{"id":"W4315630289","doi":"10.1109/globecom48099.2022.10000743","title":"FLAC: Federated Learning with Autoencoder Compression and Convergence Guarantee","year":2022,"lang":"en","type":"article","venue":"GLOBECOM 2022 - 2022 IEEE Global Communications Conference","topic":"Privacy-Preserving Technologies in Data","field":"Computer Science","cited_by":13,"is_retracted":false,"has_abstract":true,"ca_institutions":"Queen's University","funders":"","keywords":"Autoencoder; Computer science; Decoding methods; Quantization (signal processing); Data compression; Bottleneck; Computer engineering; Codec; Convergence (economics); Artificial intelligence; Deep learning; Algorithm; Real-time computing; Machine learning; Embedded system; Computer hardware","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":[0.003358115,0.001460037,0.001625885,0.0008458868,0.0008359262,0.001566441,0.002020036,0.001903193,0.002431905],"category_scores_gemma":[0.01543854,0.0005864486,0.0007682754,0.0009140156,0.001796603,0.002303896,0.002655121,0.003042064,0.0007005616],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001386821,"about_ca_system_score_gemma":0.002791881,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.005162669,"about_ca_topic_score_gemma":0.003374787,"domain_scores_codex":[0.9977077,0.000598495,0.0001531096,0.0004560954,0.0007899493,0.0002945627],"domain_scores_gemma":[0.9906657,0.00549723,0.0007235098,0.001076659,0.001818713,0.0002183426],"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":[0.0001897051,0.00008562838,0.000850862,0.0001172932,0.00005475457,0.0001380841,0.00009202096,0.9004323,0.002057406,0.02396255,0.002420232,0.06959905],"study_design_scores_gemma":[0.000005318511,0.00002339266,0.00004885767,0.000007705881,0.000002626068,0.00002276687,0.000004772833,0.993891,0.0006450721,0.005165924,0.0001777955,0.000004778129],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.0122412,0.0004134222,0.9842018,0.0002992449,0.00004691055,0.00005096615,0.00008302554,0.0009305992,0.001732834],"genre_scores_gemma":[0.8289519,0.0004641759,0.1649992,0.0004973668,0.0001250903,0.0002492065,0.0003766956,0.0002045539,0.004131713],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.005162669,"threshold_uncertainty_score":0.01775962,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03787758666045778,"score_gpt":0.2856852426912725,"score_spread":0.2478076560308147,"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."}}