Abstract: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.
| Subjects: | Machine Learning (cs.LG) |
| Cite as: | arXiv:2605.21247 [cs.LG] |
| (or arXiv:2605.21247v1 [cs.LG] for this version) | |
| https://doi.org/10.48550/arXiv.2605.21247 arXiv-issued DOI via DataCite (pending registration) |
From: Zexing Zhao [view email]
[v1]
Wed, 20 May 2026 14:36:52 UTC (2,492 KB)
此内容由惯性聚合(RSS阅读器)自动聚合整理，仅供阅读参考。 原文来自 — 版权归原作者所有。