具有 Lipschitz 损失函数的几何图神经网络的泛化性
Generalization of Geometric Graph Neural Networks with Lipschitz Loss Functions
AI总结:
本文证明几何图神经网络在 Lipschitz 损失下的泛化间隙,表明单个大图即可实现跨未见图泛化,并通过真实数据集实验验证。
摘要:
本文研究几何图神经网络(GNN)的泛化能力。我们考虑在几何图上的 GNN,该图由嵌入流形上有限个随机采样点构成,并捕获了拓扑信息。我们证明了该 GNN 的最优经验风险与最优统计风险之间存在泛化间隙,该间隙随从流形采样的点数增加而减小,并随底层流形维数增加而增大。这一泛化间隙确保在采样点构成的图上训练的 GNN,可用于处理由同一底层流形构建的其他未见图。最重要的观察是,泛化能力可通过一个大图实现,而不像以往结果那样受限于图的规模。该泛化间隙基于采样图上的 GNN 到底层流形神经网络(MNN)的非渐近收敛结果推导得出。我们在多个真实世界数据集上通过实验验证了这一理论结果。
英文摘要:
In this paper, we study the generalization capabilities of geometric graph neural networks (GNNs). We consider GNNs over a geometric graph constructed from a finite set of randomly sampled points over an embedded manifold with topological information captured. We prove a generalization gap between the optimal empirical risk and the optimal statistical risk of this GNN, which decreases with the number of sampled points from the manifold and increases with the dimension of the underlying manifold. This generalization gap ensures that the GNN trained on a graph on a set of sampled points can be utilized to process other unseen graphs constructed from the same underlying manifold. The most important observation is that the generalization capability can be realized with one large graph instead of being limited to the size of the graph as in previous results. The generalization gap is derived based on the non-asymptotic convergence result of a GNN on the sampled graph to the underlying manifold neural networks (MNNs). We verify this theoretical result with experiments on multiple real-world datasets.
机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。