ReMasker: Imputing Tabular Data with Masked Autoencoding
This addresses the problem of handling missing data in tabular datasets for data scientists and researchers, representing an incremental improvement over existing methods.
The authors tackled the problem of imputing missing values in tabular data by introducing ReMasker, a method based on masked autoencoding that randomly re-masks additional values during training, and showed it performs on par with or outperforms state-of-the-art methods in imputation fidelity and utility, with performance often improving as missing data ratios increase.
We present ReMasker, a new method of imputing missing values in tabular data by extending the masked autoencoding framework. Compared with prior work, ReMasker is both simple -- besides the missing values (i.e., naturally masked), we randomly ``re-mask'' another set of values, optimize the autoencoder by reconstructing this re-masked set, and apply the trained model to predict the missing values; and effective -- with extensive evaluation on benchmark datasets, we show that ReMasker performs on par with or outperforms state-of-the-art methods in terms of both imputation fidelity and utility under various missingness settings, while its performance advantage often increases with the ratio of missing data. We further explore theoretical justification for its effectiveness, showing that ReMasker tends to learn missingness-invariant representations of tabular data. Our findings indicate that masked modeling represents a promising direction for further research on tabular data imputation. The code is publicly available.