English

Robust Mid-Pass Filtering Graph Convolutional Networks

Machine Learning 2023-02-17 v1 Cryptography and Security

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.

Keywords

Cite

@article{arxiv.2302.08048,
  title  = {Robust Mid-Pass Filtering Graph Convolutional Networks},
  author = {Jincheng Huang and Lun Du and Xu Chen and Qiang Fu and Shi Han and Dongmei Zhang},
  journal= {arXiv preprint arXiv:2302.08048},
  year   = {2023}
}

Comments

Accepted by WWW'23