Learning flexible representations of stochastic processes on graphs

Abstract

Graph convolutional networks adapt the architecture of convolutional neural networks to learn rich representations of data supported on arbitrary graphs by replacing the convolution operations of convolutional neural networks with graph-dependent linear operations. However, these graph-dependent linear operations are developed for scalar functions supported on undirected graphs. We propose a class of linear operations for stochastic (time-varying) processes on directed (or undirected) graphs to be used in graph convolutional networks. We propose a parameterization of such linear operations using functional calculus to achieve arbitrarily low learning complexity. The proposed approach is shown to model richer behaviors and display greater flexibility in learning representations than product graph methods.

References in corpus (6)

• The Emerging Field of Signal Processing on Graphs: Extending High-Dimensional Data Analysis to Networks and Other Irregular Domains
• Geometric deep learning: going beyond Euclidean data
• Convolutional Neural Networks on Graphs with Fast Localized Spectral Filtering
• Discrete Signal Processing on Graphs
• Understanding Deep Convolutional Networks
• Representation Learning on Graphs: Methods and Applications