From Diffusion to Reaction-Diffusion: A Dynamical-Systems View of Oversmoothing in Hypergraph Neural Networks

• URL: http://arxiv.org/abs/2607.15773v1
• Date: Fri, 17 Jul 2026 09:04:22 GMT
• Title: From Diffusion to Reaction-Diffusion: A Dynamical-Systems View of Oversmoothing in Hypergraph Neural Networks
• Abstract summary: This work investigates hypergraph oversmoothing from a dynamical-systems perspective.<n>We develop a reaction--diffusion framework for depth-resistant hypergraph learning.
• Score: 3.3213704823862433
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Higher-order couplings enhance the expressive power of hypergraph neural networks (HGNNs), but they also intensify representation collapse in deep propagation due to strong multi-way feature mixing. This work investigates hypergraph oversmoothing from a dynamical-systems perspective and develops a reaction--diffusion framework for depth-resistant hypergraph learning. By defining hypergraph gradient and divergence operators, we interpret message passing as an incidence-level diffusion process. The analysis of pure diffusion shows that its continuous semiflow exponentially contracts the null-mode-free component of node representations and drives the Dirichlet energy to zero, revealing hypergraph oversmoothing as an intrinsic transverse-energy dissipation phenomenon. Motivated by this analysis, we propose Hypergraph Neural Reaction--Diffusion (HNRD), which introduces a reaction mechanism acting on the transverse component to compensate diffusion-induced dissipation and stabilize discriminative variations. We establish global well-posedness of the proposed dynamics and prove that the null-mode-free Dirichlet energy remains bounded away from zero. A forward-Euler discretization provides a practical HNRD layer with a stability condition for deep propagation. Experiments on benchmark and synthetic heterophilic hypergraphs demonstrate that HNRD consistently improves over representative hypergraph baselines. Depth, robustness, and efficiency analyses further show that HNRD preserves stable performance and nonzero Dirichlet energy under deep propagation and perturbations. These results provide a principled dynamical framework for designing deep hypergraph architectures that maintain higher-order expressiveness without representation collapse.

