Stability of Flow Models for Graph Signals

• URL: http://arxiv.org/abs/2607.07510v1
• Date: Wed, 08 Jul 2026 15:04:39 GMT
• Title: Stability of Flow Models for Graph Signals
• Abstract summary: We analyze continuous normalized flow models parameterized by Graph Neural Networks (GNNs)<n>We derive explicit stability bounds on the generated probability distributions.<n>Experiments using synthetic smooth signals on block model graphs and real-world fMRI signals on brain connectomes demonstrate that this bound-oriented approach generative models are more robust to structural noise, without sacrificing output quality.
• Score: 11.329941453877444
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Generating signals on graphs requires permutation-equivariant models that exhibit stability with respect to relative structural perturbations. While favorable stability properties of Graph Neural Networks (GNNs) have been well documented, it is unclear how structural errors propagate through the dynamics of continuous generative flow models that are gaining traction for graph signal generation. In this paper, we analyze continuous normalized flow models parameterized by GNNs and show that permutation equivariance is preserved for both the resulting continuous-time ordinary differential equations and their discrete numerical approximations used as graph signal samplers. Our primary contribution is to derive explicit stability bounds on the generated probability distributions, which quantify how relative graph perturbations affect the final sampled signals. Motivated by these theoretical bounds, we introduce a stability-promoting regularized flow matching strategy that actively penalizes the spatial Lipschitz constant of the vector field during model training. Experiments using synthetic smooth signals on stochastic block model graphs and real-world fMRI signals on brain connectomes demonstrate that this bound-oriented approach yields generative models that are more robust to structural noise, without sacrificing output quality.

Related papers

• 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)
• Latent-Hysteresis Graph ODEs: Modeling Coupled Topology-Feature Evolution via Continuous Phase Transitions [4.104525618451057]
  Graph neural ordinary differential equations (Graph ODEs) extend graph learning from discrete message-passing layers to continuous-time representation flows.<n>We show that Graph ODEs with strictly positive irreducible mixing operators face an inherent emphmonostability trap: in the long-time regime, information leakage is unavoidable and the dynamics converge to a single global consensus attractor.
  arXiv  Detail & Related papers  (2026-04-27T10:27:41Z)
• Conditional Score-Based Modeling of Effective Langevin Dynamics [0.0]
  We introduce a data-driven calibration method based on a relationship between the coefficients of a reduced model and a finite-time transition density.<n>The resulting identity expresses derivatives of lagged correlation functions as stationary expectations over observed lagged pairs.<n>We validate the approach on analytically tractable and data-driven nonequilibrium diffusions.
  arXiv  Detail & Related papers  (2026-04-27T01:58:16Z)
• GeodesicNVS: Probability Density Geodesic Flow Matching for Novel View Synthesis [54.39598154430305]
  We propose a Data-to-Data Flow Matching framework that learns deterministic transformations directly between paired views.<n>PDG-FM constrains flow trajectories using geodesic interpolants derived from probability density metrics of pretrained diffusion models.<n>These results highlight the advantages of incorporating data-dependent geometric regularization into deterministic flow matching for consistent novel view generation.
  arXiv  Detail & Related papers  (2026-03-01T09:30:11Z)
• Variational Bayesian Flow Network for Graph Generation [54.94088904387278]
  We propose Variational Bayesian Flow Network (VBFN) for graph generation.<n>VBFN performs variational lifting to a tractable joint Gaussian variational belief family governed by structured precisions.<n>On synthetic and molecular graph datasets, VBFN improves fidelity and diversity, and surpasses baseline methods.
  arXiv  Detail & Related papers  (2026-01-30T03:59:38Z)
• Discrete Bayesian Sample Inference for Graph Generation [48.418206985863726]
  We introduce GraphBSI, a novel one-shot graph generative model based on Bayesian Sample Inference (BSI)<n>We state BSI as a differential equation (SDE) and derive a noise-controlled family of SDEs that preserves the marginal distributions via an approximation of the score function.<n>In our empirical evaluation, we demonstrate state-of-the-art performance on molecular and synthetic graph generation, outperforming existing one-shot graph generative models.
  arXiv  Detail & Related papers  (2025-11-04T21:25:51Z)
• Learning Time-Varying Graphs from Incomplete Graph Signals [1.7430416823420511]
  We develop an efficient Alternating Direction Multiplier algorithm for solving the problem of imputing missing data from a graph.<n>We prove that the proposed ADMM scheme converges to and we derive a stationary point.
  arXiv  Detail & Related papers  (2025-10-19T11:12:13Z)
• Uncertainty Estimation on Graphs with Structure Informed Stochastic Partial Differential Equations [1.2584276673531931]
  Graph Neural Networks have achieved impressive results across diverse network modeling tasks, but accurately estimating uncertainty on graphs remains difficult.<n>We present a principled way to design a novel message passing scheme that incorporates spatial-temporal noises motivated by the Gaussian Process approach to SPDE.<n>Our method simultaneously captures uncertainty across space and time and allows explicit control over the covariance kernel smoothness, thereby enhancing uncertainty estimates on graphs with both low and high label informativeness.
  arXiv  Detail & Related papers  (2025-06-07T19:58:38Z)
• Simple and Critical Iterative Denoising: A Recasting of Discrete Diffusion in Graph Generation [0.0]
  dependencies between intermediate noisy states lead to error accumulation and propagation during the reverse denoising process.<n>We propose a novel framework called Simple Iterative Denoising, which simplifies discrete diffusion and circumvents the issue.<n>Our empirical evaluations demonstrate that the proposed method significantly outperforms existing discrete diffusion baselines in graph generation tasks.
  arXiv  Detail & Related papers  (2025-03-27T15:08:58Z)
• Dynamic Causal Explanation Based Diffusion-Variational Graph Neural Network for Spatio-temporal Forecasting [60.03169701753824]
  We propose a novel Dynamic Diffusion-al Graph Neural Network (DVGNN) fortemporal forecasting. The proposed DVGNN model outperforms state-of-the-art approaches and achieves outstanding Root Mean Squared Error result.
  arXiv  Detail & Related papers  (2023-05-16T11:38:19Z)
• Score-based Generative Modeling of Graphs via the System of Stochastic Differential Equations [57.15855198512551]
  We propose a novel score-based generative model for graphs with a continuous-time framework. We show that our method is able to generate molecules that lie close to the training distribution yet do not violate the chemical valency rule.
  arXiv  Detail & Related papers  (2022-02-05T08:21:04Z)

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.