HDTR-KT: Mutually Regulated Knowledge Tracing with Hierarchical Local Evolution and Dual-Timescale Global Cognition
5 affiliations
- 1School of Engineering Education and Engineering Culture Innovation, Hunan Institute of Engineering, Xiangtan 411104, China
- 2School of Computer Science and Engineering, Hunan University of Science and Technology, Xiangtan 411201, China
- 3School of Information and Electrical Engineering, Hunan University of Science and Technology, Xiangtan 411201, China
- 4School of Physics and Electronic Science, Changsha University of Science and Technology, Changsha 410114, China
- 5School of Electrical and Information Engineering, Hunan Institute of Technology, Hengyang 421002, China
Abstract
Knowledge tracing aims to infer students’ evolving knowledge states from historical question–response interactions to predict future performance. Despite the progress of recent deep models, existing approaches often lack an explicit mechanism for determining how different types of learning evidence should be transferred, retained, and coordinated across cognitive states with different abstraction levels and temporal characteristics. To address this limitation, this study proposes HDTR-KT, a knowledge tracing framework that models cognitive evolution through hierarchical evidence transition and dual-timescale state regulation. At the local level, HDTR-KT establishes an asymmetric transition from question-level experience to concept-level mastery, where question-specific increments are selectively transformed into concept messages rather than directly updating both states with identical interaction evidence. A constrained forgetting mechanism further preserves the hierarchical retention relationship between item memory and concept mastery. At the global level, different evidence sources are assigned to states with distinct temporal dynamics: prediction residuals drive an adaptive short-term state to capture transient deviations, whereas concept-level evidence is conservatively accumulated into a long-term state through a bounded update process. The fused global context subsequently regulates local-state forgetting, forming a closed-loop evolution mechanism between global cognition and localized memory. Extensive experiments on three real-world educational datasets demonstrate that HDTR-KT achieves consistently competitive predictive performance compared with representative baselines.
Related
- Dynamic analysis and spatiotemporal evolution of multi-stage knowledge dissemination under AI-enabled dual-channel “Interpersonal–Human-Machine” interaction
- Two-Timescale Fine-tuning Provably Learns New Features for Two-Layer ReLU Networks
- Fractional Spike-Frequency Adaptation for Multi-Timescale Negative Feedback in an LGMD2 Inspired Neuromorphic Model
- Inferring Multi-Timescale Neural Dynamics with Switching Linear Dynamical Systems
- Two-Timescale Antenna Positioning for Pinching-Antenna System Based on Statistical Channel Information
BibTeX
@article{yang2026hdtrkt,
title = {{HDTR-KT: Mutually Regulated Knowledge Tracing with Hierarchical Local Evolution and Dual-Timescale Global Cognition}},
author = {Liujun Yang and Sudan Xu and Jingqiang Zhao and Jie Jin and Fei Yu and Lv Zhao},
journal = {Mathematics},
year = {2026},
month = oct,
doi = {10.3390/math14193626},
url = {https://www.mdpi.com/2227-7390/14/19/3626},
note = {CC BY 4.0},
}
RIS
TY - JOUR
TI - HDTR-KT: Mutually Regulated Knowledge Tracing with Hierarchical Local Evolution and Dual-Timescale Global Cognition
AU - Liujun Yang
AU - Sudan Xu
AU - Jingqiang Zhao
AU - Jie Jin
AU - Fei Yu
AU - Lv Zhao
PY - 2026
DA - 2026/10/07
JO - Mathematics
DO - 10.3390/math14193626
UR - https://www.mdpi.com/2227-7390/14/19/3626
AB - Knowledge tracing aims to infer students’ evolving knowledge states from historical question–response interactions to predict future performance. Despite the progress of recent deep models, existing approaches often lack an explicit mechanism for determining how different types of learning evidence should be transferred, retained, and coordinated across cognitive states with different abstraction levels and temporal characteristics. To address this limitation, this study proposes HDTR-KT, a knowledge tracing framework that models cognitive evolution through hierarchical evidence transition and dual-timescale state regulation. At the local level, HDTR-KT establishes an asymmetric transition from question-level experience to concept-level mastery, where question-specific increments are selectively transformed into concept messages rather than directly updating both states with identical interaction evidence. A constrained forgetting mechanism further preserves the hierarchical retention relationship between item memory and concept mastery. At the global level, different evidence sources are assigned to states with distinct temporal dynamics: prediction residuals drive an adaptive short-term state to capture transient deviations, whereas concept-level evidence is conservatively accumulated into a long-term state through a bounded update process. The fused global context subsequently regulates local-state forgetting, forming a closed-loop evolution mechanism between global cognition and localized memory. Extensive experiments on three real-world educational datasets demonstrate that HDTR-KT achieves consistently competitive predictive performance compared with representative baselines.
SN - 2227-7390
ER -