Research map / Label-efficient and robust learning / Knowledge distillation
Knowledge Tracing Machines: Factorization Machines for Knowledge Tracing
Read the paperCheck your idea against 108,967 papers
AI-extracted summary. Written by AI from the paper's title only (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 item-level bias to skill, wins, and fails features | KTM on Assistments · Assistments | AUC: +0.07 AUC | Helped |
| Add item-level bias to skill, wins, and fails features | KTM on Berkeley · Berkeley | AUC: +0.09 AUC | Helped |
| Encode wins and fails separately instead of only attempt count | KTM on Assistments · Assistments | AUC: +0.07 AUC | Helped |
| Encode wins and fails separately instead of only attempt count | KTM on Berkeley · Berkeley | AUC: +0.01 | Helped |
| Add extra side information (ablation) | KTM on Assistments · Assistments | AUC: 0.7589 -> 0.8186 | Helped |
| Increase embedding dimension from 0 to 20 (ablation) | KTM (items, skills, wins, fails) on Assistments · Assistments | AUC: 0.7589 -> 0.7502 | No clear effect |
| Increase embedding dimension from 0 to 20 (ablation) | KTM (items, skills, wins, fails) on Berkeley · Berkeley | AUC: 0.7753 -> 0.7780 | Helped |
| Add skill features to item features (ablation) | KTM on Fraction · Fraction | AUC: 0.666 -> 0.667 | No clear effect |
| Add skill features to item features (ablation) | KTM on TIMSS · TIMSS | AUC: 0.695 -> 0.695 | No clear effect |
| Increase embedding dimension from 0 to 20 (ablation) | MIRTb on Fraction · Fraction | AUC: 0.6662 -> 0.6672 | No clear effect |
| Use an item-level bias rather than skill-only features | KTM on Fraction · Fraction | AUC | No clear effect |
| Increase embedding dimension from 0 to 20 (ablation) | KTM on Assistments with extra features · Assistments | AUC: 0.815 -> 0.819 | No clear effect |
Closest papers by meaning
- An Autoencoder-Like Nonnegative Matrix Co-Factorization for Improved Student Cognitive Modeling (NeurIPS 2024 · similarity 0.86)
- Uncertainty-aware Knowledge Tracing (AAAI 2025 · similarity 0.86)
- Rethinking and Improving Student Learning and Forgetting Processes for Attention based Knowledge Tracing Models (AAAI 2025 · similarity 0.85)
- Predictive, scalable and interpretable knowledge tracing on structured domains (ICLR 2024 · similarity 0.85)
- Extended LSTMs for Knowledge Tracing: Peeking Inside the Black Box (Student Abstract) (AAAI 2025 · similarity 0.85)
- Neighborhood-Aware Negative Sampling for Student Knowledge and Behavior Modeling (AAAI 2025 · similarity 0.84)
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.