Nonlinear State-Space Generalizations of Graph Convolutional Neural Networks

by   Luana Ruiz, et al.

Graph convolutional neural networks (GCNNs) learn compositional representations from network data by nesting linear graph convolutions into nonlinearities. In this work, we approach GCNNs from a state-space perspective revealing that the graph convolutional module is a minimalistic linear state-space model, in which the state update matrix is the graph shift operator. We show this state update may be problematic because it is nonparametric, and depending on the graph spectrum it may explode or vanish. Therefore, the GCNN has to trade its degrees of freedom between extracting features from data and handling these instabilities. To improve such trade-off, we propose a novel family of nodal aggregation rules that aggregates node features within a layer in a nonlinear state-space parametric fashion and allowing for a better trade-off. We develop two architectures within this family inspired by the recursive ideas with and without nodal gating mechanisms. The proposed solutions generalize the GCNN and provide an additional handle to control the state update and learn from the data. Numerical results on source localization and authorship attribution show the superiority of the nonlinear state-space generalization models over the baseline GCNN.



There are no comments yet.


page 1

page 2

page 3

page 4


State Space System Modeling of a Quad Copter UAV

In this paper, a linear mathematical model for a quad copter unmanned ae...

State Space System Modelling of a Quad Copter UAV

In this paper, a linear mathematical model for a quad copter unmanned ae...

Graph-Time Convolutional Neural Networks

Spatiotemporal data can be represented as a process over a graph, which ...

Stability of Graph Convolutional Neural Networks to Stochastic Perturbations

Graph convolutional neural networks (GCNNs) are nonlinear processing too...

A Robust Alternative for Graph Convolutional Neural Networks via Graph Neighborhood Filters

Graph convolutional neural networks (GCNNs) are popular deep learning ar...

Learning Compositional Koopman Operators for Model-Based Control

Finding an embedding space for a linear approximation of a nonlinear dyn...

An Axiomatic Approach to Robustness in Search Problems with Multiple Scenarios

This paper is devoted to the search of robust solutions in state space g...
This week in AI

Get the week's most popular data science and artificial intelligence research sent straight to your inbox every Saturday.