Few-shot Classification on Graphs with Structural Regularized GCNs

Shengzhong Zhang, Ziang Zhou, Zengfeng Huang, Zhongyu Wei

Abstract: We consider the fundamental problem of semi-supervised node classification in attributed graphs with a focus on \emph{few-shot} learning. Here, we propose Structural Regularized Graph Convolutional Networks (SRGCN), novel neural network architectures extending the well-known GCN structures by stacking transposed convolutional layers for reconstruction of input features. We add a reconstruction error term in the loss function as a regularizer. Unlike standard regularization such as $L_1$ or $L_2$, which controls the model complexity by including a penalty term depends solely on parameters, our regularization function is parameterized by a trainable neural network whose structure depends on the topology of the underlying graph. The new approach effectively addresses the shortcomings of previous graph convolution-based techniques for learning classifiers in the few-shot regime and significantly improves generalization performance over original GCNs when the number of labeled samples is insufficient. Experimental studies on three challenging benchmarks demonstrate that the proposed approach has matched state-of-the-art results and can improve classification accuracies by a notable margin when there are very few examples from each class.

Keywords: Graph Convolutional Networks, Few-shot, Classification