CACTI: Leveraging Copy Masking and Contextual Information to Improve Tabular Data Imputation

We present CACTI, a masked autoencoding approach for imputing tabular data that leverages the structure in missingness patterns and contextual information. Our approach employs a novel median truncated copy masking training strategy that encourages the model to learn from empirical patterns of missingness while incorporating semantic relationships between features - captured by column names and text descriptions - to better represent feature dependence. These dual sources of inductive bias enable CACTI to outperform state-of-the-art methods - an average $R^2$ gain of 7.8% over the next best method (13.4%, 6.1%, and 5.3% under missing not at random, at random and completely at random, respectively) - across a diverse range of datasets and missingness conditions. Our results highlight the value of leveraging dataset-specific contextual information and missingness patterns to enhance imputation performance.

@article{gorla2025_2506.02306,
  title={ CACTI: Leveraging Copy Masking and Contextual Information to Improve Tabular Data Imputation },
  author={ Aditya Gorla and Ryan Wang and Zhengtong Liu and Ulzee An and Sriram Sankararaman },
  journal={arXiv preprint arXiv:2506.02306},
  year={ 2025 }
}