Research map / Architectures and efficiency / Neural architecture search
Evolutionary Neural Architecture Search for Transformer in Knowledge Tracing
Shangshang Yang, Xiaoshan Yu, Ye Tian, Xueming Yan, Haiping Ma, Xingyi Zhang
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 |
|---|---|---|---|
| ENAS-KT architecture instead of SAINT+ | Transformer KT · EdNet | AUC: 0.7916 -> 0.8062 | Improved |
| ENAS-KT instead of NAS-Cell | KT · EdNet | AUC: 0.7796 -> 0.8062 | Improved |
| use selected features instead of all features (concat) (ablation) | Transformer KT · EdNet | AUC: 0.7937 -> 0.7958 | Improved |
| hierarchical fusion instead of concat (ablation) | Transformer KT · EdNet | AUC: 0.7958 -> 0.7987 | Improved |
| add convolution local operations (ablation) | Transformer KT · EdNet | AUC: 0.7987 -> 0.8012 | Improved |
| search architecture (vs fixed Conv 1x3) (ablation) | ENAS-KT · EdNet | AUC: 0.8012 -> 0.8062 | Improved |
| remove searched architecture (use SAINT+ model) (ablation) | ENAS-KT · EdNet | AUC: 0.8062 -> 0.7987 | Hurt |
| remove hierarchical fusion (use concat) (ablation) | ENAS-KT · EdNet | AUC: 0.8062 -> 0.8041 | Hurt |
| remove selected features (use all) (ablation) | ENAS-KT · EdNet | AUC: 0.8062 -> 0.8030 | Hurt |
| increase SAINT hidden size to 192 | SAINT · EdNet | AUC: 0.7825 -> 0.7828 | No clear effect |
| increase SAINT+ hidden size to 192 | SAINT+ · EdNet | AUC: 0.7916 -> 0.7921 | No clear effect |
| use cheaper search (small supernet) (ablation) | ENAS-KT · EdNet | AUC: 0.8062 -> 0.8036 | Hurt |
Closest papers by meaning
- Rethinking and Improving Student Learning and Forgetting Processes for Attention based Knowledge Tracing Models (AAAI 2025 · similarity 0.85)
- Cognitive Fluctuations Enhanced Attention Network for Knowledge Tracing (AAAI 2025 · similarity 0.84)
- Predictive, scalable and interpretable knowledge tracing on structured domains (ICLR 2024 · similarity 0.84)
- Neural Collapse Inspired Knowledge Distillation (AAAI 2025 · similarity 0.84)
- Uncertainty-aware Knowledge Tracing (AAAI 2025 · similarity 0.84)
- Mechanism and Emergence of Stacked Attention Heads in Multi-Layer Transformers (ICLR 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.
