{"id":"W4402626816","doi":"10.1109/tmc.2024.3464512","title":"Knowledge-Aware Parameter Coaching for Communication-Efficient Personalized Federated Learning in Mobile Edge Computing","year":2024,"lang":"en","type":"article","venue":"IEEE Transactions on Mobile Computing","topic":"Recommender Systems and Techniques","field":"Computer Science","cited_by":5,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Victoria","funders":"Fundamental Research Funds for the Central Universities; National Natural Science Foundation of China","keywords":"Computer science; Coaching; Mobile computing; Edge computing; Mobile edge computing; Mobile telephony; Enhanced Data Rates for GSM Evolution; Multimedia; Mobile device; Computer network; Distributed computing; World Wide Web; Artificial intelligence; Mobile radio","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":[0.00136241,0.001028063,0.001315419,0.0006390577,0.0008101658,0.001251334,0.002057253,0.00131452,0.00130949],"category_scores_gemma":[0.00452909,0.0004614809,0.0006191966,0.0009351666,0.0006648144,0.003230689,0.002006458,0.001864651,0.0005626764],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0008040361,"about_ca_system_score_gemma":0.001057909,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.005154711,"about_ca_topic_score_gemma":0.006785924,"domain_scores_codex":[0.9990582,0.0002659329,0.00005531368,0.0002775235,0.0002044623,0.0001385847],"domain_scores_gemma":[0.9983359,0.0006395448,0.0001336094,0.0005263238,0.0002723132,0.00009236037],"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":[0.0003132088,0.0003775519,0.003244129,0.0001128939,0.0001205069,0.0002217605,0.0003361966,0.6956251,0.007449855,0.008392652,0.004006061,0.2798],"study_design_scores_gemma":[0.000008202294,0.00002778563,0.0001827906,0.000005294607,0.00001128363,0.00004295011,0.00003014621,0.9934235,0.001496838,0.004362773,0.0003987165,0.00000977279],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.03273561,0.0003494924,0.9640068,0.0002009429,0.0000311654,0.00003966127,0.00005875111,0.001272421,0.001305171],"genre_scores_gemma":[0.8506892,0.0002301388,0.146572,0.0002459328,0.00003917193,0.00008753456,0.00019868,0.0001151571,0.001822276],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.005154711,"threshold_uncertainty_score":0.01024938,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03042608811050865,"score_gpt":0.3143957564740178,"score_spread":0.2839696683635091,"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."}}