Fisher-Bures Adversary Graph Convolutional Networks

In a graph convolutional network, we assume that the graph G is generated w.r.t. some observation noise. During learning, we make small random perturbations Delta G of the graph and try to improve generalization. Based on quantum information geometry, Delta G can be characterized by the eigen-decomposition of the graph Laplacian matrix. We try to minimize the loss w.r.t. the perturbed G + Delta G while making Delta G to be effective in terms of the Fisher information of the neural network. Our proposed model can consistently improve graph convolutional networks on semi-supervised node classification tasks with reasonable computational overhead. We present three different geometries on the manifold of graphs: the intrinsic geometry measures the information theoretic dynamics of a graph; the extrinsic geometry characterizes how such dynamics can affect externally a graph neural network; the embedding geometry is for measuring node embeddings. These new analytical tools are useful in developing a good understanding of graph neural networks and fostering new techniques.