Sampling-guided Heterogeneous Graph Neural Network with Temporal Smoothing for Scalable Longitudinal Data Imputation

TL;DR

This paper introduces SHT-GNN, a scalable graph neural network framework that effectively imputes missing data in large, complex longitudinal datasets by modeling observations and covariates with temporal smoothing.

Contribution

The paper presents a novel GNN framework that handles arbitrary missing data patterns in longitudinal studies using subject-specific subnetworks and temporal smoothing, improving scalability and accuracy.

Findings

Outperforms existing imputation methods on synthetic and real datasets.

Effectively handles high missing data rates in large-scale longitudinal data.

Demonstrates robustness and superior performance in complex data scenarios.

Abstract

In this paper, we propose a novel framework, the Sampling-guided Heterogeneous Graph Neural Network (SHT-GNN), to effectively tackle the challenge of missing data imputation in longitudinal studies. Unlike traditional methods, which often require extensive preprocessing to handle irregular or inconsistent missing data, our approach accommodates arbitrary missing data patterns while maintaining computational efficiency. SHT-GNN models both observations and covariates as distinct node types, connecting observation nodes at successive time points through subject-specific longitudinal subnetworks, while covariate-observation interactions are represented by attributed edges within bipartite graphs. By leveraging subject-wise mini-batch sampling and a multi-layer temporal smoothing mechanism, SHT-GNN efficiently scales to large datasets, while effectively learning node representations and imputing missing data. Extensive experiments on both synthetic and real-world datasets, including the Alzheimer's Disease Neuroimaging Initiative (ADNI) dataset, demonstrate that SHT-GNN significantly outperforms existing imputation methods, even with high missing data rates. The empirical results highlight SHT-GNN's robust imputation capabilities and superior performance, particularly in the context of complex, large-scale longitudinal data.