Deep Knowledge Tracing Incorporating a Hypernetwork With Independent Student and Item Networks
Deep Knowledge Tracing Incorporating a Hypernetwork With Independent Student and Item Networks
复制标题
DOI：
10.1109/tlt.2023.3346671
复制
发表时间：
2024
影响因子：
3.7
通讯作者：
Emiko Tsutsumi;Yiming Guo;Ryo Kinoshita;Maomi Ueno
中科院分区：
文献类型：
--
作者：
Emiko Tsutsumi;Yiming Guo;Ryo Kinoshita;Maomi Ueno
知识追踪（KT）是一种追踪学生在一段时间内的知识状态的任务，人工智能研究人员对其进行了积极的评估。最近的报告描述了将项目反应理论（IRT）与深度学习方法相结合的deep -IRT提供了卓越的性能。它可以表达每个学生的能力和每个项目的难度，如IRT。然而，由于能力参数取决于每个项目，其可解释性与IRT相比不足。Deep-IRT隐含地假设具有相同技能的项目是等效的，当相同技能的项目难度差异很大时，这一假设就不成立了。对于相同的技能，不相等的项目会阻碍对学生能力评估的解释。为了克服这些困难，本研究提出了一种新颖的Deep-IRT，它使用两个独立的网络来模拟学生对一个项目的反应：1)学生网络和2)项目网络。提出的Deep-IRT方法独立学习学生参数和项目参数，避免影响预测精度。此外，我们为所提出的Deep-IRT提出了一种新的超网络架构，以平衡存储学生知识状态的潜在变量中的当前和过去数据。6个基准数据集的实验结果表明，该方法的预测精度平均提高了2.0%左右。此外，模拟数据集的实验表明，在$p< 0.5$显著性水平上，所提出的方法与真实参数的相关性比先前的Deep-IRT方法更强。
Knowledge tracing (KT), the task of tracking the knowledge state of a student over time, has been assessed actively by artificial intelligence researchers. Recent reports have described that Deep-IRT, which combines item response theory (IRT) with a deep learning method, provides superior performance. It can express the abilities of each student and the difficulty of each item such as IRT. Nevertheless, its interpretability is inadequate compared to that of IRT because the ability parameter depends on each item. Deep-IRT implicitly assumes that items with the same skills are equivalent, which does not hold when item difficulties for the same skills differ greatly. For identical skills, items that are not equivalent hinder the interpretation of a student's ability estimate. To overcome those difficulties, this study proposes a novel Deep-IRT that models a student response to an item using two independent networks: 1) a student network and 2) an item network. The proposed Deep-IRT method learns student parameters and item parameters independently to avoid impairing the predictive accuracy. Moreover, we propose a novel hypernetwork architecture for the proposed Deep-IRT to balance both the current and the past data in the latent variable storing student's knowledge states. Results of experiments with six benchmark datasets demonstrate that the proposed method improves the prediction accuracy by about 2.0%, on average. In addition, experiments for the simulation dataset demonstrated that the proposed method provides a stronger correlation with true parameters than the earlier Deep-IRT method does at the $p< 0.5$ significance level.