Scholarlink

<p>Cognitive diagnosis, pivotal for AI-enhanced learning, faces the challenge of fusing robust modeling of complex student-exercise-knowledge relationships with psychometric theoretical consistency: (1) performance degradation from over-smoothing induced by polarized knowledge associations in graph attention networks, and (2) limited interpretability due to the opaque nature of deep learning architectures. We present GEAR-CD, a GCN-enhanced graph attention framework with adaptive relation pruning that addresses these limitations through three key innovations: First, hierarchical graph attention unifies interaction modeling across heterogeneous relationships (knowledge concepts, exercises, and learners). Second, GCN-based convolutional kernels with automated edge pruning mitigate attention-driven over-smoothing. Third, theoretically-grounded design ensures alignment with Item Response Theory (IRT) principles. Comprehensive evaluations on Junyi, Assistments and EdNet datasets demonstrate GEAR-CD’s superiority, achieving 6.85% and 2.05% relative improvements over baseline and state-of-the-art models respectively in prediction accuracy (ACC=81.67%), while maintaining exceptional stability (<InlineEquation ID="IEq1"> <EquationSource Format="TEX">\(\sigma&lt;\)</EquationSource> </InlineEquation>0.0001). Visualization analyses confirm both diagnostic robustness (via radar plots) and theoretical validity (t-SNE manifolds linearity <InlineEquation ID="IEq2"> <EquationSource Format="TEX">\(\hbox {R}^{2}\)</EquationSource> </InlineEquation>=0.93), establishing GEAR-CD as a credible solution for operational learning systems.</p>

错误：搜索内容不能为空，请输入英文关键词
错误：关键词超出字数限制，请精简
高级检索

Variance-stabilized cognitive diagnosis via GCN-enhanced graph attention with adaptive relation pruning

  • 期刊论文

  • 出版模式：

    开放获取

  • 发表日期：

    2025年12月4日

查看全文
  • Xiaoli Zhang,
  • Zixi Dai,
  • Guifu Zhu,
  • Sicui Wang,
  • Qian Qian

摘要

Cognitive diagnosis, pivotal for AI-enhanced learning, faces the challenge of fusing robust modeling of complex student-exercise-knowledge relationships with psychometric theoretical consistency: (1) performance degradation from over-smoothing induced by polarized knowledge associations in graph attention networks, and (2) limited interpretability due to the opaque nature of deep learning architectures. We present GEAR-CD, a GCN-enhanced graph attention framework with adaptive relation pruning that addresses these limitations through three key innovations: First, hierarchical graph attention unifies interaction modeling across heterogeneous relationships (knowledge concepts, exercises, and learners). Second, GCN-based convolutional kernels with automated edge pruning mitigate attention-driven over-smoothing. Third, theoretically-grounded design ensures alignment with Item Response Theory (IRT) principles. Comprehensive evaluations on Junyi, Assistments and EdNet datasets demonstrate GEAR-CD’s superiority, achieving 6.85% and 2.05% relative improvements over baseline and state-of-the-art models respectively in prediction accuracy (ACC=81.67%), while maintaining exceptional stability ( \(\sigma<\) 0.0001). Visualization analyses confirm both diagnostic robustness (via radar plots) and theoretical validity (t-SNE manifolds linearity \(\hbox {R}^{2}\) =0.93), establishing GEAR-CD as a credible solution for operational learning systems.