arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2112.07575cs.LGcs.SYeess.SPeess.SY
收藏

基于概率Lipschitz约束的鲁棒图神经网络

Robust Graph Neural Networks via Probabilistic Lipschitz Constraints

University of Pennsylvania(宾夕法尼亚大学)

Raghu Arghal, Eric Lei, Shirin Saeedi Bidokhti

摘要:

图神经网络(GNN)最近已经被证明在诸如分散控制和资源分配的各种基于网络的任务上表现良好,并且为这些任务提供计算高效的方法,这些任务在这方面传统上是具有挑战性的。然而,像许多基于神经网络的系统一样,GNN容易受到输入的变化和扰动的影响,这些输入可能包括节点属性和图形结构。为了使它们对现实世界的应用程序更有用,重要的是要确保它们在部署后的健壮性。出于控制GNN滤波器的Lipschitz常数相对于节点属性,我们建议约束GNN的滤波器组的频率响应。我们将此公式扩展到使用连续频率响应约束的动态图设置,并通过场景方法解决问题的放松变体。这允许在采样约束上使用相同的计算效率算法,其使用场景优化中的结果对GNN的稳定性提供PAC风格的保证。我们还强调了这种设置和GNN稳定性之间的重要联系,以图形扰动,并提供实验结果,证明了我们的方法的有效性和广泛性。

英文摘要:

Graph neural networks (GNNs) have recently been demonstrated to perform well on a variety of network-based tasks such as decentralized control and resource allocation, and provide computationally efficient methods for these tasks which have traditionally been challenging in that regard. However, like many neural-network based systems, GNNs are susceptible to shifts and perturbations on their inputs, which can include both node attributes and graph structure. In order to make them more useful for real-world applications, it is important to ensure their robustness post-deployment. Motivated by controlling the Lipschitz constant of GNN filters with respect to the node attributes, we propose to constrain the frequency response of the GNN's filter banks. We extend this formulation to the dynamic graph setting using a continuous frequency response constraint, and solve a relaxed variant of the problem via the scenario approach. This allows for the use of the same computationally efficient algorithm on sampled constraints, which provides PAC-style guarantees on the stability of the GNN using results in scenario optimization. We also highlight an important connection between this setup and GNN stability to graph perturbations, and provide experimental results which demonstrate the efficacy and broadness of our approach.

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。

↑