Meta-path structured graph pre-training for improving knowledge tracing in intelligent tutoring

SGKT: Session graph-based knowledge tracing for student performance prediction

Knowledge tracing (KT) is a research topic that seeks to model the knowledge acquisition of students by analyzing their past performance in answering questions, based on which their performance in answering future questions is predicted. Each question involves a knowledge component (KC) such as the topics concerned or the skills required. However, existing models only consider whether a student answers a question correctly at the end, but not the process of how the student attempts to answer it. It is anticipated that the interaction process can at least partially reveal the thinking process of the student, and hopefully even the competence of acquiring or understanding each of the KCs. By analyzing fine-grained clickstream events recorded for each question, we can better understand the student’s ability and performance or even the learning process, just like a personal tutor observing how a student solves a problem. Based on real student interaction data including clickstream events collected from an online learning platform on which students solve mathematics problems, we conduct clustering analysis for each question to show that clickstreams can reflect students’ behavior such as the steps and order of answering a question, time allocation, and score acquiring ability. We then propose the first clickstream-based KT model, dubbed the Click-stream Knowledge Tracing (CKT) model, which augments a basic KT model by modeling the clickstream activities of students when answering questions. We apply different variants of CKT and compare them with the baseline KT model that does not use clickstream data. Despite the limited number of questions with clickstream data and its noisy nature, which may compromise the data quality, we show that incorporating clickstream data leads to performance improvement. This pilot study will likely open a new direction in KT research by analyzing the finer-grained interaction data of students on online learning platforms.

In educational data mining, knowledge tracing (KT) aims to model learning performance based on student knowledge mastery. Deep-learning-based KT models perform remarkably better than traditional KT and have attracted considerable attention. However, most of them lack interpretability, making it challenging to explain why the model performed well in the prediction. In this paper, we propose an interpretable deep KT model, referred to as fuzzy deep knowledge tracing (FDKT) via fuzzy reasoning. Specifically, we formalize continuous scores into several fuzzy scores using the fuzzification module. Then, we input the fuzzy scores into the fuzzy reasoning module (FRM). FRM is designed to deduce the current cognitive ability, based on which the future performance was predicted. FDKT greatly enhanced the intrinsic interpretability of deep-learning-based KT through the interpretation of the deduction of student cognition. Furthermore, it broadened the application of KT to continuous scores. Improved performance with regard to both the advantages of FDKT was demonstrated through comparisons with the state-of-the-art models.

Knowledge tracing (KT) is an essential task in online education systems. It aims to predict the future performance of students based on their historical learning interaction data. Despite significant advancements in attention-based KT models, they still face some limitations: inaccurate input representation and excessive student forgetting modeling. These limitations often lead to the attention noise problem: the model assigns non-negligible attention weight to some information that is cognitively irrelevant in nature, thereby generating interference signals. To address this problem, we propose a novel KT model, i.e., DenoiseKT. DenoiseKT effectively models the difficulty of the questions and utilizes graph neural network to capture the complex relationship between questions, thereby refining the representations of input features. Additionally, the denoised attention mechanism introduces a weight factor to reduce the model's attention weight distribution on irrelevant information. We extensively compare DenoiseKT with 22 state-of-the-art KT models on 4 widely-used public datasets. Experimental results show that DenoiseKT can effectively solve the attention noise problem and outperform other models. The source code of DenoiseKT is available at https://pykt.org.

Knowledge tracing aims to trace students’ evolving knowledge states by predicting their future performance on concept-related exercises. Recently, some graph-based models have been developed to incorporate the relationships between exercises to improve knowledge tracing, but only a single type of relationship information is generally explored. In this article, we present a novel Dual Graph Ensemble learning method for Knowledge Tracing (DGEKT), which establishes a dual graph structure of students’ learning interactions to capture the heterogeneous exercise–concept associations and interaction transitions by hypergraph modeling and directed graph modeling, respectively. To combine the dual graph models, we introduce the technique of online knowledge distillation. This choice arises from the observation that, while the knowledge tracing model is designed to predict students’ responses to the exercises related to different concepts, it is optimized merely with respect to the prediction accuracy on a single exercise at each step. With online knowledge distillation, the dual graph models are adaptively combined to form a stronger ensemble teacher model, which provides its predictions on all exercises as extra supervision for better modeling ability. In the experiments, we compare DGEKT against eight knowledge tracing baselines on three benchmark datasets, and the results demonstrate that DGEKT achieves state-of-the-art performance.

