To Predict or Not to Predict? Proportionally Masked Autoencoders for Tabular Data Imputation
Proceedings of the AAAI Conference on Artificial Intelligence · 11.04.2025 · 39 (17) · 17886-17894
DOI: 10.1609/aaai.v39i17.33967 ↗Kurz gefasst
Fachartikel in der Zeitschrift Proceedings of the AAAI Conference on Artificial Intelligence, online erschienen am 11.04.2025. Verfasst von Jungkyu Kim und 2 weiteren Autor:innen. Die Arbeit wurde bisher 3-mal zitiert (Crossref).
Abstract (Originalsprache)
Masked autoencoders (MAEs) have recently demonstrated effectiveness in tabular data imputation. However, due to the inherent heterogeneity of tabular data, the uniform random masking strategy commonly used in MAEs can disrupt the distribution of missingness, leading to suboptimal performance. To address this, we propose a proportional masking strategy for MAEs. Specifically, we first compute the statistics of missingness based on the observed proportions in the dataset, and then generate masks that align with these statistics, ensuring that the distribution of missingness is preserved after masking. Furthermore, we argue that simple MLP-based token mixing offers competitive or often superior performance compared to attention mechanisms while being more computationally efficient, especially in the tabular domain with the inherent heterogeneity. Experimental results validate the effectiveness of the proposed proportional masking strategy across various missing data patterns in tabular datasets.
Zitieren
APA
Kim, J., Lee, K., & Park, T. (2025). To Predict or Not to Predict? Proportionally Masked Autoencoders for Tabular Data Imputation. Proceedings of the AAAI Conference on Artificial Intelligence, 39(17), 17886-17894. https://doi.org/10.1609/aaai.v39i17.33967
Vancouver
Kim J, Lee K, Park T. To Predict or Not to Predict? Proportionally Masked Autoencoders for Tabular Data Imputation. Proceedings of the AAAI Conference on Artificial Intelligence. 2025;39(17):17886-17894. doi:10.1609/aaai.v39i17.33967
BibTeX
@article{Kim2025,
author = {Kim, Jungkyu and Lee, Kibok and Park, Taeyoung},
title = {To Predict or Not to Predict? Proportionally Masked Autoencoders for Tabular Data Imputation},
journal = {Proceedings of the AAAI Conference on Artificial Intelligence},
year = {2025},
volume = {39},
number = {17},
pages = {17886--17894},
doi = {10.1609/aaai.v39i17.33967}
}
EUVIMED