TR2021-044

Spatio-Temporal Graph Scattering Transform


    •  Pan, C., Chen, S., Ortega, A., "Spatio-Temporal Graph Scattering Transform", International Conference on Learning Representations (ICLR), May 2021.
      BibTeX TR2021-044 PDF
      • @inproceedings{Pan2021may,
      • author = {Pan, Chao and Chen, Siheng and Ortega, Antonio},
      • title = {Spatio-Temporal Graph Scattering Transform},
      • booktitle = {International Conference on Learning Representations (ICLR)},
      • year = 2021,
      • month = may,
      • url = {https://www.merl.com/publications/TR2021-044}
      • }
  • Research Areas:

    Artificial Intelligence, Signal Processing

Abstract:

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 spatiotemporal 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.