Research map / Label-efficient and robust learning / Knowledge distillation
KeenKT: Knowledge Mastery-State Disambiguation for Knowledge Tracing
Zhifei Li, Lifan Chen, Jiali Yi, Xiaoju Hou, Yue Zhao, Wenxin Huang, Miao Zhang, Kui Xiao, Bing Yang
Read the paperCheck your idea against 137,217 papers
AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.
Measured effects reported in the paper
| What was changed | Where | Measured | Effect |
|---|---|---|---|
| add distributional contrastive learning (ablation) | KeenKT · ASSISTments2009 | AUC: 0.8445 -> 0.8606 | Improved |
| add diffusion denoising reconstruction (ablation) | KeenKT · ASSISTments2009 | AUC: 0.8432 -> 0.8606 | Improved |
| add NIG distribution embedding (ablation) | KeenKT · ASSISTments2009 | AUC: 0.8427 -> 0.8606 | Improved |
| add NIG distribution embedding (ablation) | KeenKT · Algebra2005 | AUC: 0.9218 -> 0.9346 | Improved |
| add distributional contrastive learning (ablation) | KeenKT · Bridge2006 | AUC: 0.8175 -> 0.8255 | Improved |
| add diffusion denoising reconstruction (ablation) | KeenKT · Bridge2006 | AUC: 0.8143 -> 0.8255 | Improved |
| add NIG distribution embedding (ablation) | KeenKT · Bridge2006 | AUC: 0.8125 -> 0.8255 | Improved |
| KeenKT vs best baseline on ACC (UKT) | KeenKT · Algebra2005 | ACC: 0.8781 -> 0.8772 | No clear effect |
| KeenKT vs UKT on ACC | KeenKT · Bridge2006 | ACC: 0.8531 -> 0.8517 | Hurt |
| KeenKT vs best baseline on AUC | KeenKT · POJ | AUC: 0.6902 -> 0.7306 | Improved |
| KeenKT vs best baseline on ACC | KeenKT · POJ | ACC: 0.6556 -> 0.7008 | Improved |
| larger confidence coefficient gamma (0.4 vs above 3.2) (ablation) | KeenKT · AL2005 vs POJ | ACC | Mixed |
Closest papers by meaning
- Uncertainty-aware Knowledge Tracing (AAAI 2025 · similarity 0.90)
- Rethinking and Improving Student Learning and Forgetting Processes for Attention based Knowledge Tracing Models (AAAI 2025 · similarity 0.87)
- Predictive, scalable and interpretable knowledge tracing on structured domains (ICLR 2024 · similarity 0.86)
- Cognitive Fluctuations Enhanced Attention Network for Knowledge Tracing (AAAI 2025 · similarity 0.86)
- DeepKD: A Deeply Decoupled and Denoised Knowledge Distillation Trainer (NeurIPS 2025 · similarity 0.85)
- ABKD: Pursuing a Proper Allocation of the Probability Mass in Knowledge Distillation via $\alpha$-$\beta$-Divergence (ICML 2025 · similarity 0.85)
Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.
