Convolutional Neural Networks Architectures for Signals Supported on Graphs

05/01/2018
by   Fernando Gama, et al.
0

We describe two architectures that generalize convolutional neural networks (CNNs) for the processing of signals supported on graphs. The selection graph neural network (GNN) replaces linear time invariant filters with linear shift invariant graph filters to generate convolutional features and reinterprets pooling as a possibly nonlinear subsampling stage where nearby nodes pool their information in a set of preselected sample nodes. A key component of the architecture is to remember the position of sampled nodes to permit computation of convolutional features at deeper layers. The aggregation GNN diffuses the signal through the graph and stores the sequence of diffused components observed by a designated node. This procedure effectively aggregates all components into a stream of information having temporal structure to which the convolution and pooling stages of regular CNNs can be applied. A multinode version of aggregation GNNs is further introduced for operation in large scale graphs. An important property of selection and aggregation GNNs is that they reduce to conventional CNNs when particularized to time signals reinterpreted as graph signals in a circulant graph. Comparative numerical analyses are performed in a synthetic source localization application. Performance is evaluated for a text category classification problem using word proximity networks. Multinode aggregation GNNs are consistently the best performing GNN architecture.

READ FULL TEXT

page 5

page 8

page 9

research
08/04/2020

Graph Neural Networks: Architectures, Stability and Transferability

Graph Neural Networks (GNNs) are information processing architectures fo...
research
03/03/2020

Graphon Pooling in Graph Neural Networks

Graph neural networks (GNNs) have been used effectively in different app...
research
10/27/2017

Convolutional Neural Networks Via Node-Varying Graph Filters

Convolutional neural networks (CNNs) are being applied to an increasing ...
research
10/29/2018

Median activation functions for graph neural networks

Graph neural networks (GNNs) have been shown to replicate convolutional ...
research
03/06/2018

MIMO Graph Filters for Convolutional Neural Networks

Superior performance and ease of implementation have fostered the adopti...
research
10/22/2020

Rethinking pooling in graph neural networks

Graph pooling is a central component of a myriad of graph neural network...
research
03/29/2019

Invariance-Preserving Localized Activation Functions for Graph Neural Networks

Graph signals are signals with an irregular structure that can be descri...

Please sign up or login with your details

Forgot password? Click here to reset