Node Feature Kernels Increase Graph Convolutional Network Robustness

09/04/2021
by   Mohamed El Amine Seddik, et al.
0

The robustness of the much-used Graph Convolutional Networks (GCNs) to perturbations of their input is becoming a topic of increasing importance. In this paper, the random GCN is introduced for which a random matrix theory analysis is possible. This analysis suggests that if the graph is sufficiently perturbed, or in the extreme case random, then the GCN fails to benefit from the node features. It is furthermore observed that enhancing the message passing step in GCNs by adding the node feature kernel to the adjacency matrix of the graph structure solves this problem. An empirical study of a GCN utilised for node classification on six real datasets further confirms the theoretical findings and demonstrates that perturbations of the graph structure can result in GCNs performing significantly worse than Multi-Layer Perceptrons run on the node features alone. In practice, adding a node feature kernel to the message passing of perturbed graphs results in a significant improvement of the GCN's performance, thereby rendering it more robust to graph perturbations. Our code is publicly available at:https://github.com/ChangminWu/RobustGCN.

READ FULL TEXT

page 1

page 2

page 3

page 4

research
11/19/2020

Node Similarity Preserving Graph Convolutional Networks

Graph Neural Networks (GNNs) have achieved tremendous success in various...
research
05/03/2021

Schema-Aware Deep Graph Convolutional Networks for Heterogeneous Graphs

Graph convolutional network (GCN) based approaches have achieved signifi...
research
06/23/2020

Data Augmentation View on Graph Convolutional Network and the Proposal of Monte Carlo Graph Learning

Today, there are two major understandings for graph convolutional networ...
research
10/21/2019

Edge Dithering for Robust Adaptive Graph Convolutional Networks

Graph convolutional networks (GCNs) are vulnerable to perturbations of t...
research
08/23/2018

Learning Human-Object Interactions by Graph Parsing Neural Networks

This paper addresses the task of detecting and recognizing human-object ...
research
03/04/2022

R-GCN: The R Could Stand for Random

The inception of Relational Graph Convolutional Networks (R-GCNs) marked...
research
05/06/2020

Anonymized GCN: A Novel Robust Graph Embedding Method via Hiding Node Position in Noise

Graph convolution network (GCN) have achieved state-of-the-art performan...

Please sign up or login with your details

Forgot password? Click here to reset