Research map / Label-efficient and robust learning / Knowledge distillation
Enhancing the Knowledge Tracing via a Plug-In Guided Diffusion Model
Shuaishuai Zu, Jihao Zhao, Biao Qin
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 GOOD plug-in diffusion module | DisKT · Assist12 | AUC: 0.7598 -> 0.7981 | Improved |
| add GOOD plug-in to AKT | AKT · Ednet | AUC: 0.7003 -> 0.7308 | Improved |
| add GOOD vs HD plug-in denoising | AKT · Assist12 | AUC: HD-AKT 0.7710 -> AKT-GOOD 0.7844 | Improved |
| add GOOD to FoLiBiKT on small dataset | FoLiBiKT · Spanish | AUC: 0.8399 -> 0.8515 | Improved |
| replace person-wise noise with token-wise noise (ablation) | GOOD · Assist09 and Ednet | AUC / ACC | Improved |
| add TemporalConv in knowledge-aware adaptive layer norm (ablation) | GOOD · Assist09 and Ednet | AUC / ACC | Improved |
| raise lambda beyond 1.0 (to 8) (ablation) | GOOD · four datasets | AUC | Mixed |
| add GOOD to FoLiBiKT, prediction distance to labels | FoLiBiKT · Assist09 | KL divergence: 0.5695 -> 0.5275 | Improved |
| add GOOD to AKT, training+inference time | AKT · Assist09 | time per epoch: 1.56s -> 2.80s | Hurt |
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)
- Cognitive Fluctuations Enhanced Attention Network for Knowledge Tracing (AAAI 2025 · similarity 0.87)
- Predictive, scalable and interpretable knowledge tracing on structured domains (ICLR 2024 · similarity 0.87)
- PLD: A Choice-Theoretic List-Wise Knowledge Distillation (NeurIPS 2025 · similarity 0.85)
- Can Students Beyond the Teacher? Distilling Knowledge from Teacher’s Bias (AAAI 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.
