Graph Navier Stokes Networks

• URL: http://arxiv.org/abs/2605.21247v2
• Date: Mon, 25 May 2026 15:42:38 GMT
• Title: Graph Navier Stokes Networks
• Abstract summary: We introduce Graph Navier Stokes Networks (GNSN), a novel architecture that transcends conventional diffusion-based message passing.<n>GNSN defines a dynamic velocity field on the graph to govern convection, enabling more efficient and direct message propagation.<n>GNSN consistently outperforms state-of-the-art baselines in classification accuracy.
• Score: 47.79249022892634
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• 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.

Related papers

• Graph Signal Generative Diffusion Models [74.75869068073577]
  We introduce U-shaped encoder-decoder graph neural networks (U-GNNs) for graph signal generation using denoising diffusion processes.<n>The architecture learns node features at different resolutions with skip connections between the encoder and decoder paths.<n>We demonstrate the effectiveness of the diffusion model in probabilistic forecasting of stock prices.
  arXiv  Detail & Related papers  (2025-09-21T21:57:27Z)
• Superposition in Graph Neural Networks [11.888196115363298]
  We study superposition, the sharing of directions by multiple features, directly in the latent space of graph neural networks (GNNs)<n>Across GCN/GIN/GAT we find: increasing width produces a phase pattern in overlap; topology imprints overlap onto node-level features that pooling partially remixes into task-aligned graph axes.
  arXiv  Detail & Related papers  (2025-08-31T16:43:29Z)
• Topology-aware Neural Flux Prediction Guided by Physics [13.352980442733987]
  Graph Neural Networks (GNNs) often struggle in preserving high-frequency components of nodal signals when dealing with directed graphs.<n>This paper proposes a novel framework that combines 1) explicit difference matrices that model directional gradients and 2) implicit physical constraints that enforce messages passing within GNNs to be consistent with natural laws.
  arXiv  Detail & Related papers  (2025-06-06T02:01:50Z)
• Directed Homophily-Aware Graph Neural Network [7.539052660225002]
  We propose Directed Homophily-aware Graph Neural Network (DHGNN), a novel framework that incorporates homophily-aware and direction-sensitive components.<n>DHGNN employs a resettable gating mechanism to adaptively modulate message contributions based on homophily levels and informativeness.<n>Our analysis shows that the gating mechanism captures directional homophily gaps and fluctuating homophily across layers, providing deeper insights into message-passing behavior on complex graph structures.
  arXiv  Detail & Related papers  (2025-05-28T13:41:04Z)
• Graph Spring Neural ODEs for Link Sign Prediction [49.71046810937725]
  We propose a novel message-passing layer architecture called Graph Spring Network (GSN) modeled after spring forces.<n>We show that our method achieves accuracy close to the state-of-the-art methods with node generation time speedup factors of up to 28,000 on large graphs.
  arXiv  Detail & Related papers  (2024-12-17T13:50:20Z)
• Overcoming Oversmoothness in Graph Convolutional Networks via Hybrid Scattering Networks [11.857894213975644]
  We propose a hybrid graph neural network (GNN) framework that combines traditional GCN filters with band-pass filters defined via the geometric scattering transform. Our theoretical results establish the complementary benefits of the scattering filters to leverage structural information from the graph, while our experiments show the benefits of our method on various learning tasks.
  arXiv  Detail & Related papers  (2022-01-22T00:47:41Z)
• Spectral Graph Convolutional Networks With Lifting-based Adaptive Graph Wavelets [81.63035727821145]
  Spectral graph convolutional networks (SGCNs) have been attracting increasing attention in graph representation learning. We propose a novel class of spectral graph convolutional networks that implement graph convolutions with adaptive graph wavelets.
  arXiv  Detail & Related papers  (2021-08-03T17:57:53Z)
• Uniting Heterogeneity, Inductiveness, and Efficiency for Graph Representation Learning [68.97378785686723]
  graph neural networks (GNNs) have greatly advanced the performance of node representation learning on graphs. A majority class of GNNs are only designed for homogeneous graphs, leading to inferior adaptivity to the more informative heterogeneous graphs. We propose a novel inductive, meta path-free message passing scheme that packs up heterogeneous node features with their associated edges from both low- and high-order neighbor nodes.
  arXiv  Detail & Related papers  (2021-04-04T23:31:39Z)
• Graph Highway Networks [77.38665506495553]
  Graph Convolution Networks (GCN) are widely used in learning graph representations due to their effectiveness and efficiency. They suffer from the notorious over-smoothing problem, in which the learned representations converge to alike vectors when many layers are stacked. We propose Graph Highway Networks (GHNet) which utilize gating units to balance the trade-off between homogeneity and heterogeneity in the GCN learning process.
  arXiv  Detail & Related papers  (2020-04-09T16:26:43Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.