Although spatio-temporal graph neural networks have achieved great empirical success in handling multiple correlated time series, they may be impractical in some real-world scenarios due to a lack of sufficient high-quality training data. Furthermore, spatio-temporal graph neural networks lack theoretical interpretation. To address these issues, we put forth a novel mathematically designed framework to analyze spatio-temporal data. Our proposed spatio-temporal graph scattering transform (ST-GST) extends traditional scattering transforms to the spatio-temporal domain. It performs iterative applications of spatio-temporal graph wavelets and nonlinear activation functions, which can be viewed as a forward pass of spatio-temporal graph convolutional networks without training. Since all the filter coefficients in ST-GST are mathematically designed, it is promising for the real-world scenarios with limited training data, and also allows for a theoretical analysis, which shows that the proposed ST-GST is stable to small perturbations of input signals and structures. Finally, our experiments show that i) ST-GST outperforms spatio-temporal graph convolutional networks by an increase of 35% in accuracy for MSR Action3D dataset; ii) it is better and computationally more efficient to design the transform based on separable spatio-temporal graphs than the joint ones; and iii) the nonlinearity in ST-GST is critical to empirical performance.
翻译:尽管spatio-时钟图神经神经网络在处理多个相关时间序列方面取得了巨大的实证成功,但由于缺少足够的高质量培训数据,它们在某些现实世界情景中可能不切实际。 此外,spatio-时钟图神经网络缺乏理论解释。为了解决这些问题,我们提出了一个数学设计的新颖框架,用于分析时钟数据。我们提议的spatio-时钟图分布变异(ST-GST)将传统的散射变换扩展到时圈域。它执行的是空间-时序图波子和非线激活功能的迭代应用,这些可被视为不经过培训的时钟图神经网络的向前传递。由于ST-GST的所有过滤系数都是数学设计的,因此对培训数据有限的真实世界情景很有希望,也允许进行理论分析,表明拟议的ST-GSTT稳定到小的输入孔信号和结构。最后,我们的实验显示,ST-GST-STS-3的变现精确度将更精确性地显示,在Stacial-stal-stal-stal-stal-stable sportstable sportstable smartiumtal sign signal martiumstal-stal smarviii;我们用i) ST-stital ST-stital-stital-stal-stal-stal ASetal ASyal ASyal ASetal ASemmal ASyal AStututudal exal ex ex ex