Fed-ReMasker: Federated Tabular Imputation under Feature-Level Missingness
This work adapts the ReMasker masked autoencoder to federated learning (Fed-ReMasker), enabling centers to impute features never observed locally by leveraging knowledge learned across collaborating centers to evaluate feature-level missingness.
Ioannis Papathanail, Rooholla Poursoleymani, Lubnaa Abdur Rahman et al.
· 0 citations