Generalization Guarantee of Training Graph Convolutional Networks with Graph Topology Sampling

by   Hongkang Li, et al.

Graph convolutional networks (GCNs) have recently achieved great empirical success in learning graph-structured data. To address its scalability issue due to the recursive embedding of neighboring features, graph topology sampling has been proposed to reduce the memory and computational cost of training GCNs, and it has achieved comparable test performance to those without topology sampling in many empirical studies. To the best of our knowledge, this paper provides the first theoretical justification of graph topology sampling in training (up to) three-layer GCNs for semi-supervised node classification. We formally characterize some sufficient conditions on graph topology sampling such that GCN training leads to a diminishing generalization error. Moreover, our method tackles the nonconvex interaction of weights across layers, which is under-explored in the existing theoretical analyses of GCNs. This paper characterizes the impact of graph structures and topology sampling on the generalization performance and sample complexity explicitly, and the theoretical findings are also justified through numerical experiments.


page 1

page 2

page 3

page 4


FastGCN: Fast Learning with Graph Convolutional Networks via Importance Sampling

The graph convolutional networks (GCN) recently proposed by Kipf and Wel...

Progressive Graph Convolutional Networks for Semi-Supervised Node Classification

Graph convolutional networks have been successful in addressing graph-ba...

Distributed Graph Convolutional Networks

The aim of this work is to develop a fully-distributed algorithmic frame...

Topology and Prediction Focused Research on Graph Convolutional Neural Networks

Important advances have been made using convolutional neural network (CN...

On the Importance of Sampling in Learning Graph Convolutional Networks

Graph Convolutional Networks (GCNs) have achieved impressive empirical a...

A Graph Data Augmentation Strategy with Entropy Preserving

The Graph Convolutional Networks (GCNs) proposed by Kipf and Welling are...

Stochastic Training of Graph Convolutional Networks

Graph convolutional networks (GCNs) are powerful deep neural networks fo...

Please sign up or login with your details

Forgot password? Click here to reset