Robust Mid-Pass Filtering Graph Convolutional Networks

TL;DR

This paper introduces Mid-GCN, a robust graph convolutional network that uses mid-pass filtering to enhance resistance against adversarial attacks, verified through theoretical analysis and extensive experiments.

Contribution

We propose Mid-GCN, a novel GCN model leveraging mid-frequency signal filtering for robustness, avoiding additional objectives and training overhead.

Findings

Mid-GCN improves node classification accuracy under adversarial attacks.

Theoretical analysis confirms robustness of mid-pass filtering.

Extensive experiments on benchmark datasets validate effectiveness.

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.