Disentangling Heterogeneous Knowledge Concept Embedding for Cognitive Diagnosis on Untested Knowledge

TL;DR

This paper introduces DisKCD, a novel framework that disentangles tested and untested knowledge concepts to improve cognitive diagnosis, especially for untested concepts, by leveraging heterogeneous data sources and a relation graph network.

Contribution

DisKCD is the first framework to explicitly model untested knowledge concepts in cognitive diagnosis using a heterogeneous relation graph network.

Findings

DisKCD significantly improves diagnosis accuracy on untested knowledge concepts.

The model effectively leverages course grades, exercises, and resources for better embeddings.

Experimental results demonstrate superior performance over existing methods.

Abstract

Cognitive diagnosis is a fundamental and critical task in learning assessment, which aims to infer students' proficiency on knowledge concepts from their response logs. Current works assume each knowledge concept will certainly be tested and covered by multiple exercises. However, whether online or offline courses, it's hardly feasible to completely cover all knowledge concepts in several exercises. Restricted tests lead to undiscovered knowledge deficits, especially untested knowledge concepts(UKCs). In this paper, we propose a novel framework for Cognitive Diagnosis called Disentangling Heterogeneous Knowledge Cognitive Diagnosis(DisKCD) on untested knowledge. Specifically, we leverage course grades, exercise questions, and learning resources to learn the potential representations of students, exercises, and knowledge concepts. In particular, knowledge concepts are disentangled into tested and untested based on the limiting actual exercises. We construct a heterogeneous relation graph network via students, exercises, tested knowledge concepts(TKCs), and UKCs. Then, through a hierarchical heterogeneous message-passing mechanism, the fine-grained relations are incorporated into the embeddings of the entities. Finally, the embeddings will be applied to multiple existing cognitive diagnosis models to infer students' proficiency on UKCs. Experimental results on real-world datasets show that the proposed model can effectively improve the performance of the task of diagnosing students' proficiency on UKCs. Our code is available at https://github.com/Hubuers/DisKCD.