Online Adversarial Knowledge Distillation for Graph Neural Networks

Abstract

Knowledge distillation has recently become a popular technique to improve the model generalization ability on convolutional neural networks. However, its effect on graph neural networks is less than satisfactory since the graph topology and node attributes are likely to change in a dynamic way and in this case a static teacher model is insufficient in guiding student training. In this paper, we tackle this challenge by simultaneously training a group of graph neural networks in an online distillation fashion, where the group knowledge plays a role as a dynamic virtual teacher and the structure changes in graph neural networks are effectively captured. To improve the distillation performance, two types of knowledge are transferred among the students to enhance each other: local knowledge reflecting information in the graph topology and node attributes, and global knowledge reflecting the prediction over classes. We transfer the global knowledge with KL-divergence as the vanilla knowledge distillation does, while exploiting the complicated structure of the local knowledge with an efficient adversarial cyclic learning framework. Extensive experiments verified the effectiveness of our proposed online adversarial distillation approach.

Keywords: knowledge distillation, Graph Neural Networks, Dynamic Graph, Online Distillation