RegKT: Interpretable and Robust Deep Knowledge Tracing With IRT-Regularizer

Researchers Samuel Girard, Juan D. Pinto, Jill-Jênn Vie, and Amel Bouzeghoub proposed RegKT, a regularization technique that uses an IRT (Item Response Theory) regularizer to improve the robustness and interpretability of deep-learning-based knowledge tracing models, according to a paper posted to arXiv as 2609.21791v1. The method targets two problems the authors identify in existing knowledge tracing models: reduced interpretability, which they say hinders adoption by practitioners in educational settings, and overfitting on the small datasets common in educational applications. The authors state the approach makes deep knowledge tracing more feasible for real-world educational use.

RegKT: Interpretable and Robust Deep Knowledge Tracing With IRT-Regularizer By Samuel Girard, Juan D. Pinto, Jill-J\^enn Vie, Amel BouzeghoubSource: arXiv cs.LG https://arxiv.org/list/cs.LG/recent arXiv:2609.21791v1 Announce Type: new Abstract: As deep learning https://www.machinebrief.com/glossary/deep-learning models continue to advance, knowledge tracing models have achieved higher accuracy. However, these gains come at the cost of reduced interpretability, which is crucial for practitioners in educational settings to adopt new methodologies. Additionally, deep learning models are prone to overfitting https://www.machinebrief.com/glossary/overfitting , particularly when dealing with the small datasets that are common in educational applications. In this paper, we propose a novel regularization https://www.machinebrief.com/glossary/regularization technique designed to enhance the robustness of deep-learning-based knowledge tracing models, while simultaneously improving their interpretability. Our method addresses both the interpretability and overfitting challenges, making it more feasible for real-world educational applications. Get AI news in your inbox Daily digest of what matters in AI. Key Terms Explained Deep Learning A subset of machine learning that uses neural networks with many layers hence 'deep' to learn complex patterns from large amounts of data. Overfitting When a model memorizes the training data so well that it performs poorly on new, unseen data. Regularization Techniques that prevent a model from overfitting by adding constraints during training.