GIKT: A Graph-based Interaction Model for Knowledge Tracing
GIKT: A Graph-based Interaction Model for Knowledge Tracing
复制标题
DOI：
10.1007/978-3-030-67658-2_18
复制
发表时间：
2020-09
期刊：
影响因子：
--
通讯作者：
Yang Yang-Yang;Jian Shen;Yanru Qu;Yunfei Liu;Kerong Wang;Yaoming Zhu;Weinan Zhang;Yong Yu
中科院分区：
文献类型：
--
作者：
Yang Yang-Yang;Jian Shen;Yanru Qu;Yunfei Liu;Kerong Wang;Yaoming Zhu;Weinan Zhang;Yong Yu
随着在线教育的快速发展，知识追踪（KT）已成为追踪学生的知识状况并预测他们在新问题上的表现的基本问题。在线教育系统中的问题通常很多，并且总是与很少的技能相关。然而，先前的文献未能将问题信息与高阶问题技能相关性一起涉及，这主要受到数据稀疏和多技能问题的限制。从模型的角度来看，以前的模型很难捕捉学生练习历史的长期依赖性，并且无法以一致的方式对学生问题和学生技能之间的相互作用进行建模。在本文中，我们提出了一种基于图的知识追踪交互模型（GIKT）来解决上述问题。更具体地说，GIKT 利用图卷积网络（GCN）通过嵌入传播充分整合问题技能相关性。此外，考虑到相关问题通常分散在整个练习历史中，而问题和技能只是知识的不同实例，GIKT将学生对问题的掌握程度概括为学生当前状态、学生历史状态、目标问题和相关技能之间的相互作用。对三个数据集的实验表明，GIKT 实现了新的最先进性能，绝对 AUC 提高了 2%–6%。
With the rapid development in online education,knowledge tracing(KT) has become a fundamental problem which traces students’ knowledge status and predicts their performance on new questions. Questions are often numerous in online education systems, and are always associated with much fewer skills. However, the previous literature fails to involve question information together with high-order question-skill correlations, which is mostly limited by data sparsity and multi-skill problems. From the model perspective, previous models can hardly capture the long-term dependency of student exercise history, and cannot model the interactions between student-questions, and student-skills in a consistent way. In this paper, we propose a Graph-based Interaction model for Knowledge Tracing (GIKT) to tackle the above problems. More specifically, GIKT utilizes graph convolutional network (GCN) to substantially incorporate question-skill correlations via embedding propagation. Besides, considering that relevant questions are usually scattered throughout the exercise history, and that question and skill are just different instantiations of knowledge, GIKT generalizes the degree of students’ master of the question to the interactions between the student’s current state, the student’s history states, the target question, and related skills. Experiments on three datasets demonstrate that GIKT achieves the new state-of-the-art performance, with 2%–6% absolute AUC improvement.