Knowledge Tracing (KT) refers to the problem of predicting learners’ future potential performance given their past learning history in e-learning systems. In order to better trace the learners’ knowledge, KT tasks have become increasingly complicated recently, and various factors related to learning (such as skill, exercise, hint, etc.) have been incorporated into the modeling of KS of the learner, which renders it inadequate for the traditional KT definition to formalize these tasks. Therefore, this paper first gives a more general formal definition of KT tasks, and then proposes an Extensible Deep Knowledge Tracing model for multiple learning factors based on this general definition, named EDKT. EDKT can integrate various different learning factors by extending or ablating factors in two plug-ins on the basis of minor modifications. To demonstrate the effectiveness of the proposed model, we conduct extensive experiments on three real-world benchmark datasets, and the results show that EDKT comprehensively outperforms the state-of-the-art KT models on predicting future learner responses.

Knowledge Tracing (KT) aims to model students' evolving knowledge states and predict their future performance. Traditional sequential models often struggle with long-range dependencies due to inefficient memory retention and high computational costs, limiting their effectiveness in capturing students' continuous learning trajectories. Meanwhile, graph-based KT models effectively represent knowledge concept relationships but are not designed for sequential modeling. To address these challenges, we propose DualFlowKT, a novel model that employs a dual-path architecture, integrating Graph Neural Networks (GNNs) for structured knowledge modeling and the Mamba state space model for efficient long-sequence learning. Specifically, the graph-based path extracts relational dependencies among knowledge concepts, while the sequential path leverages Mamba's selective state-space modeling to effectively capture long-range learning patterns with enhanced memory efficiency and reduced computational overhead. To further enhance input representations, we introduce a Feature Enhancement Module (FEM) that extracts critical learning features such as concept continuity, learning rate, and adaptive difficulty. Additionally, a gated fusion mechanism dynamically integrates knowledge structure representations from GNNs with sequential dependencies captured by Mamba, allowing the model to adaptively balance structural and temporal learning information. Extensive experiments on multiple KT benchmark datasets demonstrate that DualFlowKT outperforms existing methods, particularly in handling long-sequence interactions and complex knowledge structures. Furthermore, the model provides deeper insights into students' evolving knowledge states, supporting personalized education systems.

Model-agnostic counterfactual reasoning for identifying and mitigating answer bias in knowledge tracing

Quantum computing enhanced knowledge tracing: Personalized KT research for mitigating data sparsity

Knowledge tracing (KT) is a problem of modeling students’ knowledge states to predict their future performance by observing their historical learning interactions. The collection of educational data presents significant challenges, as students’ limited learning engagement restricts the generation of large-scale interaction data, while stringent privacy regulations further limit the availability of student learning sequences from online platforms. Hence, it is crucial to enhance the capabilities of deep learning based KT (DLKT) models by constructing large-scale datasets through the integration of student interaction data across multiple subjects and sources. The success of ChatGPT demonstrates that the decoder-only Transformer architecture is highly effective in capturing complex information from large-scale sequential data. Against this background, we propose a novel decoder-only Transformer architecture based model, named Unified DLKT ( UniKT ), to learn coherent and unified representations across a wide range of data sources. Specifically, we combine student learning sequences from six educational scenarios and utilize a multi-source encoding to learn unified representations of interactions from mixed data. UniKT is a stack of Transformer decoder layers for handling long-term dependencies among students’ historical interactions and future performance. We evaluate UniKT on six publicly available real-world educational datasets, and experimental results demonstrate that our method outperforms the majority of existing DLKT models in terms of AUC and accuracy. Furthermore, the empirical analysis shows the strong transferability and adaptability of UniKT in learning from multiple sources. To encourage reproducible research, we make our data and code publicly available at https://pykt.org/ .

