Deep Trustworthy Knowledge Tracing

Abstract

Knowledge tracing (KT), a key component of an intelligent tutoring system, is a machine learning technique that estimates the mastery level of a student based on his/her past performance. The objective of KT is to predict a student's response to the next question. Compared with traditional KT models, deep learning-based KT (DLKT) models show better predictive performance because of the representation power of deep neural networks. Various methods have been proposed to improve the performance of DLKT, but few studies have been conducted on the reliability of DLKT. In this work, we claim that the existing DLKTs are not reliable in real education environments. To substantiate the claim, we show limitations of DLKT from various perspectives such as knowledge state update failure, catastrophic forgetting, and non-interpretability. We then propose a novel regularization to address these problems. The proposed method allows us to achieve trustworthy DLKT. In addition, the proposed model which is trained on scenarios with forgetting can also be easily extended to scenarios without forgetting.

References in corpus (12)

• A Critical Review of Recurrent Neural Networks for Sequence Learning
• Deep Knowledge Tracing
• One-shot Learning with Memory-Augmented Neural Networks
• How deep is knowledge tracing?
• Deep Reinforcement Learning for List-wise Recommendations
• Deep-IRT: Make Deep Learning Based Knowledge Tracing Explainable Using Item Response Theory
• Back to the Basics: Bayesian extensions of IRT outperform neural networks for proficiency estimation
• Reinforcement Learning based Recommender System using Biclustering Technique
• Latent Skill Embedding for Personalized Lesson Sequence Recommendation
• Energy-Based Sequence GANs for Recommendation and Their Connection to Imitation Learning
• Extended Abstract: Mimicry Resilient Program Behavior Modeling with LSTM based Branch Models
• DNA Steganalysis Using Deep Recurrent Neural Networks