{"id":"W4323338515","doi":"10.1109/tcomm.2023.3253718","title":"Decentralized Aggregation for Energy-Efficient Federated Learning via D2D Communications","year":2023,"lang":"en","type":"article","venue":"IEEE Transactions on Communications","topic":"Privacy-Preserving Technologies in Data","field":"Computer Science","cited_by":55,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of British Columbia, Okanagan Campus; University of British Columbia; Carleton University; University of Toronto","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Computer science; Efficient energy use; Energy (signal processing); Computer network; Distributed computing; Electronic engineering; Electrical engineering; Engineering","routes":{"ca_aff":true,"ca_fund":true,"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":["metaepi_narrow","sts","open_science"],"consensus_categories":[],"category_scores_codex":[0.0006257982,0.0002444672,0.0002382172,0.0005559839,0.002709421,0.000296122,0.02694885,0.0001896366,0.00001252063],"category_scores_gemma":[0.0006363481,0.000275572,0.0001704615,0.002442883,0.000312313,0.0004255223,0.001998912,0.000615749,0.0001461291],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002202101,"about_ca_system_score_gemma":0.0001262658,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001231131,"about_ca_topic_score_gemma":0.0002651781,"domain_scores_codex":[0.9977722,0.0004188112,0.0005223176,0.0004898553,0.0003051195,0.0004917326],"domain_scores_gemma":[0.9827765,0.00173334,0.0002103193,0.01487483,0.000297168,0.000107904],"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":[0.00004989747,0.001580458,0.00002355555,0.00004190557,0.000324453,0.000002344069,0.0007866777,0.03338746,0.009610909,0.02622975,0.0376026,0.89036],"study_design_scores_gemma":[0.000517339,0.00006552626,0.00002451553,0.00004920102,0.00002723682,0.000006399734,0.00008662939,0.9467778,0.007962498,0.01930777,0.02490605,0.0002690127],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.0003457823,0.00022277,0.9478217,0.04683306,0.0002878411,0.0004940908,0.00007319654,0.003425974,0.000495617],"genre_scores_gemma":[0.7698241,0.002531305,0.2259886,0.0001750457,0.000007651652,0.0009860048,0.000190864,0.00003716091,0.0002592336],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9133903,"threshold_uncertainty_score":0.9999697,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.06539950561102888,"score_gpt":0.317415120928327,"score_spread":0.2520156153172981,"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."}}