#machine learning #data science Preprint

Stable Filters for Generative Modeling of Graph Signals

M. Schmidt Gonzalo Mateos

Sep 2026 · 0 citations · 27 references

Engineering Computer Science Mathematics

TL;DR

This paper derives explicit Wasserstein stability bounds that quantify the effect of relative graph perturbations on the generated distributions and introduces a principled framework for designing stable graph filters that preserve the smoothing behavior of graph heat diffusion, while boosting structural stability.

Abstract

Generating signals on graphs requires permutation-equivariant models that exhibit stability with respect to relative structural perturbations. While recent graph-aware Schr\"odinger bridge models incorporate topology information directly into their reference dynamics, it is unclear how perturbations of the graph propagate through these dynamics and affect the resulting generated distributions. In this paper, we analyze the structural stability of graph-aware continuous-time generative models whose drift combines a graph filter with a learned graph neural network. We derive explicit Wasserstein stability bounds that quantify the effect of relative graph perturbations on the generated distributions. Motivated by these bounds, we introduce a principled framework for designing stable graph filters that preserve the smoothing behavior of graph heat diffusion, while boosting structural stability. Experiments on synthetic and fMRI signals show our stable filters enhance structural robustness while matching or exceeding the generative quality of the heat equation baseline.

DOI arXiv Semantic Scholar

View source

Similar papers

#graph neural networks Review Sep 2026

Shaping Graph Neural Networks with Dynamical Systems

This work presents a unified dynamical-systems perspective for shaping approaches that explicitly control and regulate the degree of propagation, conservation, and dissipation of information throughout the neural flow, and highlights how neural differential equations provide a coherent theoretical framework for designi...

Alessio Gravina · Intelligenza Artificiale · 0 citations

#artificial intelligence Preprint Sep 2026

A Unified Uncertainty Representation for Graph Neural Networks via Doubly-Spectral Stochastic Expansion

A capacity theorem shows that, under a full-rank feature assumption, a restricted subfamily matches the chaos coefficients of any Gaussian-latent random graph signal, with exponentially decaying truncation error under a growth condition; the task-level claims are established empirically.

Fred Xu, Thomas Markovich, Florence Regol et al. · 0 citations

#machine learning Preprint Oct 2026

Stability-Shaped Deep Graph Learning

In deep graph neural networks, increasing depth enlarges the receptive field but often leads to over-smoothing, where node representations tend to align. We develop a unified, mode-wise stability framework for deep GNN propagation that provides a principled characterization of over-smoothing. By interpreting layer dept...

Jun-You Zhu, Lang-Zhou He, Fen-Ying Cai et al. · 0 citations

#graph neural networks Open access Sep 2026

Topology-aware GNNs under structural perturbations: Empirical robustness across domains

Results support a conditional empirical conclusion: combining structure, topology, and stability-oriented training can improve robustness under specified structural perturbations, with dataset-dependent accuracy–stability trade-offs rather than universal guarantees.

Jelena Losic, Charles Fanning · PLOS Complex Systems · 0 citations

Preprint Sep 2026

Spectral Dynamics of DeepWalk Embeddings for Dynamic Network Change-Point Detection

Dynamic networks describe evolving relational systems in which abrupt structural changes may signal anomalous events or important transitions. Detecting such changes requires distinguishing genuine structural signals from fluctuations in network observations and learned representations. We propose a DeepWalk-based fram...

Hou-Lin Zhou, Ye-Jin Wang, Xu-Fei Tang et al. · 0 citations

#machine learning Preprint Oct 2026

Efficient Graph Generation via Direct Prediction and Flow Matching

Generative modeling of graph-structured data is crucial for tasks ranging from drug discovery to social network simulation. Among these models, denoising diffusion models have achieved great success in graph generation by learning to progressively reverse a process that adds noise to the original graph. However, the st...

Susie Lu · 0 citations