{"id":"W3172809435","doi":"10.2196/26598","title":"Implementing Vertical Federated Learning Using Autoencoders: Practical Application, Generalizability, and Utility Study","year":2021,"lang":"en","type":"article","venue":"JMIR Medical Informatics","topic":"Privacy-Preserving Technologies in Data","field":"Computer Science","cited_by":47,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"Ministry of Science and ICT, South Korea; Korea Health Industry Development Institute; National Research Foundation","keywords":"Autoencoder; Computer science; Generalizability theory; Artificial intelligence; Machine learning; Raw data; Categorical variable; Deep learning; Artificial neural network; Data mining; Feature (linguistics); Data modeling; Pattern recognition (psychology); Database; Statistics","routes":{"ca_aff":false,"ca_fund":false,"ca_venue":true,"about_ca":false,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaresearch","open_science"],"consensus_categories":[],"category_scores_codex":[0.002126752,0.0001833616,0.0002816237,0.00006990624,0.0004729922,0.0004939077,0.003476917,0.0002065877,0.00006330964],"category_scores_gemma":[0.03064635,0.0001702035,0.00003247432,0.000782906,0.0002087211,0.001188738,0.05150589,0.0007717424,0.00001352288],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00008586574,"about_ca_system_score_gemma":0.0005385975,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00003264163,"about_ca_topic_score_gemma":0.00003083262,"domain_scores_codex":[0.9968663,0.0002630971,0.0008840825,0.0003622034,0.001041295,0.0005830551],"domain_scores_gemma":[0.99637,0.0004064289,0.0001401449,0.002521464,0.0002954482,0.000266475],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00007504778,0.006001087,0.4704582,0.00162753,0.0005906214,0.0006991344,0.01774368,0.0001931485,0.0006484307,0.02273895,0.08368688,0.3955373],"study_design_scores_gemma":[0.0004726048,0.00005986528,0.003034965,0.00002326584,0.00001275783,0.0001327905,0.002408451,0.985544,0.0001673687,0.005225778,0.002738216,0.000179945],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.2871843,0.00001783037,0.7054034,0.006303411,0.00006291953,0.0003011201,0.00000147085,0.000468824,0.0002566908],"genre_scores_gemma":[0.5659216,0.00001502496,0.4334518,0.00050737,0.00003068816,0.0000420598,0.00001949426,0.000008426285,0.000003510912],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9853508,"threshold_uncertainty_score":0.9775189,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.06282766158257184,"score_gpt":0.3817565824914482,"score_spread":0.3189289209088763,"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."}}