AI Paper Atlas

Research map / Label-efficient and robust learning / Knowledge distillation

XES3G5M: A Knowledge Tracing Benchmark Dataset with Auxiliary Information

Zitao Liu, Qiongqiong Liu, Teng Guo, Jiahao Chen, Shuyan Huang, Xiangyu Zhao, Jiliang Tang, Weiqi Luo, Jian Weng

NeurIPS 2023 · Label-efficient and robust learning › Knowledge distillation · approach: Self and data-free distillation · 10 citations (OpenAlex)

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 changedWhereMeasuredEffect
add question/KC content with early fusion (ablation)simpleKT · XES3G5M test (5-fold)AUC: 0.8163 -> 0.8277Improved
add question/KC content with early fusion (ablation)AKT · XES3G5M test (5-fold)AUC: 0.8207 -> 0.8292Improved
use early fusion instead of add fusion for auxiliary info (ablation)AKT · XES3G5M test (5-fold)AUC: 0.8228 -> 0.8292Improved
add KC Route information on top of content (ablation)simpleKT · XES3G5M test (5-fold)AUC: 0.8277 -> 0.8262Hurt
add auxiliary question content (ablation)qDKT · XES3G5M test (5-fold)AUC: 0.8225 -> 0.8228No clear effect
use late fusion instead of early fusion with KC Cont (ablation)simpleKT · XES3G5M test (5-fold)AUC: 0.8277 -> 0.8251Hurt
include timestamps (DKT-F vs DKT)DKT · XES3G5M test (5-fold)AUC: 0.7852 -> 0.7940Improved
add question ID features alongside KC (IEKT/QIKT vs KC-only models)DLKT · XES3G5M test (5-fold)AUC: 0.7852 -> 0.8280Improved

Closest papers by meaning

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.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy