Topology Adaptive Graph Convolutional Networks

10/28/2017
by   Jian Du, et al.
0

Convolution acts as a local feature extractor in convolutional neural networks (CNNs). However, the convolution operation is not applicable when the input data is supported on an irregular graph such as with social networks, citation networks, or knowledge graphs. This paper proposes the topology adaptive graph convolutional network (TAGCN), a novel graph convolutional network that generalizes CNN architectures to graph-structured data and provides a systematic way to design a set of fixed-size learnable filters to perform convolutions on graphs. The topologies of these filters are adaptive to the topology of the graph when they scan the graph to perform convolution, replacing the square filter for the grid-structured data in traditional CNNs. The outputs are the weighted sum of these filters' outputs, extraction of both vertex features and strength of correlation between vertices. It can be used with both directed and undirected graphs. The proposed TAGCN not only inherits the properties of convolutions in CNN for grid-structured data, but it is also consistent with convolution in traditional signal processing. We apply TAGCN to semi-supervised learning problems for graph vertex classification; experiments on a number of data sets demonstrate that our method outperforms the existing graph convolutional neural networks and achieves state-of-the-art performance for each data set tested.

READ FULL TEXT

page 1

page 2

page 3

page 4

research
01/10/2018

Adaptive Graph Convolutional Neural Networks

Graph Convolutional Neural Networks (Graph CNNs) are generalizations of ...
research
08/23/2018

Topology and Prediction Focused Research on Graph Convolutional Neural Networks

Important advances have been made using convolutional neural network (CN...
research
03/02/2017

Robust Spatial Filtering with Graph Convolutional Neural Networks

Convolutional Neural Networks (CNNs) have recently led to incredible bre...
research
06/16/2017

Dynamic Filters in Graph Convolutional Networks

Convolutional neural networks (CNNs) have massively impacted visual reco...
research
08/12/2018

Large-Scale Learnable Graph Convolutional Networks

Convolutional neural networks (CNNs) have achieved great success on grid...
research
10/02/2021

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

Graph convolutional neural networks (GCNNs) are popular deep learning ar...
research
06/03/2018

Dual-Primal Graph Convolutional Networks

In recent years, there has been a surge of interest in developing deep l...

Please sign up or login with your details

Forgot password? Click here to reset