Graph Navier Stokes Networks
For graph neural network researchers, GNSN provides a new paradigm to mitigate oversmoothing and improve performance on heterophilic graphs.
Graph Navier Stokes Networks (GNSN) introduces a novel architecture that incorporates convection into graph message passing, addressing the oversmoothing problem in GNNs. It consistently outperforms state-of-the-art baselines across twelve real-world datasets in classification accuracy.
Graph Neural Networks (GNNs) have emerged as a cornerstone of deep learning, with most existing methods rooted in graph signal processing and diffusion equations to model message passing. However, these approaches inherently suffer from the oversmoothing problem, where node features become indistinguishable as the network depth increases. Inspired by the Navier Stokes equations, we introduce Graph Navier Stokes Networks (GNSN), a novel architecture that transcends conventional diffusion-based message passing by incorporating convection into graph structures. GNSN defines a dynamic velocity field on the graph to govern convection, enabling more efficient and direct message propagation. By adaptively balancing convection and diffusion, GNSN is able to efficiently handle datasets with varying levels of homophily. Extensive evaluations across twelve real-world datasets demonstrate that GNSN consistently outperforms state-of-the-art baselines in classification accuracy. Moreover, experimental results further emphasize its effectiveness in alleviating the oversmoothing problem.