EGNN: Constructing explainable graph neural networks via knowledge distillation

Yuan Li, Li Liu, Guoyin Wang, Yong Du, Penggang Chen

Abstract: Highlights•Simultaneously optimizing multiple objectives of distilling knowledge from the pretrained model and cross-entropy loss, the proposed EGNN model exhibits superior performance.•The transparent and interpretable neighbor selection strategy is designed. The neighbor nodes are selected in a sliced layer way, thus the neighbors’ contributions of user’s representation are traceable.•Four state-of-the-art GNN models are selected as teacher networks. Experimental results on three real-world datasets show the effectiveness of the proposed framework.