{"id":"W4393156655","doi":"10.1609/aaai.v38i15.29603","title":"Efficient Asynchronous Federated Learning with Prospective Momentum Aggregation and Fine-Grained Correction","year":2024,"lang":"en","type":"article","venue":"Proceedings of the AAAI Conference on Artificial Intelligence","topic":"Privacy-Preserving Technologies in Data","field":"Computer Science","cited_by":22,"is_retracted":false,"has_abstract":true,"ca_institutions":"McMaster University","funders":"Natural Sciences and Engineering Research Council of Canada; National Natural Science Foundation of China","keywords":"Asynchronous communication; Computer science; Momentum (technical analysis); Computer network; Business","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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.003303224,0.001338415,0.001687944,0.0007553088,0.001094035,0.0019224,0.004106517,0.001274086,0.001861734],"category_scores_gemma":[0.01051372,0.0005962285,0.0006532487,0.0009881718,0.00114791,0.004461858,0.003090913,0.002341324,0.0008129029],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001460476,"about_ca_system_score_gemma":0.002943668,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.007115564,"about_ca_topic_score_gemma":0.009685458,"domain_scores_codex":[0.9978364,0.0004224422,0.0001501392,0.0006541788,0.0006775593,0.0002593482],"domain_scores_gemma":[0.9960874,0.0009400369,0.0002853934,0.00141347,0.001044663,0.000229072],"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":[0.0005525097,0.0006146235,0.005374819,0.00009159569,0.000100152,0.0002254774,0.0002538921,0.565702,0.0092067,0.01190743,0.008162621,0.3978082],"study_design_scores_gemma":[0.00002327562,0.00002585017,0.0001272694,0.000002771162,0.000006275136,0.00002609302,0.00001128577,0.9934923,0.001998756,0.003855089,0.0004234057,0.000007694847],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.02156127,0.0001543877,0.9723168,0.0002603824,0.00007519157,0.00007067152,0.00006352584,0.004424034,0.001073714],"genre_scores_gemma":[0.7543906,0.0001082749,0.2406083,0.0004014303,0.00009678263,0.0001788271,0.0003218421,0.0002994112,0.003594533],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.007115564,"threshold_uncertainty_score":0.01746935,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.030473913786981,"score_gpt":0.2682071313148553,"score_spread":0.2377332175278743,"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."}}