Robust Mid-Pass Filtering Graph Convolutional Networks

Abstract

Graph convolutional networks (GCNs) are currently the most promising paradigm for dealing with graph-structure data, while recent studies have also shown that GCNs are vulnerable to adversarial attacks. Thus developing GCN models that are robust to such attacks become a hot research topic. However, the structural purification learning-based or robustness constraints-based defense GCN methods are usually designed for specific data or attacks, and introduce additional objective that is not for classification. Extra training overhead is also required in their design. To address these challenges, we conduct in-depth explorations on mid-frequency signals on graphs and propose a simple yet effective Mid-pass filter GCN (Mid-GCN). Theoretical analyses guarantee the robustness of signals through the mid-pass filter, and we also shed light on the properties of different frequency signals under adversarial attacks. Extensive experiments on six benchmark graph data further verify the effectiveness of our designed Mid-GCN in node classification accuracy compared to state-of-the-art GCNs under various adversarial attack strategies.

arXiv commentAccepted by WWW'23

References in corpus (21)

• The Emerging Field of Signal Processing on Graphs: Extending High-Dimensional Data Analysis to Networks and Other Irregular Domains
• T-GCN: A Temporal Graph ConvolutionalNetwork for Traffic Prediction
• Spectral Networks and Locally Connected Networks on Graphs
• Molecular Graph Convolutions: Moving Beyond Fingerprints
• Simplifying Graph Convolutional Networks
• Adversarial Attacks on Neural Networks for Graph Data
• Predict then Propagate: Graph Neural Networks meet Personalized PageRank
• Adversarial Attacks on Graph Neural Networks via Meta Learning
• Revisiting Graph Neural Networks: All We Have is Low-Pass Filters
• Deep Gaussian Embedding of Graphs: Unsupervised Inductive Learning via Ranking
• GNNGuard: Defending Graph Neural Networks against Adversarial Attacks
• Certifiable Robustness and Robust Training for Graph Convolutional Networks
• DeepRobust: A PyTorch Library for Adversarial Attacks and Defenses
• Attacking Graph Convolutional Networks via Rewiring
• Scattering GCN: Overcoming Oversmoothness in Graph Convolutional Networks
• PaSca: a Graph Neural Architecture Search System under the Scalable Paradigm
• How Powerful are Spectral Graph Neural Networks
• BernNet: Learning Arbitrary Graph Spectral Filters via Bernstein Approximation
• How does Heterophily Impact the Robustness of Graph Neural Networks? Theoretical Connections and Practical Implications
• EvenNet: Ignoring Odd-Hop Neighbors Improves Robustness of Graph Neural Networks
• When Does A Spectral Graph Neural Network Fail in Node Classification?

Cited by in corpus (2)

• Can Large Language Models Improve the Adversarial Robustness of Graph Neural Networks?
• A Survey on Learning from Graphs with Heterophily: Recent Advances and Future Directions