Learning to Drop: Robust Graph Neural Network via Topological Denoising
This work improves the robustness and generalization performance of GNNs for practitioners working with real-world, often noisy, graph data.
This paper addresses the issue of noisy input graphs in Graph Neural Networks (GNNs) by proposing PTDNet, a parameterized topological denoising network. PTDNet learns to drop task-irrelevant edges and applies nuclear norm regularization to the sparsified graph, leading to significant performance improvements for GNNs, especially on noisier datasets.
Graph Neural Networks (GNNs) have shown to be powerful tools for graph analytics. The key idea is to recursively propagate and aggregate information along edges of the given graph. Despite their success, however, the existing GNNs are usually sensitive to the quality of the input graph. Real-world graphs are often noisy and contain task-irrelevant edges, which may lead to suboptimal generalization performance in the learned GNN models. In this paper, we propose PTDNet, a parameterized topological denoising network, to improve the robustness and generalization performance of GNNs by learning to drop task-irrelevant edges. PTDNet prunes task-irrelevant edges by penalizing the number of edges in the sparsified graph with parameterized networks. To take into consideration of the topology of the entire graph, the nuclear norm regularization is applied to impose the low-rank constraint on the resulting sparsified graph for better generalization. PTDNet can be used as a key component in GNN models to improve their performances on various tasks, such as node classification and link prediction. Experimental studies on both synthetic and benchmark datasets show that PTDNet can improve the performance of GNNs significantly and the performance gain becomes larger for more noisy datasets.