{"id":"W4380875900","doi":"10.36227/techrxiv.23518110.v1","title":"Communication Efficient Privacy-Preserving Federated Learning via Knowledge Distillation for Human Activity Recognition Systems","year":2023,"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":"Western University; Lakehead University","funders":"","keywords":"Computer science; Machine learning; Artificial intelligence; Federated learning; Distillation; Internet of Things; Mean squared error; Activity recognition; Data mining; Embedded system; Mathematics","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":[0.002874506,0.0007589336,0.001444032,0.0006069443,0.0008418037,0.00173754,0.002164763,0.001444466,0.001074581],"category_scores_gemma":[0.008768152,0.0003809607,0.0007386552,0.001166199,0.001465074,0.003786657,0.003242374,0.001963533,0.000307257],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001287963,"about_ca_system_score_gemma":0.0019698,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002715985,"about_ca_topic_score_gemma":0.002050402,"domain_scores_codex":[0.9979537,0.0006842575,0.0001379587,0.0005050962,0.0004540619,0.0002648413],"domain_scores_gemma":[0.9957261,0.002159199,0.0003794252,0.001140838,0.0004232172,0.0001712103],"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":[0.0005217461,0.0003245182,0.001396277,0.0001056373,0.00008488908,0.0001564305,0.0001393334,0.7509219,0.004153725,0.01611952,0.002320774,0.2237553],"study_design_scores_gemma":[0.00001186864,0.00003780398,0.0001025798,0.00000351166,0.000005689044,0.00003279349,0.00001395275,0.9860373,0.001944921,0.01156388,0.0002393486,0.000006390736],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.04509994,0.0003791779,0.9519882,0.0004000943,0.00003795047,0.0000439681,0.0001329,0.001010604,0.0009071371],"genre_scores_gemma":[0.9111849,0.0001387108,0.08666851,0.0002576698,0.00002790112,0.00007465923,0.0003152197,0.00005340725,0.001278981],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.002874506,"threshold_uncertainty_score":0.01520205,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1137490068846616,"score_gpt":0.3416331261215287,"score_spread":0.2278841192368671,"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."}}