What type of study is this?

This is a Human Clinical Trial study.

September 5, 2025Open Access

Interpretable Knowledge Tracing via Transformer-Bayesian Hybrid Networks: Learning Temporal Dependencies and Causal Structures in Educational Data

Key Points

The model achieves an 8.7% increase in AUC compared to existing knowledge tracing models.
It reduces RMSE for performance prediction by 12.3%, improving accuracy in educational data interpretation.
The joint training objective aligns temporal patterns with causal structures, enhancing learning outcomes.
Models trained on 3.2 million interactions illustrate effective unification of temporal and causal reasoning.

Abstract

Knowledge tracing, the computational modeling of student learning progression through sequential educational interactions, represents a critical component for adaptive learning systems and personalized education platforms. However, existing approaches face a fundamental trade-off between predictive accuracy and interpretability: deep sequence models excel at capturing complex temporal dependencies in student interaction data but lack transparency in their decision-making processes, while probabilistic graphical models provide interpretable causal relationships but struggle with the complexity of real-world educational sequences. We propose a hybrid architecture that integrates transformer-based sequence modeling with structured Bayesian causal networks to overcome this limitation. Our dual-pathway design employs a transformer encoder to capture complex temporal patterns in student interaction sequences, while a differentiable Bayesian network explicitly models prerequisite relationships between knowledge components. These pathways are unified through a cross-attention mechanism that enables bidirectional information flow between temporal representations and causal structures. We introduce a joint training objective that simultaneously optimizes sequence prediction accuracy and causal graph consistency, ensuring learned temporal patterns align with interpretable domain knowledge. The model undergoes pre-training on 3.2 million student–problem interactions from diverse MOOCs to establish foundational representations, followed by domain-specific fine-tuning. Comprehensive experiments across mathematics, computer science, and language learning demonstrate substantial improvements: 8.7% increase in AUC over state-of-the-art knowledge tracing models (0.847 vs. 0.779), 12.3% reduction in RMSE for performance prediction, and 89.2% accuracy in discovering expert-validated prerequisite relationships. The model achieves a 0.763 F1-score for early at-risk student identification, outperforming baselines by 15.4%. This work demonstrates that sophisticated temporal modeling and interpretable causal reasoning can be effectively unified for educational applications.

Read Full Paperexternally

Demander à l'IA

Bookmark

View Full Paper