"10.1109/iwcmc58020.2023.10182555","title":"Towards On-Demand Deployment of Multiple Clients and Heterogeneous Models in Federated Learning","year":2023,"lang":"en","type":"article","venue":"","topic":"Privacy-Preserving Technologies in Data","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":true,"ca_institutions":"Concordia University","funders":"","keywords":"Computer science; Software deployment; Orchestration; Flexibility (engineering); Process (computing); Relevance (law); Distributed computing; MNIST database; Selection (genetic algorithm); Convergence (economics); Machine learning; Artificial intelligence; Deep learning; Software engineering","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":[0.005252228,0.0009259992,0.001552979,0.0006981498,0.001103637,0.002694658,0.003601468,0.0016361,0.001448937],"category_scores_gemma":[0.009416725,0.0007106409,0.0009436476,0.0009068876,0.001154491,0.005771451,0.006096704,0.002427469,0.0007173711],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001321073,"about_ca_system_score_gemma":0.001771729,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.003496955,"about_ca_topic_score_gemma":0.003605502,"domain_scores_codex":[0.9959916,0.001641742,0.0002129293,0.0009163283,0.0007585696,0.0004787995],"domain_scores_gemma":[0.9946326,0.00158423,0.0002440104,0.002390084,0.0006546893,0.0004943886],"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":[0.001310418,0.001134472,0.01278836,0.000244021,0.0002326141,0.0008445684,0.001179705,0.5308769,0.01400135,0.0356929,0.007864627,0.3938301],"study_design_scores_gemma":[0.00001963034,0.00006014105,0.0003071015,0.00001167811,0.00001292548,0.0001041362,0.0001328382,0.9852929,0.003089102,0.00941565,0.00154138,0.00001256125],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.05971497,0.0002403504,0.9346354,0.0004759614,0.00005468477,0.0001258973,0.00007253861,0.003456604,0.001223632],"genre_scores_gemma":[0.6657786,0.0001574141,0.3310813,0.000309235,0.0000363717,0.0001251923,0.0003380187,0.0002574661,0.001916321],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.005252228,"threshold_uncertainty_score":0.02777678,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.0524334730508122,"score_gpt":0.2856840543680958,"score_spread":0.2332505813172836,"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."}}