Towards more accurate and interpretable model: Fusing multiple knowledge relations into deep knowledge tracing

Zhiyi Duan, Xiaoxiao Dong, Hengnian Gu, Xiong Wu, Zhen Li, Dongdai Zhou

Abstract: Highlights•A novel knowledge tracing model fusing multiple knowledge relations.•Learn the knowledge relations representations by Generative Adversarial Networks.•Gated Recurrent Unit is used to update the students’ knowledge states.•Design an attention-based method to fuse different knowledge relations.•Experiments on real-world datasets show the effectiveness and interpretability.