Related papers

• Revisiting Spectral Representations in Generative Diffusion Models [98.43552218868837]
  Diffusion models have shown remarkable performance on diverse generation tasks.<n>Recent work finds that imposing representation alignment on the hidden states of diffusion networks can both facilitate training convergence and enhance sampling quality.<n>We investigate the connection between self-supervised spectral representation learning and diffusion generative models through a shared perspective on perturbation kernels.
  arXiv  Detail & Related papers  (2026-09-08T04:54:02Z)
• Fluid-DiT: Graph-Free Diffusion Transformers for Fluid Flow Simulations Learning [50.053186229257555]
  We propose a Graph-Free Diffusion Transformer that replaces graph message passing with attention-based denoising.<n>By leveraging the transformer's global receptive field, Fluid-DiT naturally captures both local flow structures and long-range correlations.<n>It consistently outperforms graph-based diffusion baselines in both sample quality and distributional accuracy.
  arXiv  Detail & Related papers  (2026-08-07T12:28:45Z)
• Persistent Gaussian Perturbations Prevent Oversmoothing in Recurrent Graph Neural Networks [2.8427946758947304]
  We study a recurrent graph neural network in which independent Gaussian noise is injected after every propagation step.<n>We prove that the hidden representations form a geometrically ergodic Markov chain admitting a unique invariant probability measure.<n>Our analysis reveals persistent perturbations as a fundamentally different mechanism for combating oversmoothing.
  arXiv  Detail & Related papers  (2026-07-30T13:21:18Z)
• HYVINT: Intensity-Driven Hypergraph Generation with Variational Representations [14.364205966885805]
  Hypergraphs provide a principled framework for modeling polyadic interactions.<n>Existing generators often rely on implicit latent spaces or continuous incidence decoders.<n>We propose HYVINT, an intensity-driven hypergraph generative framework.
  arXiv  Detail & Related papers  (2026-05-16T06:38:33Z)
• Detecting Deepfakes via Hamiltonian Dynamics [58.881686693914446]
  We propose a new perspective on deepfake detection: moving from static pattern recognition to dynamical stability analysis.<n>Our approach is motivated by physics-inspired priors.<n>Hamiltonian Action Anomaly Detection (HAAD) outperforms evaluated state-of-the-art baselines.
  arXiv  Detail & Related papers  (2026-05-06T01:55:38Z)
• Hypergraph Neural Diffusion: A PDE-Inspired Framework for Hypergraph Message Passing [6.809465248544176]
  Hypergraph Neural Diffusion is a novel framework that unifies nonlinear diffusion equations with neural message passing on hypergraphs.<n>We derive rigorous theoretical guarantees, including energy dissipation, solution boundedness via a discrete maximum principle, and stability under explicit and implicit numerical schemes.<n>Our results highlight the power of PDE-inspired design in enhancing the stability, expressivity, and interpretability of hypergraph learning.
  arXiv  Detail & Related papers  (2026-04-13T03:52:01Z)
• Stochastic Gradient Descent in the Saddle-to-Saddle Regime of Deep Linear Networks [74.46751089984072]
  gradient descent (SGD) noise on descent in deep linear networks is poorly understood.<n>We investigate the dynamics of SGD during training of DLNs in the saddle-to-saddle regime.<n>Our results establish that SGD noise encodes information about the progression of feature learning but does not fundamentally alter the saddle-to-saddle dynamics.
  arXiv  Detail & Related papers  (2026-04-07T18:43:08Z)
• Tackling Over-smoothing on Hypergraphs: A Ricci Flow-guided Neural Diffusion Approach [11.470914132766636]
  Hypergraph neural networks (HGNNs) have demonstrated strong capabilities in modeling complex higher-order relationships.<n>Existing HGNNs often suffer from over-smoothing as the number of layers increases and lack effective control over message passing among nodes.<n>We propose Ricci Flow-guided Hypergraph Neural Diffusion, a novel message passing paradigm for hypergraphs guided by discrete Ricci flow.
  arXiv  Detail & Related papers  (2026-03-16T06:19:19Z)
• PHASE-Net: Physics-Grounded Harmonic Attention System for Efficient Remote Photoplethysmography Measurement [63.007237197267834]
  Existing deep learning methods are mostly physiological monitoring and lack theoretical robustness.<n>We propose a physics-informed r paradigm derived from the Navier-Stokes equations of hemodynamics, showing that the pulse signal follows a second-order system.<n>This provides a theoretical justification for using a Temporal Conal Network (TCN)<n>Phase-Net achieves state-of-the-art performance with strong efficiency, offering a theoretically grounded and deployment-ready r solution.
  arXiv  Detail & Related papers  (2025-09-29T14:36:45Z)
• Transformers from Diffusion: A Unified Framework for Neural Message Passing [79.9193447649011]
  Message passing neural networks (MPNNs) have become a de facto class of model solutions.<n>We propose an energy-constrained diffusion model, which integrates the inductive bias of diffusion with layer-wise constraints of energy.<n>Building on these insights, we devise a new class of message passing models, dubbed Transformers (DIFFormer), whose global attention layers are derived from the principled energy-constrained diffusion framework.
  arXiv  Detail & Related papers  (2024-09-13T17:54:41Z)
• Continuous Geometry-Aware Graph Diffusion via Hyperbolic Neural PDE [36.48610732998552]
  We introduce theoretical principles textite.g., field and flow, gradient, divergence, and diffusivity on a non-Euclidean manifold for HPDE integration. We propose the Hyperbolic Graph Diffusion Equation (HGDE) -- a flexible vector flow function that can be integrated to obtain expressive hyperbolic node embeddings.
  arXiv  Detail & Related papers  (2024-06-03T12:50:58Z)
• Momentum Diminishes the Effect of Spectral Bias in Physics-Informed Neural Networks [72.09574528342732]
  Physics-informed neural network (PINN) algorithms have shown promising results in solving a wide range of problems involving partial differential equations (PDEs) They often fail to converge to desirable solutions when the target function contains high-frequency features, due to a phenomenon known as spectral bias. In the present work, we exploit neural tangent kernels (NTKs) to investigate the training dynamics of PINNs evolving under gradient descent with momentum (SGDM)
  arXiv  Detail & Related papers  (2022-06-29T19:03:10Z)

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.