Enhancing Graph Structures for Node Classification: An Alternative View on Adversarial Attacks

Recently, graph neural networks (GNNs) have become a popular approach to deal with machine learning tasks for graph-structured data. To achieve reliable performance with a GNN-based approach, obtaining high-quality graph structures is crucial. However, the graph data in the real-world often contain noise from data themselves or during the collecting procedure, which leads to the performance degradation of GNNs. In this paper, we propose a novel approach to enhance graph structures for performance improvement of GNNs by reversely applying the concept of adversarial attacks on graph data. Experimental results demonstrate the effectiveness of our method in improving performance of GNNs. Furthermore, we investigate the changes in the graph structure induced by our method, taking into account the connectivity of both interclass and intra-class edges and measuring the extent of over-smoothing.