I-GCN: Robust Graph Convolutional Network via Influence Mechanism

12/11/2020
by   Haoxi Zhan, et al.
0

Deep learning models for graphs, especially Graph Convolutional Networks (GCNs), have achieved remarkable performance in the task of semi-supervised node classification. However, recent studies show that GCNs suffer from adversarial perturbations. Such vulnerability to adversarial attacks significantly decreases the stability of GCNs when being applied to security-critical applications. Defense methods such as preprocessing, attention mechanism and adversarial training have been discussed by various studies. While being able to achieve desirable performance when the perturbation rates are low, such methods are still vulnerable to high perturbation rates. Meanwhile, some defending algorithms perform poorly when the node features are not visible. Therefore, in this paper, we propose a novel mechanism called influence mechanism, which is able to enhance the robustness of the GCNs significantly. The influence mechanism divides the effect of each node into two parts: introverted influence which tries to maintain its own features and extroverted influence which exerts influences on other nodes. Utilizing the influence mechanism, we propose the Influence GCN (I-GCN) model. Extensive experiments show that our proposed model is able to achieve higher accuracy rates than state-of-the-art methods when defending against non-targeted attacks.

READ FULL TEXT

page 1

page 2

page 3

page 4

page 5

page 6

page 7

research
11/11/2019

GraphDefense: Towards Robust Graph Convolutional Networks

In this paper, we study the robustness of graph convolutional networks (...
research
02/16/2023

Robust Mid-Pass Filtering Graph Convolutional Networks

Graph convolutional networks (GCNs) are currently the most promising par...
research
09/12/2020

Certified Robustness of Graph Classification against Topology Attack with Randomized Smoothing

Graph classification has practical applications in diverse fields. Recen...
research
03/05/2019

The Vulnerabilities of Graph Convolutional Networks: Stronger Attacks and Defensive Techniques

Graph deep learning models, such as graph convolutional networks (GCN) a...
research
02/23/2022

Classification of Computer Aided Engineering (CAE) Parts Using Graph Convolutional Networks

CAE engineers work with hundreds of parts spread across multiple body mo...
research
10/21/2019

Edge Dithering for Robust Adaptive Graph Convolutional Networks

Graph convolutional networks (GCNs) are vulnerable to perturbations of t...
research
02/19/2020

Indirect Adversarial Attacks via Poisoning Neighbors for Graph Convolutional Networks

Graph convolutional neural networks, which learn aggregations over neigh...

Please sign up or login with your details

Forgot password? Click here to reset