DyGKT: Dynamic Graph Learning for Knowledge Tracing

TL;DR

DyGKT introduces a novel dynamic graph learning approach for knowledge tracing that models evolving student-question relationships and time intervals, outperforming static models on multiple datasets.

Contribution

This work is the first to apply dynamic graph learning to knowledge tracing, capturing evolving relationships and temporal semantics for improved student performance prediction.

Findings

DyGKT outperforms existing static models on five real-world datasets.

The dual time encoder effectively captures long-term and short-term semantics.

Dynamic graph modeling enhances the understanding of evolving student-question interactions.

Abstract

Knowledge Tracing aims to assess student learning states by predicting their performance in answering questions. Different from the existing research which utilizes fixed-length learning sequence to obtain the student states and regards KT as a static problem, this work is motivated by three dynamical characteristics: 1) The scales of students answering records are constantly growing; 2) The semantics of time intervals between the records vary; 3) The relationships between students, questions and concepts are evolving. The three dynamical characteristics above contain the great potential to revolutionize the existing knowledge tracing methods. Along this line, we propose a Dynamic Graph-based Knowledge Tracing model, namely DyGKT. In particular, a continuous-time dynamic question-answering graph for knowledge tracing is constructed to deal with the infinitely growing answering behaviors, and it is worth mentioning that it is the first time dynamic graph learning technology is used in this field. Then, a dual time encoder is proposed to capture long-term and short-term semantics among the different time intervals. Finally, a multiset indicator is utilized to model the evolving relationships between students, questions, and concepts via the graph structural feature. Numerous experiments are conducted on five real-world datasets, and the results demonstrate the superiority of our model. All the used resources are publicly available at https://github.com/PengLinzhi/DyGKT.