Graph Structure Learning for Robust Graph Neural Networks

Abstract

Graph Neural Networks (GNNs) are powerful tools in representation learning for graphs. However, recent studies show that GNNs are vulnerable to carefully-crafted perturbations, called adversarial attacks. Adversarial attacks can easily fool GNNs in making predictions for downstream tasks. The vulnerability to adversarial attacks has raised increasing concerns for applying GNNs in safety-critical applications. Therefore, developing robust algorithms to defend adversarial attacks is of great significance. A natural idea to defend adversarial attacks is to clean the perturbed graph. It is evident that real-world graphs share some intrinsic properties. For example, many real-world graphs are low-rank and sparse, and the features of two adjacent nodes tend to be similar. In fact, we find that adversarial attacks are likely to violate these graph properties. Therefore, in this paper, we explore these properties to defend adversarial attacks on graphs. In particular, we propose a general framework Pro-GNN, which can jointly learn a structural graph and a robust graph neural network model from the perturbed graph guided by these properties. Extensive experiments on real-world graphs demonstrate that the proposed framework achieves significantly better performance compared with the state-of-the-art defense methods, even when the graph is heavily perturbed. We release the implementation of Pro-GNN to our DeepRobust repository for adversarial attacks and defenses (footnote: https://github.com/DSE-MSU/DeepRobust). The specific experimental settings to reproduce our results can be found in https://github.com/ChandlerBang/Pro-GNN.

Accepted by KDD 2020

References in corpus (17)

• Community detection in graphs
• Semi-Supervised Classification with Graph Convolutional Networks
• Inductive Representation Learning on Large Graphs
• Spectral Networks and Locally Connected Networks on Graphs
• Graph Neural Networks: A Review of Methods and Applications
• Simplifying Graph Convolutional Networks
• Adversarial Attacks on Neural Networks for Graph Data
• Variational Graph Auto-Encoders
• Gated Graph Sequence Neural Networks
• Adversarial Attacks on Graph Neural Networks via Meta Learning
• Transferring Robustness for Graph Neural Network Against Poisoning Attacks
• Adversarial Attacks on Node Embeddings via Graph Poisoning
• Adversarial Attack on Graph Structured Data
• Adversarial Examples on Graph Data: Deep Insights into Attack and Defense
• DeepRobust: A PyTorch Library for Adversarial Attacks and Defenses
• Attacking Graph Convolutional Networks via Rewiring
• A Unified Framework for Data Poisoning Attack to Graph-based Semi-supervised Learning

Cited by in corpus (6)

• Iterative Deep Graph Learning for Graph Neural Networks: Better and Robust Node Embeddings
• SLAPS: Self-Supervision Improves Structure Learning for Graph Neural Networks
• Deep Contrastive Graph Learning with Clustering-Oriented Guidance
• Regional Homogeneity: Towards Learning Transferable Universal Adversarial Perturbations Against Defenses
• USER: Unsupervised Structural Entropy-based Robust Graph Neural Network
• Graph Feature Gating Networks