Rethinking GNNs and Missing Features: Challenges, Evaluation and a Robust Solution

2026-01-08

arXiv.org

AI Summary

This work addresses the challenge of non-missing-completely-at-random (non-MCAR) node feature missingness, a common yet underexplored issue in real-world graph neural network (GNN) applications. While existing methods often rely on high-dimensional sparse features and the MCAR assumption, limiting their generalizability, this study establishes a more realistic evaluation framework by introducing new datasets with dense semantic features and a standardized protocol for non-MCAR missingness mechanisms. Building upon missing data theory, the authors propose GNNmim, a lightweight and robust model designed to handle diverse missing patterns. Extensive experiments demonstrate that GNNmim consistently matches or surpasses the performance of specialized models across multiple datasets and missingness scenarios, confirming its effectiveness and strong generalization capability.

Technology Category

• Machine Learning: Graph-based Machine Learning
• Data Mining & Knowledge Management: Graph Mining, Social Network Analysis & Community
• Reasoning under Uncertainty: Graphical Models

Application Category

• Graph Algorithms and Modeling for the Web: Graph neural networks and deep learning approaches for Web-related graphs
• Web Mining and Content Analysis: Web data generation and simulation
• Semantics and Knowledge: Methods to enhance, augment, integrate or synergize semantic models such as knowledge graphs and LLMs

Abstract

Handling missing node features is a key challenge for deploying Graph Neural Networks (GNNs) in real-world domains such as healthcare and sensor networks. Existing studies mostly address relatively benign scenarios, namely benchmark datasets with (a) high-dimensional but sparse node features and (b) incomplete data generated under Missing Completely At Random (MCAR) mechanisms. For (a), we theoretically prove that high sparsity substantially limits the information loss caused by missingness, making all models appear robust and preventing a meaningful comparison of their performance. To overcome this limitation, we introduce one synthetic and three real-world datasets with dense, semantically meaningful features. For (b), we move beyond MCAR and design evaluation protocols with more realistic missingness mechanisms. Moreover, we provide a theoretical background to state explicit assumptions on the missingness process and analyze their implications for different methods. Building on this analysis, we propose GNNmim, a simple yet effective baseline for node classification with incomplete feature data. Experiments show that GNNmim is competitive with respect to specialized architectures across diverse datasets and missingness regimes.

Problem

• Graph Neural Networks
• Missing Features
• Node Classification
• Missingness Mechanisms
• Real-world Datasets

Innovation

• Graph Neural Networks
• Missing Features
• Non-MCAR Missingness
• GNNmim
• Robust Evaluation