Cognitive Structure Generation: From Educational Priors to Policy Optimization

TL;DR

This paper presents a novel framework called Cognitive Structure Generation (CSG) that uses a diffusion probabilistic model and reinforcement learning to generate and optimize students' cognitive structures, improving student modeling and interpretability.

Contribution

The paper introduces CSG, a new approach combining diffusion models and reinforcement learning to generate and optimize cognitive structures from educational data.

Findings

Cognitive structures generated by CSG improve student modeling performance.

Cognitive structures enhance interpretability of student models.

Experimental results show significant performance gains on real-world datasets.

Abstract

Cognitive structure is a student's subjective organization of an objective knowledge system, reflected in the psychological construction of concepts and their relations. However, cognitive structure assessment remains a long-standing challenge in student modeling and psychometrics, persisting as a foundational yet largely unassessable concept in educational practice. This paper introduces a novel framework, Cognitive Structure Generation (CSG), in which we first pretrain a Cognitive Structure Diffusion Probabilistic Model (CSDPM) to generate students' cognitive structures from educational priors, and then further optimize its generative process as a policy with hierarchical reward signals via reinforcement learning to align with genuine cognitive development levels during students' learning processes. Experimental results on four popular real-world education datasets show that cognitive structures generated by CSG offer more comprehensive and effective representations for student modeling, substantially improving performance on KT and CD tasks while enhancing interpretability.