GREAD: Graph Neural Reaction-Diffusion Networks
This addresses a key limitation in GNNs for graph learning tasks, though it appears incremental as it builds on existing reaction-diffusion approaches.
The paper tackles the oversmoothing problem in graph neural networks (GNNs) by proposing GREAD, a method based on reaction-diffusion equations that incorporates all popular types of reaction equations and a custom-designed one, achieving superior performance in experiments with 9 datasets and 28 baselines.
Graph neural networks (GNNs) are one of the most popular research topics for deep learning. GNN methods typically have been designed on top of the graph signal processing theory. In particular, diffusion equations have been widely used for designing the core processing layer of GNNs, and therefore they are inevitably vulnerable to the notorious oversmoothing problem. Recently, a couple of papers paid attention to reaction equations in conjunctions with diffusion equations. However, they all consider limited forms of reaction equations. To this end, we present a reaction-diffusion equation-based GNN method that considers all popular types of reaction equations in addition to one special reaction equation designed by us. To our knowledge, our paper is one of the most comprehensive studies on reaction-diffusion equation-based GNNs. In our experiments with 9 datasets and 28 baselines, our method, called GREAD, outperforms them in a majority of cases. Further synthetic data experiments show that it mitigates the oversmoothing problem and works well for various homophily rates.