Power up! Robust Graph Convolutional Network via Graph Powering


  • Ming Jin Virginia Tech
  • Heng Chang Tsinghua University
  • Wenwu Zhu Tsinghua University
  • Somayeh Sojoudi University of California at Berkeley




Graph-based Machine Learning, Adversarial Learning & Robustness, Semi-Supervised Learning, Graph Mining, Social Network Analysis & Community


Graph convolutional networks (GCNs) are powerful tools for graph-structured data. However, they have been recently shown to be vulnerable to topological attacks. To enhance adversarial robustness, we go beyond spectral graph theory to robust graph theory. By challenging the classical graph Laplacian, we propose a new convolution operator that is provably robust in the spectral domain and is incorporated in the GCN architecture to improve expressivity and interpretability. By extending the original graph to a sequence of graphs, we also propose a robust training paradigm that encourages transferability across graphs that span a range of spatial and spectral characteristics. The proposed approaches are demonstrated in extensive experiments to simultaneously improve performance in both benign and adversarial situations.




How to Cite

Jin, M., Chang, H., Zhu, W., & Sojoudi, S. (2021). Power up! Robust Graph Convolutional Network via Graph Powering. Proceedings of the AAAI Conference on Artificial Intelligence, 35(9), 8004-8012. https://doi.org/10.1609/aaai.v35i9.16976



AAAI Technical Track on Machine Learning II