{"id":"W4283380598","doi":"10.36227/techrxiv.19740394.v1","title":"Decentralized Aggregation for Energy-Efficient Federated Learning via Overlapped Clustering and D2D Communications","year":2022,"lang":"en","type":"preprint","venue":"","topic":"Privacy-Preserving Technologies in Data","field":"Computer Science","cited_by":3,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of British Columbia","funders":"","keywords":"News aggregator; Computer science; Cluster analysis; Scheduling (production processes); Energy consumption; Boosting (machine learning); Distributed computing; Data aggregator; Local optimum; Cluster (spacecraft); Computation; Convergence (economics); Scheme (mathematics); Topology (electrical circuits); Mathematical optimization; Wireless sensor network; Algorithm; Computer network; Artificial intelligence; Mathematics; 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":[0.001087634,0.0006400748,0.001019765,0.0004495941,0.0008181152,0.001021061,0.001596288,0.0008346297,0.00105896],"category_scores_gemma":[0.00208053,0.0002946106,0.0004607908,0.0008742973,0.0006024646,0.001368915,0.001886134,0.0008062107,0.000237311],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0009460489,"about_ca_system_score_gemma":0.001208732,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.003801174,"about_ca_topic_score_gemma":0.004734643,"domain_scores_codex":[0.9992385,0.000200398,0.00003743711,0.0002133858,0.0001748874,0.0001355127],"domain_scores_gemma":[0.999034,0.0003582212,0.0001162862,0.000239773,0.0001740932,0.00007761763],"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":[0.0002241375,0.0001322377,0.001233116,0.00006786097,0.00004742563,0.0001415952,0.0001218793,0.8808227,0.004344834,0.01476727,0.002853366,0.09524356],"study_design_scores_gemma":[0.000007159308,0.00002023186,0.00008925419,0.000001794558,0.000003664772,0.00001511072,0.00001478168,0.9949936,0.0006063454,0.003857514,0.0003871605,0.000003400319],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.03315994,0.000242274,0.9634001,0.0002486162,0.00004371102,0.000047219,0.00007180352,0.0006038202,0.002182555],"genre_scores_gemma":[0.9041914,0.0001134219,0.09341231,0.0001333656,0.00003227143,0.00008090213,0.0001428354,0.00003162323,0.001861801],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.003801174,"threshold_uncertainty_score":0.007558107,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.0439209384036523,"score_gpt":0.3015788762398748,"score_spread":0.2576579378362225,"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."}}