02/02/2021

Power up! Robust Graph Convolutional Network via Graph Powering

Ming Jin, Heng Chang, Wenwu Zhu, Somayeh Sojoudi

Keywords:

Abstract Paper Similar Papers

Abstract: 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.

The video of this talk cannot be embedded. You can watch it here:
https://slideslive.com/38949217
(Link will open in new window)
 0
 0
 0
 0
  Share    
This is an embedded video. Talk and the respective paper are published at AAAI 2021 virtual conference. If you are one of the authors of the paper and want to manage your upload, see the question "My papertalk has been externally embedded..." in the FAQ section.

Comments

Post Comment
no comments yet
code of conduct: tbd Characters remaining: 140

Similar Papers

 0
 0
 0
 0
 2:43 
 0
 0
 0
 0
 14:31 
 0
 0
 0
 0
 17:38 
 0
 0
 0
 1
 5:15 
 0
 0
 0
 0
 17:33 
 0
 0
 0
 0
 8:20 
 0
 0
 0
 0
 4:58 
 0
 0
 0
 0
 16:23 
 0
 0
 0
 0
 3:20 
 0
 0
 0
 0
 5:07 
 0
 0
 0
 0
 12:11 
 0
 0
 0
 0
 11:42 
 0
 0
 0
 0
 14:49 
 0
 0
 0
 0
 5:25 
 0
 0
 0
 0
 15:07 
 0
 0
 0
 0
 4:39 
 0
 0
 0
 0
 9:50 
 0
 0
 0
 0
 14:53 
 0
 0
 0
 0
 3:47 
 0
 0
 0
 0
 19:11 
 0
 0
 0
 0
 14:46 
 0
 0
 0
 0
 9:51 
 0
 0
 0
 0
 11:21 
 0
 0
 0
 0
 1:01 
 0
 0
 0
 0
 9:39 
 0
 0
 0
 0
 20:08 
 0
 0
 0
 0
 5:15 
 0
 0
 0
 0
 5:08 
 0
 0
 0
 0
 5:01 
 0
 0
 0
 0
 16:07 
 0
 0
 0
 0
 13:35 
 0
 0
 0
 0
 4:57 
 0
 0
 0
 0
 4:59 
 0
 0
 0
 0
 10:50 
 0
 0
 0
 0
 3:10 
 0
 0
 0
 0
 8:23 
 0
 0
 0
 0
 16:41 
 0
 0
 0
 0
 8:47 
 0
 0
 0
 0
 15:54 
 0
 0
 0
 0
 3:38