{"id":"W3112044954","doi":"10.1609/aaai.v35i9.16960","title":"Personalized Cross-Silo Federated Learning on Non-IID Data","year":2021,"lang":"en","type":"article","venue":"Proceedings of the AAAI Conference on Artificial Intelligence","topic":"Privacy-Preserving Technologies in Data","field":"Computer Science","cited_by":659,"is_retracted":false,"has_abstract":true,"ca_institutions":"McMaster University; Huawei Technologies (Canada); Simon Fraser University","funders":"Natural Sciences and Engineering Research Council of Canada; Hong Kong Baptist University","keywords":"Computer science; Benchmark (surveying); Heuristic; Pairwise comparison; Convergence (economics); Federated learning; Deep learning; Machine learning; Artificial intelligence; Artificial neural network; Data mining","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":["metaresearch","metaepi_narrow","scholarly_communication","open_science"],"consensus_categories":["open_science"],"category_scores_codex":[0.0009821209,0.0003329558,0.0003804732,0.0001385526,0.0005498006,0.001236546,0.03290711,0.0001967328,0.0001559851],"category_scores_gemma":[0.03257003,0.000271303,0.000103343,0.0012449,0.0005617495,0.001037369,0.04724868,0.0009448074,0.0002383344],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00008588683,"about_ca_system_score_gemma":0.000305016,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00003813554,"about_ca_topic_score_gemma":0.00001032241,"domain_scores_codex":[0.9965976,0.0000440237,0.00063433,0.001312956,0.0008526053,0.0005584718],"domain_scores_gemma":[0.9938958,0.0002671851,0.000493549,0.00413486,0.00110658,0.0001020396],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.0002484787,0.0006531125,0.002025364,0.0001566598,0.000117192,0.00002412628,0.0008478214,0.0001097911,0.1784359,0.6304137,0.02205699,0.1649108],"study_design_scores_gemma":[0.00005196583,0.0001417107,0.0001948033,0.0002858,0.000008706699,0.00001189726,0.0003484535,0.2927283,0.5431193,0.1621695,0.0006557659,0.0002837724],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.6189232,0.000233085,0.1901414,0.1225951,0.003122493,0.001532189,0.0001663109,0.002324424,0.0609618],"genre_scores_gemma":[0.9786565,0.0001011879,0.02014641,0.0003755619,0.00006458937,0.00001776947,0.00001267764,0.00002248038,0.0006027792],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.4682442,"threshold_uncertainty_score":0.9999739,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1532262172409678,"score_gpt":0.3559079458792938,"score_spread":0.202681728638326,"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."}}