• Corpus ID: 249625818

How does Heterophily Impact Robustness of Graph Neural Networks? Theoretical Connections and Practical Implications

@inproceedings{Zhu2021HowDH,
  title={How does Heterophily Impact Robustness of Graph Neural Networks? Theoretical Connections and Practical Implications},
  author={Jiong Zhu and Junchen Jin and Donald Loveland and Michael T. Schaub and Danai Koutra},
  year={2021}
}
Webridge tworesearchdirectionsongraphneural networks (GNNs), by formalizing the relation between heterophily of node labels (i.e., connected nodes tend to have dissimilar labels) and the robustness of GNNs to adversarial attacks. Our theoretical and empirical analyses show that for homophilous graph data, impactful structural attacks always lead to reduced homophily, while for heterophilous graph data the change in the homophily level depends on the node degrees. These insights have practical… 

Figures and Tables from this paper