IVGAE: Handling Incomplete Heterogeneous Data with a Variational Graph Autoencoder

TL;DR

IVGAE introduces a graph-based autoencoder framework that effectively imputes missing heterogeneous data by modeling structural dependencies and missingness patterns, outperforming existing methods across various real-world datasets.

Contribution

The paper proposes IVGAE, a novel variational graph autoencoder with a dual-decoder and Transformer-based embeddings for improved handling of incomplete heterogeneous data.

Findings

IVGAE outperforms existing methods in RMSE and F1 scores.

Effective in various missing data scenarios including MCAR, MAR, and MNAR.

Achieves consistent improvements across 16 real-world datasets.

Abstract

Handling missing data remains a fundamental challenge in real-world tabular datasets, especially when data are heterogeneous with both numerical and categorical features. Existing imputation methods often fail to capture complex structural dependencies and handle heterogeneous data effectively. We present \textbf{IVGAE}, a Variational Graph Autoencoder framework for robust imputation of incomplete heterogeneous data. IVGAE constructs a bipartite graph to represent sample-feature relationships and applies graph representation learning to model structural dependencies. A key innovation is its \textit{dual-decoder architecture}, where one decoder reconstructs feature embeddings and the other models missingness patterns, providing structural priors aware of missing mechanisms. To better encode categorical variables, we introduce a Transformer-based heterogeneous embedding module that avoids high-dimensional one-hot encoding. Extensive experiments on 16 real-world datasets show that IVGAE achieves consistent improvements in RMSE and downstream F1 across MCAR, MAR, and MNAR missing scenarios under 30\% missing rates. Code and data are available at: https://github.com/echoid/IVGAE.