arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2110.02880cs.LG
收藏

时空图神经网络

Space-Time Graph Neural Networks

University of Pennsylvania(宾夕法尼亚大学)

Samar Hadou, Charilaos I. Kanatsoulis, Alejandro Ribeiro

摘要:

我们介绍了时空图神经网络(ST-GNN),一种新的GNN架构,量身定制,以共同处理时变网络数据的底层时空拓扑结构。我们提出的架构的基石是时间和图形卷积滤波器的组成,其次是逐点非线性激活函数。我们介绍了一个通用的定义卷积运算符,模仿其底层支持信号的扩散过程。在这个定义之上,我们提出了时空图卷积,它是建立在时间和图形移位运算符的组合上的。我们证明了具有多元积分Lipschitz滤波器的ST-GNNs对底层图中的小扰动以及时间扭曲引起的时域中的小扰动是稳定的。我们的分析表明,网络拓扑和系统时间演化的微小变化不会显著影响ST-GNN的性能。分散控制系统的数值实验表明,所提出的ST-GNNs的有效性和稳定性。

英文摘要:

We introduce space-time graph neural network (ST-GNN), a novel GNN architecture, tailored to jointly process the underlying space-time topology of time-varying network data. The cornerstone of our proposed architecture is the composition of time and graph convolutional filters followed by pointwise nonlinear activation functions. We introduce a generic definition of convolution operators that mimic the diffusion process of signals over its underlying support. On top of this definition, we propose space-time graph convolutions that are built upon a composition of time and graph shift operators. We prove that ST-GNNs with multivariate integral Lipschitz filters are stable to small perturbations in the underlying graphs as well as small perturbations in the time domain caused by time warping. Our analysis shows that small variations in the network topology and time evolution of a system does not significantly affect the performance of ST-GNNs. Numerical experiments with decentralized control systems showcase the effectiveness and stability of the proposed ST-GNNs.

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。

↑