【摘要】 知识追踪旨在评估学习者的学习状态，并根据先前的答题情况预测他们未来的答题表现.然而现有的知识追踪模型大多仅关注问题或技能间的关联，忽略了学生与问题间的结构关系.为此我们提出了基于学生-问题关联的异构图知识追踪模型（Student-Problem association based heterogeneous graph Knowledge Tracing model,SPKT）.该模型在知识追踪中融合了学生的学习能力和问题的重要性，并使用图注意力网络学习学生问题间的关联，获得学生、问题的嵌入表示并进行知识状态的预测.通过在真实公开数据集上的性能对比和模型消融实验，并可视化SPKT模型的知识追踪效果，证明了SPKT在预测性能上优于现有的知识追踪模型.更多还原

【Abstract】 Knowledge tracing aims to assess learners’ learning status and predict their future performance based on previous answers. However, most of the existing knowledge tracing models only focus on the relationship between problems or skills, and ignore the structural relationship between students and problems. Therefore, we propose a student-problem association based heterogeneous graph knowledge tracing model(SPKT). The model integrates the learning ability of students and the importance of problems in knowledge tracing, and uses graph attention network to learn the interaction between students’ problems, so as to obtain the embedded representation of students and problems, meanwhile predicting the learners’ status. It is proved that SPKT is superior to the existing knowledge tracking model in terms of prediction performance through a large number of experiments and data visualization.更多还原