Share Email Print
cover

Proceedings Paper

Estimation of time-series on graphs using Bayesian graph convolutional neural networks
Author(s): Fatemeh Teimury; Soumyasundar Pal; Arezou Amini; Mark Coates
Format Member Price Non-Member Price
PDF $17.00 $21.00

Paper Abstract

There has recently been an explosion of interest in graph neural networks, which extend the application of neural networks to data recorded on graphs. Most of the work has focused on static tasks, where a feature vector is available at each node in a graph, often with an associated label, and the goal is to perform node classification or regression, graph classification, or link prediction. Some work has recently emerged addressing the processing of sequences of data (time-series) on graphs using methods based on neural networks; most strategies involve combining Long Short-Term Memory units (LSTMs) or Gated Recurrent Units (GRUs) with graph convolution. However most of these methods process the observed graph as the ground truth, thereby failing to account for the uncertainty associated with graph structure in the learning task. As a remedy to this issue, in the recently proposed Bayesian graph convolutional neural networks, the provided graph is treated as a noisy observation of a true underlying graph or a realization of a random graph model. We can thus model uncertainty in the identification of relationships between nodes in the graph. We specify a joint posterior probability on the graph and the weights of the neural network and then perform inference through a combination of variational inference and Monte Carlo sampling. In this paper, we extend the Bayesian framework to address a regression task for time-series on graphs.

Paper Details

Date Published: 9 September 2019
PDF: 8 pages
Proc. SPIE 11138, Wavelets and Sparsity XVIII, 111380Y (9 September 2019);
Show Author Affiliations
Fatemeh Teimury, McGill Univ. (Canada)
Soumyasundar Pal, McGill Univ. (Canada)
Arezou Amini, McGill Univ. (Canada)
Mark Coates, McGill Univ. (Canada)


Published in SPIE Proceedings Vol. 11138:
Wavelets and Sparsity XVIII
Dimitri Van De Ville; Manos Papadakis; Yue M. Lu, Editor(s)

© SPIE. Terms of Use
Back to Top
PREMIUM CONTENT
Sign in to read the full article
Create a free SPIE account to get access to
premium articles and original research
Forgot your username?
close_icon_gray