HRGNN: Learning Holistically Robust Graph Neural Networks on Noisy Graphs with Label Scarcity
Jun-Wei Chiu, Cheng-te Li · ACM Transactions on Intelligent Systems and Technology · 2025
Graph Neural Networks (GNNs) have recently achieved remarkable performance on the node classification task. While most typical GNN models presume that the graph data is clean, however, graphs could be polluted by various noises that hurt the prediction accuracy. Besides, while GNNs rely on sufficient labeled data to propagate the supervision signal, we should move to a more realistic setting—to learn with a limited amount of labeled data, i.e., label scarcity. In this work, we aim at building a Holistically Robust Graph Neural Network (HRGNN) against four different types of graph noise, including adversarial attacks, edge sparsity, noisy labels, and high heterophily, in the presence of label scarcity. We proposed a novel GNN framework, HRGNN, to fulfill the goal. The main idea of HRGNN is to create synthetic nodes with labels and learn to properly connect them with existing nodes. With synthetic nodes, HRGNN can inject reliable information into existing nodes due to the message-passing mechanism of GNNs that helps purify the polluted representations of nodes and alleviate the negative effect caused by various noises. Furthermore, edge filtering in HRGNN helps remove the noisy edges to prevent the propagation of incorrect information, while pseudo-labeling provides more label information to defend against label scarcity and label noise. Experiments conducted on eight graph datasets exhibit that HRGNN consistently outperforms the state-of-the-art GNN competing models on four types of noisy settings with label scarcity. To the best of our knowledge, HRGNN is the first GNN model that is holistically robust to various types of noise and label scarcity.