Pattern-Aware Graph Neural Networks for Handling Missing Data
Publication Date
1-1-2026
Document Type
Conference Proceeding
Publication Title
2026 International Conference on Advances in Artificial Intelligence and Machine Learning Aaiml 2026
DOI
10.1109/AAIML67890.2026.11498101
First Page
62
Last Page
67
Abstract
Missing data is ubiquitous in real-world datasets. Traditional methods either discard incomplete samples or apply imputation techniques that ignore potentially informative missingness patterns, implicitly assuming that missingness occurs randomly. However, missingness patterns might provide additional information. We propose pattern-aware graph neural networks that explicitly encode which features are missing alongside observed values. We used four encoding strategies-learned embeddings, frozen random embeddings, statistical features, and hierarchical representations-across seven UCI datasets with naturally occurring missingness. Our Pattern-aware methods achieve substantial improvements over baselines, with an average improvement of 17% in balanced accuracy and 22% in F1-macro across all datasets. Our code and data are available at https://github.com/TranMinett/pattern_aware_GRAPE.
Keywords
Bipartite Graphs, Graph Neural Networks, Missing Data, Pattern Encoding, Tabular Data
Department
Applied Data Science
Recommended Citation
Minett Tran and Taehee Jeong. "Pattern-Aware Graph Neural Networks for Handling Missing Data" 2026 International Conference on Advances in Artificial Intelligence and Machine Learning Aaiml 2026 (2026): 62-67. https://doi.org/10.1109/AAIML67890.2026.11498101
