Cognition-Mode Aware Variational Representation Learning Framework for Knowledge Tracing

TL;DR

This paper introduces CMVF, a probabilistic framework that enhances knowledge tracing by modeling student uncertainty and cognition modes, leading to more robust representations especially for students with limited data.

Contribution

The paper proposes a novel variational framework with cognition-mode aware priors to improve student representation learning in knowledge tracing tasks.

Findings

CMVF improves robustness of student representations.

It enhances existing KT methods across multiple datasets.

The approach effectively handles data sparsity issues.

Abstract

The Knowledge Tracing (KT) task plays a crucial role in personalized learning, and its purpose is to predict student responses based on their historical practice behavior sequence. However, the KT task suffers from data sparsity, which makes it challenging to learn robust representations for students with few practice records and increases the risk of model overfitting. Therefore, in this paper, we propose a Cognition-Mode Aware Variational Representation Learning Framework (CMVF) that can be directly applied to existing KT methods. Our framework uses a probabilistic model to generate a distribution for each student, accounting for uncertainty in those with limited practice records, and estimate the student's distribution via variational inference (VI). In addition, we also introduce a cognition-mode aware multinomial distribution as prior knowledge that constrains the posterior student distributions learning, so as to ensure that students with similar cognition modes have similar distributions, avoiding overwhelming personalization for students with few practice records. At last, extensive experimental results confirm that CMVF can effectively aid existing KT methods in learning more robust student representations. Our code is available at https://github.com/zmy-9/CMVF.