Recent advancements in computer-assisted learning systems have caused an increase in the research of knowledge tracing, wherein student performance on coursework exercises is predicted over time. From the viewpoint of data structure, the coursework can be potentially structured as a graph. Incorporating this graph-structured nature into the knowledge tracing model as a relational inductive bias can improve its performance; however, previous methods, such as deep knowledge tracing, did not consider such a latent graph structure. Inspired by the recent successes of the graph neural network (GNN), we herein propose a GNN-based knowledge tracing method, i.e., graph-based knowledge tracing. Casting the knowledge structure as a graph enabled us to reformulate the knowledge tracing task as a time-series node-level classification problem in the GNN. As the knowledge graph structure is not explicitly provided in most cases, we propose various implementations of the graph structure. Empirical validations on two open datasets indicated that our method could potentially improve the prediction of student performance and demonstrated more interpretable predictions compared to those of the previous methods, without the requirement of any additional information.

Knowledge tracing (KT) aims to predict students' future performance based on their past learning activities. However, no one is perfect. Factors such as carelessness, fatigue, and stress often cause students to make mistakes on problems they have already mastered, leading to anomalies in their historical learning data. These anomalies disrupt inherent patterns in the data, misleading the KT model. Extracting cognitive patterns that accurately reflect students' knowledge mastery from such error-prone data remains a significant challenge. Against this background, this paper proposes a novel KT method named RoubstKT, inspired by educational measurement theory and frequency-based decomposition. A cognitive decoupling analyzer is proposed to decouple the student's cognitive pattern and random factors from the data through smoothing and subtraction operations, then recombine them using a gating mechanism or adaptive parameter fusion strategy. To more effectively diagnose students' knowledge mastery, we employ a decay-based attention mechanism that focuses on random behaviors at adjacent time steps. We conducted comprehensive experiments based on real-world datasets and targeted datasets with added random noise. The experimental results demonstrated the effectiveness of the proposed method.

An efficient state-aware Coarse-Fine-Grained model for Knowledge Tracing

Knowledge tracing models student exercise records to dynamically assess their knowledge levels, providing targeted guidance for education and learning.Existing knowledge tracing models lack the utilization of global information in question representation and have not overcome the issue of long-term dependency on the sequence of student responses.To address these issues, we propose an Enhanced Question Representation and Historical Performance Fusion Knowledge Tracing model (QRHKT).First, we construct a heterogeneous graph structure by combining the inclusion relations between questions and concepts, transition relations between questions, and co-occurrence relations between concepts, and enhance question representations through graph neural network algorithms.To address the long-term dependency issue, we categorize the knowledge states into current knowledge states and historically important knowledge states from the perspective of the importance of a student's historical knowledge state.The current knowledge state is obtained through a long short-term memory network, and historically important knowledge states are generated by weighted aggregation based on importance coefficients.Finally, by integrating these two types of knowledge states with question representation, we predict the student's answering performance.Experimental results show that our proposed QRHKT achieves better knowledge tracing results on three public datasets.

With the ongoing development of online education platforms, knowledge tracing (KT) has become a critical task that can help online education platforms provide personalized education. KT aims to find out students’ knowledge states and predict whether students can correctly answer the question according to their exercise history. However, existing works fail to incorporate question information and ignore some useful contextual information. In this paper, we propose a novel Sequential Self-Attentive model for Knowledge Tracing (SSAKT). SSAKT utilizes question information based on Multidimensional Item Response Theory (MIRT) which can capture the relations between questions and skills. Then SSAKT uses a self-attention layer to capture the relations between questions. Unlike traditional self-attention networks, the self-attention layer in SSAKT uses Long Short-Term Memory networks (LSTM) to perform positional encoding. Moreover, a context module is designed to capture the contextual information. Experiments on four real-world datasets show that SSAKT outperforms existing KT models. We also conduct a case study that shows our model can effectively capture the relations between questions and skills.