Semi-supervised learning on graphs is an important problem in the machine learning area. In recent years, state-of-the- art classification methods based on graph neural networks (GNNs) have shown their superiority over traditional ones such as label propagation. However, these neural models are mostly “black boxes” and their sophisticated architectures will lead to a complex prediction mechanism which could not make full use of valuable prior knowledge lying in the data, e.g., structurally correlated nodes tend to have the same class. In this paper, we propose a framework based on knowledge distillation to address the above issues. Our framework extracts the knowledge of an arbitrary learned GNN model (teacher model), and injects it into a well-designed student model. The student model is built with two simple prediction mechanisms, i.e., label propagation and feature transformation, which naturally preserves structure-based and feature-based prior knowledge, respectively. In specific, we design the student model as a trainable combination of parameterized label propagation and feature transformation modules. As a result, the learned student can benefit from both prior knowledge and the knowledge in GNN teachers for more effective predictions. Moreover, the learned student model has a more interpretable prediction process than GNNs. We conduct experiments on five public benchmark datasets and employ seven GNN models including GCN, GAT, APPNP, SAGE, SGC, GCNII and GLP as the teacher models. Experimental results show that the learned student model can outperform its corresponding teacher model by 1.4%-4.7% on average. The improvements are consistent and significant with better interpretability.

The Web Conference is announcing latest news and developments biweekly or on a monthly basis. We respect The General Data Protection Regulation 2016/679.