Graph filters improve stability when generating data on networks
Stabilizing Filters for Graph Signal Generation
Machine Learning
Summary
Generating signals that sit on networks, like social connections or brain regions, can be tricky because the network itself might have errors. The authors studied how small mistakes in the network affect the data generation process and found a way to measure this impact precisely. They then designed special filters that make the generation more stable despite those errors, all while keeping the generated signals meaningful. Tests on fake and brain data showed these filters work well at balancing stability and signal quality.
What this means in practice
- •For medical image processors: Generate robust brain activity signals from noisy fMRI networks to improve analysis in neurological studies.
- •For social network engineers: Create stable synthetic user or content propagation data on imperfect social graphs for testing recommendation algorithms.
Authors
Martin Schmidt, Gonzalo Mateos
Abstract
Generating graph signals is an important task in machine learning, and incorporating the underlying graph into a generative model enables structurally-informed distribution modeling. However, said graph is often noisy or imperfectly estimated, and structural errors can affect the generative process and the resulting signal distribution. While recent work has established stability guarantees for graph neural ordinary differential equations, the robustness of graph-aware reference dynamics, as used in topological Schrödinger bridge models, remains largely unexplored. Here, we investigate the structural stability of continuous-time generative models whose dynamics combine a graph filter with a learned graph neural network. We first derive a Wasserstein stability bound that quantifies the effect of graph perturbations on the generated signal distributions. Informed by this analysis, we then propose a principled framework for designing graph filters that balance structural stability with induced signal smoothing. We characterize the optimal filter design and provide an explicit family of polynomial filters with provable stability guarantees. Experiments on synthetic graphs and real-world fMRI signals support our theoretical findings, illustrating the enhanced structural stability of the proposed filters while preserving generative performance.