Saved in:
Bibliographic Details
Main Authors: Gorla, Aditya, Wang, Ryan, Liu, Zhengtong, An, Ulzee, Sankararaman, Sriram
Format: Preprint
Published: 2025
Subjects:
Online Access:https://arxiv.org/abs/2506.02306
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866913872078700544
author Gorla, Aditya
Wang, Ryan
Liu, Zhengtong
An, Ulzee
Sankararaman, Sriram
author_facet Gorla, Aditya
Wang, Ryan
Liu, Zhengtong
An, Ulzee
Sankararaman, Sriram
contents 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.
format Preprint
id arxiv_https___arxiv_org_abs_2506_02306
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle CACTI: Leveraging Copy Masking and Contextual Information to Improve Tabular Data Imputation
Gorla, Aditya
Wang, Ryan
Liu, Zhengtong
An, Ulzee
Sankararaman, Sriram
Machine Learning
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.
title CACTI: Leveraging Copy Masking and Contextual Information to Improve Tabular Data Imputation
topic Machine Learning
url https://arxiv.org/abs/2506.02306