研究人员分析了由图神经网络（GNN）参数化的连续归一化流模型，以了解结构误差如何影响图信号生成。他们推导出了明确的稳定性界限，展示了图结构中的扰动如何影响最终采样的信号。为了增强鲁棒性，他们引入了一种促进稳定性的正则化流匹配策略，在训练过程中惩罚空间Lipschitz常数，并在合成和真实世界fMRI数据上显示出改进的性能。 AI
排序理由 关于图信号生成模型的学术论文。[lever_c_demoted from research: ic=1 ai=1.0]
AI 生成摘要 · Google Gemini · 来自 2 个来源。 我们如何撰写摘要 →
arXiv:2607.07510v1 Announce Type: cross 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 doc…
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 propa…