A Pre-trained Knowledge Tracing Model with Limited Data

Online education systems have gained increasing popularity due to their capability to fully preserve users' learning data. This advantage enables researchers to assess learners' mastery through their learning trajectories, thereby facilitating personalized education and support. Knowledge tracing, an effective educational aid, simulates students' implicit knowledge states and predicts their mastery over knowledge based on their historical answer records. However, for newly developed online learning platforms, the lack of sufficient historical answer data may impede accurate prediction of students' knowledge states, rendering existing knowledge tracing models less effective. This paper introduces the first pre-trained knowledge tracing model that leverages a substantial amount of existing data for pre-training and a smaller dataset for fine-tuning. Validated across several publicly available knowledge tracing datasets, our method demonstrates significant improvement in tracing performance on small datasets, with a maximum AUC increase of 5.07%. Beyond incorporating small datasets, our approach of pre-training the entire dataset has shown an enhanced AUC compared to the baseline, marking a novel direction in knowledge tracing research. Furthermore, the paper analyzed the outcomes of pre-training experiments with varying numbers of interactions as fine-tuning datasets, providing valuable insights for Intelligent Tutoring Systems (ITS).