mlsanityData to 14 Oct 2026

ReMasker: Imputing Tabular Data with Masked Autoencoding

arXiv 2309.13793 ↗First posted 25 Sep 2023cs.LGcited by 37

Not on the map. Why?

Abstract (arXiv)

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.

Key facts. Cited by 37 papers in the map (data through 14 Oct 2026). Builds on 24 of its 32 references that are in the map. First posted on arXiv 25 Sep 2023.

Builds on

24 of 32 references.

References · 24

  1. 2017Attention Is All You Needcited by 60,361
  2. 2018BERT: Pre-training of Deep Bidirectional Transformers for Language Understandingcited by 40,399
  3. 2020An Image is Worth 16x16 Words: Transformers for Image Recognition at Scalecited by 30,186
  4. 2021Masked Autoencoders Are Scalable Vision Learnerscited by 7,403
  5. 2022Generative Adversarial Networkscited by 5,627
  6. 2021BEiT: BERT Pre-Training of Image Transformerscited by 2,375
  7. 2019Similarity of Neural Network Representations Revisitedcited by 1,755
  8. 2016Context Encoders: Feature Learning by Inpaintingcited by 1,428
  9. 2020TabTransformer: Tabular Data Modeling Using Contextual Embeddingscited by 409
  10. 2018GAIN: Missing Data Imputation using Generative Adversarial Netscited by 352
  11. 2022On Embeddings for Numerical Features in Tabular Deep Learningcited by 186
  12. 2021TransGAN: Two Pure Transformers Can Make One Strong GAN, and That Can Scale Upcited by 162
12 more
  1. 2021StyleSwin: Transformer-based GAN for High-resolution Image Generationcited by 152
  2. 2018Handling Incomplete Heterogeneous Data using VAEscited by 149
  3. 2021Generative Adversarial Transformerscited by 120
  4. 2014Matrix Completion and Low-Rank SVD via Fast Alternating Least Squarescited by 104
  5. 2020Missing Data Imputation using Optimal Transportcited by 100
  6. 2022HyperImpute: Generalized Iterative Imputation with Automatic Model Selectioncited by 83
  7. 2017Towards Deeper Understanding of Variational Autoencoding Modelscited by 56
  8. 2021MIRACLE: Causally-Aware Imputation via Learning Missing Data Mechanismscited by 51
  9. 2022Understanding Masked Image Modeling via Learning Occlusion Invariant Featurecited by 50
  10. 2021Identifiable Generative Models for Missing Not at Random Data Imputationcited by 30
  11. 2018MIWAE: Deep Generative Modelling and Imputation of Incomplete Datacited by 14
  12. 2021MisConv: Convolutional Neural Networks for Missing Datacited by 4

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2024: 6; 2025: 16; 2026: 15.

37 papers.

Sort:

By area:

  1. 2025LSM-2: Learning from Incomplete Wearable Sensor Datacited by 23
  2. 2024DiffPuter: Empowering Diffusion Models for Missing Data Imputationcited by 19
  3. 2025On LLM-Enhanced Mixed-Type Data Imputation with High-Order Message Passingcited by 11
  4. 2024TabSeq: A Framework for Deep Learning on Tabular Data via Sequential Orderingcited by 5
  5. 2024Diffusion-nested Auto-Regressive Synthesis of Heterogeneous Tabular Datacited by 4
  6. 2025CACTI: Leveraging Copy Masking and Contextual Information to Improve Tabular Data Imputationcited by 4
  7. 2025One Pipeline, Many Transformers: Pattern-Specific Imputation Specialists for Tabular Missing Datacited by 4
  8. 2025MaskSDM with Shapley values to improve flexibility, robustness, and explainability in species distribution modelingcited by 3
  9. 2025Representation Learning of Lab Values via Masked AutoEncoderscited by 2
  10. 2025Leveraging Machine Unlearning for Cost-Efficient Preference Alignmentcited by 2
  11. 2025Impute-MACFM: Imputation based on Mask-Aware Flow Matchingcited by 2
  12. 2025Interpretable Generative and Discriminative Learning for Multimodal and Incomplete Clinical Datacited by 2
25 more
  1. 2024Masked Language Modeling Becomes Conditional Density Estimation for Tabular Data Synthesiscited by 1
  2. 2024TAEGAN: Generating Synthetic Tabular Data For Data Augmentationcited by 1
  3. 2025Imputation-free Learning of Tabular Data with Missing Values using Incremental Feature Partitions in Transformercited by 1
  4. 2025DepMicroDiff: Diffusion-Based Dependency-Aware Multimodal Imputation for Microbiome Datacited by 1
  5. 2024M3-Impute: Mask-guided Representation Learning for Missing Value Imputationcited by 0
  6. 2025IMAGIC-500: IMputation benchmark on A Generative Imaginary Country (500k samples)cited by 0
  7. 2025Meta-Imputation Balanced (MIB): An Ensemble Approach for Handling Missing Data in Biomedical Machine Learningcited by 0
  8. 2025An Interdisciplinary and Cross-Task Review on Missing Data Imputationcited by 0
  9. 2025Masked Autoencoder Joint Learning for Robust Spitzoid Tumor Classificationcited by 0
  10. 2025Weighted Conformal Prediction Provides Adaptive and Valid Mask-Conditional Coverage for General Missing Data Mechanismscited by 0
  11. 2026Nearly Optimal Bayesian Inference for Structural Missingnesscited by 0
  12. 2026Harpoon: Generalised Manifold Guidance for Conditional Tabular Diffusioncited by 0
  13. 2026Learning Representations from Incomplete EHR Data with Dual-Masked Autoencodingcited by 0
  14. 2026Demystifying the Optimal Fair Classifier in Multi-Class Classificationcited by 0
  15. 2026Learning What Not to Impute: An Uncertainty-Aware Diffusion Framework for Meaningful Missingnesscited by 0
  16. 2026TabSODA: Tabular Diffusion based Imputation with Skip Pattern Detection and Ordinal Awarenesscited by 0
  17. 2026SafeImpute: Reliable Clinical Data Imputation via Conformal Selectioncited by 0
  18. 2026Imputation Meets Clustering: Exploiting Latent Subgroup Structure for Missing Data Recoverycited by 0
  19. 2026Closing the loop in learning with missing datacited by 0
  20. 2026Impute-EM: Native Mixed-State Diffusion Models for Heterogeneous Data Imputationcited by 0
  21. 2026Fed-ReMasker: Federated Tabular Imputation under Feature-Level Missingnesscited by 0
  22. 2026Learning Causal Normalizing Flows from Incomplete Data via Observed-Data Likelihoodcited by 0
  23. 2026Marformer: A Transformer for Predicting Missing Data Distributionscited by 0
  24. 2026TabMosaic: Unified In-Context Diffusion for Tabular Generative Taskscited by 0
  25. 2026When Does Task-Aware Imputation Matter? An Analysis of Robustness Under Train-Test Mismatchcited by 0