<ul data-eligibleForWebStory="true"><li>CFMI (Conditional Flow Matching for Imputation) is a new method introduced for imputing missing data.</li><li>The methodology combines continuous normalizing flows, flow-matching, and shared conditional modeling to address traditional multiple imputation challenges.</li><li>Comparison with nine classical and state-of-the-art imputation methods on 24 small to moderate-dimensional datasets shows that CFMI matches or surpasses them across various metrics.</li><li>When applied to zero-shot imputation of time-series data, CFMI matches the accuracy of a diffusion-based method while being more computationally efficient.</li><li>CFMI performs as well as traditional methods on lower-dimensional data and scales effectively to high-dimensional settings, often outperforming other deep learning-based approaches.</li></ul>

CFMI: Flow Matching for Missing Data Imputation

Discover more