Improving Graph Neural Networks via Adversarial Robustness Evaluation
This addresses noise robustness in GNNs for graph-based learning tasks, but it appears incremental as it builds on existing adversarial evaluation techniques.
The paper tackles the problem of Graph Neural Networks (GNNs) being vulnerable to noisy edges in graph topology by using adversarial robustness evaluation to select robust nodes and assign non-robust nodes via centroids, resulting in significantly improved accuracy.
Graph Neural Networks (GNNs) are currently one of the most powerful types of neural network architectures. Their advantage lies in the ability to leverage both the graph topology, which represents the relationships between samples, and the features of the samples themselves. However, the given graph topology often contains noisy edges, and GNNs are vulnerable to noise in the graph structure. This issue remains unresolved. In this paper, we propose using adversarial robustness evaluation to select a small subset of robust nodes that are less affected by noise. We then only feed the features of these robust nodes, along with the KNN graph constructed from these nodes, into the GNN for classification. Additionally, we compute the centroids for each class. For the remaining non-robust nodes, we assign them to the class whose centroid is closest to them. Experimental results show that this method significantly improves the accuracy of GNNs.