Batch Virtual Adversarial Training for Graph Convolutional Networks
This addresses the robustness issue in GCNs for graph-structured data, though it is an incremental improvement over existing adversarial training methods.
The paper tackles the problem of graph convolutional networks (GCNs) lacking smoothness against local perturbations by proposing batch virtual adversarial training (BVAT), which achieves state-of-the-art results in semi-supervised node classification on citation and knowledge graph datasets.
We present batch virtual adversarial training (BVAT), a novel regularization method for graph convolutional networks (GCNs). BVAT addresses the shortcoming of GCNs that do not consider the smoothness of the model's output distribution against local perturbations around the input. We propose two algorithms, sample-based BVAT and optimization-based BVAT, which are suitable to promote the smoothness of the model for graph-structured data by either finding virtual adversarial perturbations for a subset of nodes far from each other or generating virtual adversarial perturbations for all nodes with an optimization process. Extensive experiments on three citation network datasets Cora, Citeseer and Pubmed and a knowledge graph dataset Nell validate the effectiveness of the proposed method, which establishes state-of-the-art results in the semi-supervised node classification tasks.