RoGAT: a robust GNN combined revised GAT with adjusted graphs

09/28/2020
by   Xianchen Zhou, et al.
0

Graph Neural Networks(GNNs) are useful deep learning models to deal with the non-Euclid data. However, recent works show that GNNs are vulnerable to adversarial attacks. Small perturbations can lead to poor performance in many GNNs, such as Graph attention networks(GATs). Therefore, enhancing the robustness of GNNs is a critical problem. Robust GAT(RoGAT) is proposed to improve the robustness of GNNs in this paper, . Note that the original GAT uses the attention mechanism for different edges but is still sensitive to the perturbation, RoGAT adjusts the edges' weight to adjust the attention scores progressively. Firstly, RoGAT tunes the edges weight based on the assumption that the adjacent nodes should have similar nodes. Secondly, RoGAT further tunes the features to eliminate feature's noises since even for the clean graph, there exists some unreasonable data. Then, we trained the adjusted GAT model to defense the adversarial attacks. Different experiments against targeted and untargeted attacks demonstrate that RoGAT outperforms significantly than most the state-of-the-art defense methods. The implementation of RoGAT based on the DeepRobust repository for adversarial attacks.

READ FULL TEXT
06/15/2020

GNNGuard: Defending Graph Neural Networks against Adversarial Attacks

Deep learning methods for graphs achieve remarkable performance on many ...
07/19/2020

Adversarial Immunization for Improving Certifiable Robustness on Graphs

Despite achieving strong performance in the semi-supervised node classif...
09/22/2020

Uncertainty-aware Attention Graph Neural Network for Defending Adversarial Attacks

With the increasing popularity of graph-based learning, graph neural net...
10/28/2021

CAP: Co-Adversarial Perturbation on Weights and Features for Improving Generalization of Graph Neural Networks

Despite the recent advances of graph neural networks (GNNs) in modeling ...
06/16/2020

DefenseVGAE: Defending against Adversarial Attacks on Graph Data via a Variational Graph Autoencoder

Graph neural networks (GNNs) achieve remarkable performance for tasks on...
03/23/2021

Spatio-Temporal Sparsification for General Robust Graph Convolution Networks

Graph Neural Networks (GNNs) have attracted increasing attention due to ...
10/26/2021

Robustness of Graph Neural Networks at Scale

Graph Neural Networks (GNNs) are increasingly important given their popu...